paulrberg
122 verified skills3,993 total stars
create-skill
Use to create/scaffold/init a new agent skill in `.agents/skills` by default or `~/.agents/skills` with `--global`.
data-ai68
evm-atlas
Use for targeted EVM chain, account, transaction, RPC, explorer, and bridge data: chain name/ID, native symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop, Layerswap, LayerZero, LI.FI, Relay, Socket, Symbiosis enrichment.
data-ai68
coingecko-open-page
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
tools68
autoresearch
Use for autoresearch or "optimize X overnight/in a loop"; sets up bounded iterative trials for a measurable optimization target.
research68
agents-introspection
Retrospect on a task against local Codex/Claude Code transcripts; propose durable fixes (AGENTS.md, skills).
development68
agents-context-management
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, and installed project skills.
documentation68
claude-handoff
Orchestrate one to five Sonnet subagents to implement an approved Claude Code plan.
development68
repo-rename
Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.
tools68
frontend-design
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible responsive code, and rendered visual verification.
development68
yeet
Use for GitHub PR/issue/discussion workflows: create/update PRs or issues, post comments, start discussions; triggers include yeet.
documentation68
commit
Commit staged or intended changes: craft a Conventional Prefix or Natural Language message, then commit — with --all, --staged, --close, or --push.
tools68
vitest
Use for Vitest in TypeScript React/Next.js: write, run, or debug unit/component tests, mocks, testing utilities, and coverage.
development68
cli-gh
Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.
tools68
codex-handoff
Orchestrate one to five Codex CLI agents to implement an approved Claude Code plan.
tools68
git-squash
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
tools68
skill-map
Use to find agent skill installs, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.
testing68
cli-just
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
tools67
html-debrief
Use for interactive HTML debriefs or saved HTML findings/reports from the current task.
development67
audit-stale-comments
Audit JavaScript, TypeScript, and Go comments for verified stale, orphaned, misleading, or redundant claims.
development67
night-shift
Autonomous overnight codebase improvement with bounded runtime, evidence-gated changes, and verification.
development67
fresh-eyes-sweep
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.
testing67
html-playground
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.
tools67
work
Orchestrate end-to-end implementation: execute directly or delegate independent tracks, integrate, and verify the requested outcome.
testing66
spreadsheets
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, transform, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.
testing66
bump-deps
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
testing66
tailwind-css
Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.
development66
skill-doctor
Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.
testing66
coingecko-historical
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
tools66
cli-cast
Use for Foundry cast/on-chain actions: prepare, simulate, sign, or broadcast transactions; call contracts; sign messages; encode/decode ABI/calldata; or make RPC calls. For read-only balances/history, prefer evm-atlas.
tools66
code-polish
Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope.
development66
find-tool
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
tools66
bump-release
Cut a release: bump versions, write changelogs, commit, tag.
documentation66
effect-ts
Use for nontrivial Effect-TS work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, or @prb/effect-next.
testing66
coingecko-cli
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.
tools66
debrief
Use for debriefs or saved findings/reports from the current task.
business66
large-file-refactor
Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.
tools66
grill-me
Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
testing66
playground
Use to create interactive single-file HTML playgrounds/explorers/tools with visual controls, live preview, and prompt copy-out.
tools66
todo-archive
Archive checked TODO.md tasks into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
testing66
diagnosing-bugs
Use when diagnosing bugs, debugging failures, chasing regressions, explaining broken/throwing/failing/slow behavior, or building a repro/root-cause loop before fixing code.
development64
loop-skill
Run another agent skill repeatedly (default 3 iterations), then report the net result once.
data-ai64
oracle-codex
This skill should be used when the user asks to consult Codex/GPT for planning or code review, or wants a second opinion on code. Trigger phrases include "ask Codex", "consult Codex", "second opinion on code", "consult the oracle". NOT for implementation tasks.
development63
update-skills
Use ONLY to check or update the project-scoped agent skills installed under .agents/skills so they match the current state of the repo. Do not trigger for creating, finding, or installing skills, or for README/AGENTS.md updates.
testing63
diagram-monochrome
This skill should be used when the user asks to create a monochrome technical diagram, schematic, or systems/architecture diagram in black-and-white line-art style. Trigger phrases include "create a diagram", "monochrome diagram", "systems diagram", "draw a schematic".
databases63
md-docs
Use ONLY to update or initialize README.md, CLAUDE.md, or AGENTS.md. Do not trigger for other Markdown files.
documentation63
agents-context
Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files. Updates existing skills only; do not create skills.
documentation62
evm-chains
Use for targeted EVM chain resolution and on-chain account data: target chain name/ID, RPC/explorer/native symbol, RouteMesh, balances, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; bridge/cross-chain Bungee, LayerZero, LI.FI, Socket enrichment.
data-ai62
code-review
Use for code/PR review, audits, bug/security checks, reviewing diffs or changes, and finding issues in code.
development62
agent-self-reflection
Use to retrospect on a task against historical Codex and Claude Code chat transcripts in the current project, identify recurring agent mistakes, and recommend or apply durable fixes such as AGENTS.md updates or new skills.
development62
code-simplify
Use for simplifying recently changed code: clean up, refactor for clarity, reduce complexity, improve readability, or maintainability.
development62
diagram-monochrome
This skill should be used when the user asks to create a monochrome technical diagram, schematic, or systems/architecture diagram in black-and-white line-art style. Trigger phrases include "create a diagram", "monochrome diagram", "systems diagram", "draw a schematic".
databases52
oracle-codex
This skill should be used when the user asks to consult Codex/GPT for planning or code review, or wants a second opinion on code. Trigger phrases include "ask Codex", "consult Codex", "second opinion on code", "consult the oracle". NOT for implementation tasks.
development52
etherscan-api
This skill should be used when the user asks to "check ETH balance", "query ERC-20 balance", "get wallet balance", "check token holdings", "fetch NFT transfers", "ERC-721 transfer history", "ERC-1155 transfer history", "find first funding transaction", "trace fund origin", "who funded this address", "query Etherscan", or mentions Etherscan API, blockchain balance queries, NFT transfer history, multi-chain balance lookups, or wallet provenance tracing.
development52
coingecko-api
This skill should be used when the user asks for crypto prices, market data, market cap, trending coins, historical or OHLC data, token lookup by contract address, coin search, token logos, global crypto stats, or mentions CoinGecko API.
development52
coderabbit
This skill should be used when the user asks to "triage coderabbit", "check coderabbit comments", "analyze coderabbit review", "fetch coderabbit findings", "coderabbit PR", "review coderabbit suggestions", "run coderabbit review", "coderabbit review", "review with coderabbit", or mentions analyzing CodeRabbit PR comments or running CodeRabbit CLI review locally.
tools47
biome-js
This skill should be used when the user asks to "configure Biome", "extend biome config", "set up BiomeJS", "add biome overrides", "biome lint-staged", "fix biome errors", or mentions biome.jsonc, Biome linting, or Biome formatting configuration.
development47
process-cleanup
This skill should be used when the user asks to "find zombies", "kill zombie processes", "clean up zombies", "check for zombie processes", "reap zombies", or mentions zombie process detection, cleanup, or process state monitoring.
testing47
delayed-command
This skill should be used when the user asks to "run npm test after 30 minutes", "git commit after 1 hour", "wait 2h then deploy", "sleep 45m and run build", "after 10m run prettier", or provides a duration followed by a shell command to execute later.
development47
skill-map
Use to find agent skill installs, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.
testing5
fresh-eyes-sweep
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.
testing5
todo-archive
Archive checked TODO.md tasks into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
testing5
evm-atlas
Use for targeted EVM chain, account, transaction, RPC, explorer, and bridge data: chain name/ID, native symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop, Layerswap, LayerZero, LI.FI, Relay, Socket, Symbiosis enrichment.
data-ai5
bump-deps
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
testing5
yeet
Use for GitHub PR/issue/discussion workflows: create/update PRs or issues, post comments, start discussions; triggers include yeet.
documentation5
bump-release
Cut a release: bump versions, write changelogs, commit, tag.
documentation5
autoresearch
Use for autoresearch or "optimize X overnight/in a loop"; sets up bounded iterative trials for a measurable optimization target.
research5
playground
Use to create interactive single-file HTML playgrounds/explorers/tools with visual controls, live preview, and prompt copy-out.
tools5
audit-stale-comments
Audit JavaScript, TypeScript, and Go comments for verified stale, orphaned, misleading, or redundant claims.
development5
agents-introspection
Retrospect on a task against local Codex/Claude Code transcripts; propose durable fixes (AGENTS.md, skills).
development5
naming-refactor
Refactor naming and repository structure exhaustively while preserving behavior and external contracts.
development5
frontend-design
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible responsive code, and rendered visual verification.
development5
tailwind-css
Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.
development5
skill-doctor
Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.
testing5
cli-cast
Use for Foundry cast/on-chain actions: prepare, simulate, sign, or broadcast transactions; call contracts; sign messages; encode/decode ABI/calldata; or make RPC calls. For read-only balances/history, prefer evm-atlas.
tools5
agents-context-management
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, and installed project skills.
documentation5
code-polish
Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope.
development5
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).
tools5
repo-rename
Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.
tools5
cli-gh
Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.
tools5
cli-just
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
tools5
html-debrief
Use for interactive HTML debriefs or saved HTML findings/reports from the current task.
development5
vitest
Use for Vitest in TypeScript React/Next.js: write, run, or debug unit/component tests, mocks, testing utilities, and coverage.
development5
large-file-refactor
Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.
tools5
coingecko-historical
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
tools5
commit
Commit staged or intended changes: craft a Conventional Prefix or Natural Language message, then commit — with --all, --staged, --close, or --push.
tools5
grill-me
Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
testing5
coingecko-open-page
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
tools5
effect-ts
Use for nontrivial Effect-TS work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, or @prb/effect-next.
testing5
find-tool
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
tools5
git-squash
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
tools5
debrief
Use for debriefs or saved findings/reports from the current task.
business5
html-playground
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.
tools5
work
Orchestrate end-to-end implementation: execute directly or delegate independent tracks, integrate, and verify the requested outcome.
testing5
spreadsheets
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, transform, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.
testing5
create-skill
Use to create/scaffold/init a new agent skill in `.agents/skills` by default or `~/.agents/skills` with `--global`.
data-ai5
night-shift
Autonomous overnight codebase improvement with bounded runtime, evidence-gated changes, and verification.
development5
coingecko-cli
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.
tools5
agent-self-reflection
Use to retrospect on a task against historical Codex and Claude Code chat transcripts in the current project, identify recurring agent mistakes, and recommend or apply durable fixes such as AGENTS.md updates or new skills.
development4
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
content-media4
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
tools4
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
development4
diagnosing-bugs
Use when diagnosing bugs, debugging failures, chasing regressions, explaining broken/throwing/failing/slow behavior, or building a repro/root-cause loop before fixing code.
development4
coderabbit
This skill should be used when the user asks to "triage coderabbit", "check coderabbit comments", "analyze coderabbit review", "fetch coderabbit findings", "coderabbit PR", "review coderabbit suggestions", "run coderabbit review", "coderabbit review", "review with coderabbit", or mentions analyzing CodeRabbit PR comments or running CodeRabbit CLI review locally.
tools4
summarize
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
content-media4
evm-chains
Use for targeted EVM chain resolution and on-chain account data: target chain name/ID, RPC/explorer/native symbol, RouteMesh, balances, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; bridge/cross-chain Bungee, LayerZero, LI.FI, Socket enrichment.
data-ai4
agents-context
Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files. Updates existing skills only; do not create skills.
documentation4
find-skills
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.
data-ai4
loop-skill
Run another agent skill repeatedly (default 3 iterations), then report the net result once.
data-ai4
code-simplify
Use for simplifying recently changed code: clean up, refactor for clarity, reduce complexity, improve readability, or maintainability.
development4
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
development4
coingecko-api
This skill should be used when the user asks for crypto prices, market data, market cap, trending coins, historical or OHLC data, token lookup by contract address, coin search, token logos, global crypto stats, or mentions CoinGecko API.
development4
notion-cli
Use the Notion CLI (`ntn`) to interact with the Notion API, manage workers, and upload files. Use when the user asks to "call the Notion API", "deploy a worker", "upload a file to Notion", "create a page", "query a database", or any task involving the `ntn` command.
tools4
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
development4
update-skills
Use ONLY to check or update the project-scoped agent skills installed under .agents/skills so they match the current state of the repo. Do not trigger for creating, finding, or installing skills, or for README/AGENTS.md updates.
testing4
vercel-react-best-practices
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.
development4
code-review
Use for code/PR review, audits, bug/security checks, reviewing diffs or changes, and finding issues in code.
development4
obscura
Use Obscura — a Rust headless browser with a Chrome DevTools Protocol server — for fast page fetches, JS execution, scraping, and CDP automation. Drop-in CDP replacement for Chrome with Puppeteer or Playwright. Trigger on requests to "open a page", "fetch a URL with JS", "scrape a site", "render this page", "automate browser via CDP", or any task where Chrome would be too heavy. Also use when the user mentions stealth fingerprinting, tracker blocking, `navigator.webdriver` masking, or evading basic bot detection.
tools4
etherscan-api
This skill should be used when the user asks to "check ETH balance", "query ERC-20 balance", "get wallet balance", "check token holdings", "fetch NFT transfers", "ERC-721 transfer history", "ERC-1155 transfer history", "find first funding transaction", "trace fund origin", "who funded this address", "query Etherscan", or mentions Etherscan API, blockchain balance queries, NFT transfer history, multi-chain balance lookups, or wallet provenance tracing.
development4
md-docs
Use ONLY to update or initialize README.md, CLAUDE.md, or AGENTS.md. Do not trigger for other Markdown files.
documentation4
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
development4
process-cleanup
This skill should be used when the user asks to "find zombies", "kill zombie processes", "clean up zombies", "check for zombie processes", "reap zombies", or mentions zombie process detection, cleanup, or process state monitoring.
testing4
oracle-codex
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think", "second opinion on code", "consult the oracle", "ask the oracle", or mentions using an AI oracle for planning or code review. NOT for implementation tasks.
development4