
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Analyze code for useEffect anti-patterns and refactor to simpler alternatives. Use when the user says "you might not need an effect", "check effects", "useEffect audit", or asks to review useEffect usage.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Update the one-liner release description in scripts/release-body.js by analyzing commit titles since the last git tag. Use when the user asks to update the release description, release notes one-liner, or prepare release body for a new version.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Resolve on-screen seedit DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Automate a full seedit release by analyzing commits, updating the release body, bumping the version, regenerating the changelog, and finalizing the git tag. Use when the user says "release", "new version", "cut a release", "prepare release", or provides a version number to ship.
Review an open GitHub pull request, inspect feedback from Cursor Bugbot, CodeRabbit, CI, and human reviewers, decide which findings are valid, implement fixes on the PR branch, merge the PR into master when it is ready, and finalize any linked GitHub issue so it matches the make-closed-issue workflow after merge. Use when the user says "check the PR", "address bugbot comments", "handle CodeRabbit feedback", "review PR feedback", or "merge this PR".
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Resolve on-screen seedit DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Resolve on-screen seedit DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Review an open GitHub pull request, inspect feedback from Cursor Bugbot, CodeRabbit, CI, and human reviewers, decide which findings are valid, implement fixes on the PR branch, merge the PR into master when it is ready, and finalize any linked GitHub issue so it matches the make-closed-issue workflow after merge. Use when the user says "check the PR", "address bugbot comments", "handle CodeRabbit feedback", "review PR feedback", or "merge this PR".
Test and debug Android APK features using a local Android emulator. Manages emulator lifecycle, builds/installs the APK, runs instrumentation tests, captures logcat diagnostics, and debugs WebView automation (imgur, postimages uploads). Use when the user asks to test APK, debug Android, test uploads, run emulator tests, or says "test-apk".
Test and debug Android APK features using a local Android emulator. Manages emulator lifecycle, builds/installs the APK, runs instrumentation tests, captures logcat diagnostics, and debugs WebView automation (imgur, postimages uploads). Use when the user asks to test APK, debug Android, test uploads, run emulator tests, or says "test-apk".
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Analyze code for useEffect anti-patterns and refactor to simpler alternatives. Use when the user says "you might not need an effect", "check effects", "useEffect audit", or asks to review useEffect usage.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Analyze code for useEffect anti-patterns and refactor to simpler alternatives. Use when the user says "you might not need an effect", "check effects", "useEffect audit", or asks to review useEffect usage.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Update the one-liner release description in scripts/release-body.js by analyzing commit titles since the last git tag. Use when the user asks to update the release description, release notes one-liner, or prepare release body for a new version.
Test and debug Android APK features using a local Android emulator. Manages emulator lifecycle, builds/installs the APK, runs instrumentation tests, captures logcat diagnostics, and debugs WebView automation (imgur, postimages uploads). Use when the user asks to test APK, debug Android, test uploads, run emulator tests, or says "test-apk".
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Automate a full 5chan release — analyze commits, update release body and blotter, bump version, generate changelog, commit, tag, and push. Use when the user says "release", "new version", "cut a release", "prepare release", or provides a version number to ship.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Update the one-liner release description in scripts/release-body.js by analyzing commit titles since the last git tag. Use when the user asks to update the release description, release notes one-liner, or prepare release body for a new version.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Review an open GitHub pull request, inspect feedback from Cursor Bugbot, CodeRabbit, CI, and human reviewers, decide which findings are valid, implement fixes on the PR branch, merge the PR into master when it is ready, and finalize any linked GitHub issue so it matches the make-closed-issue workflow after merge. Use when the user says "check the PR", "address bugbot comments", "handle CodeRabbit feedback", "review PR feedback", or "merge this PR".
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Resolve on-screen 5chan DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Resolve on-screen 5chan DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Test and debug Android APK features using a local Android emulator. Manages emulator lifecycle, builds/installs the APK, runs instrumentation tests, captures logcat diagnostics, and debugs WebView automation (imgur, postimages uploads). Use when the user asks to test APK, debug Android, test uploads, run emulator tests, or says "test-apk".
Automate a full 5chan release — analyze commits, update release body and blotter, bump version, generate changelog, commit, tag, and push. Use when the user says "release", "new version", "cut a release", "prepare release", or provides a version number to ship.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Analyze code for useEffect anti-patterns and refactor to simpler alternatives. Use when the user says "you might not need an effect", "check effects", "useEffect audit", or asks to review useEffect usage.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Create a GitHub issue from recent changes, commit only relevant diffs on a short-lived task branch, push that branch, and open a PR into master that will close the issue on merge. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Review an open GitHub pull request, inspect feedback from Cursor Bugbot, CodeRabbit, CI, and human reviewers, decide which findings are valid, implement fixes on the PR branch, merge the PR into master when it is ready, and finalize any linked GitHub issue so it matches the make-closed-issue workflow after merge. Use when the user says "check the PR", "address bugbot comments", "handle CodeRabbit feedback", "review PR feedback", or "merge this PR".
Resolve on-screen 5chan DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Test and debug Android wrapper features for Bitsocial Web using a local Android emulator or attached device. Manages emulator lifecycle, builds and installs the wrapper when commands are provided, runs focused checks, captures logcat diagnostics, and debugs WebView or TWA behavior. Use when the user asks to test Android, debug WebView behavior, run emulator tests, or says "test-apk".
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Formats GitHub commit messages following Conventional Commits style with title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Create a GitHub issue from recent changes, commit only relevant diffs, close the issue with the commit hash, and add it to the bitsocialnet project board as Done. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Review an open GitHub pull request, inspect bot and human feedback, decide which findings are valid, implement fixes on the PR branch, and merge the PR into master when it is ready. Use when the user says "check the PR", "address review comments", "review PR feedback", or "merge this PR".
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, dead-code removal, or says "refactor pass".
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Automate a Bitsocial Web release by analyzing commits, choosing a version bump, updating package.json, verifying the release build, and preparing the tag or push steps. Use when the user says "release", "new version", "cut a release", "prepare release", or provides a version number to ship.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Resolve on-screen Bitsocial Web DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.
Create a GitHub issue from recent changes, commit only relevant diffs, close the issue with the commit hash, and add it to the bitsocialnet project board as Done. Use when the user says "make closed issue", "close issue", or wants to create a tracked, already-resolved GitHub issue for completed work.
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Test and debug Android wrapper features for Bitsocial Web using a local Android emulator or attached device. Manages emulator lifecycle, builds and installs the wrapper when commands are provided, runs focused checks, captures logcat diagnostics, and debugs WebView or TWA behavior. Use when the user asks to test Android, debug WebView behavior, run emulator tests, or says "test-apk".
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Analyze code for useEffect anti-patterns and refactor to simpler alternatives. Use when the user says "you might not need an effect", "check effects", "useEffect audit", or asks to review useEffect usage.
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Add or update i18next translation keys across all language files by spawning translator subagents. Use when the user asks to add a new translation, update existing translations, translate text, or work with i18n keys. Triggers on "translate", "add translation", "translation key", "i18n", "localization".
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Update the one-liner release description in scripts/release-body.js by analyzing commit titles since the last git tag. Use when the user asks to update the release description, release notes one-liner, or prepare release body for a new version.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Resolve all merge conflicts on the current branch non-interactively, validate the build, and commit. Use when the user says "fix merge conflicts", "resolve conflicts", or when git status shows conflicting files.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Formats GitHub issue titles and descriptions for tracking problems that were fixed. Use when proposing or implementing code changes, creating GitHub issues, or when the user asks for issue suggestions.
Review an open GitHub pull request, inspect bot and human feedback, decide which findings are valid, implement fixes on the PR branch, and merge the PR into master when it is ready. Use when the user says "check the PR", "address review comments", "review PR feedback", or "merge this PR".
Resolve on-screen Bitsocial Web DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.