tim-hub
88 verified skills120 total stars
choosing-k8s-release-strategy
Picks the right Kubernetes Deployment update strategy (RollingUpdate / Recreate / Blue-Green / Canary) for the situation. Use when configuring a new Deployment, changing rollout config, or deciding how to ship a risky change.
testing2
optimize-skill-reminder
Explains the optimize-skill PostToolUse hook and how to disable it. Use when asking about or managing this hook.
tools2
lodge
Use when the user asks to "lodge", "lodge specs", "archive", "clean up specs", "move to lodge", or wants to move completed spec directories out of the active workspace.
tools2
set-up
Use when the user asks to "set up entrepreneur tools", "install marketing plugins", "bootstrap my Claude for startup work", or "entrepreneur setup". Installs PM, marketing, growth, and inference-sh plugins.
tools2
openspec-verify-change
Verifies that implementation matches an OpenSpec change before archiving. Use when checking completeness before closing a change.
testing2
openspec-new-change
Scaffolds a new OpenSpec change without generating artifacts yet. Use when starting a new change workflow.
tools2
openspec-explore
Explores ideas, designs, or requirements before or during an OpenSpec change. Use when investigating an approach or clarifying requirements.
content-media2
setup-openspec
Initializes OpenSpec in a project by copying config and schemas from powerball templates. Use when setting up OpenSpec for the first time.
databases2
openspec-apply-change
Implements the tasks in an OpenSpec change. Use when starting or working through tasks in a change.
tools2
agent-browser
Automates browser workflows — visiting URLs, clicking, filling forms, scraping, and taking screenshots. Use when automating web interactions or UI testing.
tools2
openspec-sync-specs
Syncs delta specs from an OpenSpec change into the main specs without archiving. Use when applying spec changes without closing the change.
data-ai2
openspec-continue-change
Advances an OpenSpec change through the artifact workflow (proposal → specs → design → tasks). Use when progressing a change to the next planning stage.
content-media2
openspec-archive-change
Archives a completed OpenSpec change after tasks are done. Use when finalizing or closing out a change.
tools2
openspec-propose
Generates a full OpenSpec proposal with design, specs, and tasks in one step. Use when quickly planning a feature end-to-end.
content-media2
kb
Saves insights, decisions, and learnings from the current conversation to the project knowledge base. Use when the user wants to remember something or after solving a non-obvious problem.
testing2
language-translate
Translates text between any two languages while preserving source format. Use when the user needs to translate plain text, code, or markdown content.
development2
kb-search
Searches the project knowledge base for stored insights and notes. Use when looking up previously documented information.
development2
skill-review
Reviews skills for clarity, consistency, and adherence to this repo's conventions. Use when auditing or editing a skill.
testing2
crud
Scaffolds CRUD endpoints, database models, and REST resources. Use when generating create/read/update/delete operations for an entity.
data-ai2
auth
Implements authentication, OAuth, sessions, payments, and billing. Use when adding auth flows, route protection, RBAC, or payment webhooks.
development2
deploy
Deploys to Vercel or Netlify, runs health checks, and monitors post-deploy. Use when deploying to production or checking deployment status.
testing2
notebook-lm
Creates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
development2
fix-issue
Implements a fix for a GitHub issue. Use when given an issue number or URL to resolve.
tools2
tag
Tags the current git repository with a new version tag. Use when marking a release point in git history.
tools2
creative-writing
Generates written content — blog posts, social posts, emails, and marketing copy — matched to the project's existing voice. Use when the user needs written material.
testing2
multica
Runs Multica CLI commands by mapping the user's request to the right `multica <command>` invocation. Use when the user asks to do anything with Multica — issues, agents, workspaces, autopilots, skills, squads, or the daemon.
tools2
translate-markdown
Translates a markdown file to a target language, preserving structure. Use when the user needs a markdown file translated.
tools2
language-translate
Translates text between any two languages while preserving source format. Use when the user needs to translate plain text, code, or markdown content.
development2
ci
Diagnoses and fixes CI/CD failures from GitHub Actions logs. Use when a build is broken, CI is red, or a pipeline has failed.
development2
distill-session
Distills a session's repeatable workflow into a new project skill in .claude/skills/. Use when a session solved a non-trivial, repeatable problem and the workflow is worth capturing for reuse.
tools2
build
Use when the user asks to "build", "execute a plan", "start implementing", "work through tasks", "run the plan", or wants to implement tasks from a previously created plan in .powerball/specs/.
development2
plan
Use when the user asks to "plan", "create a plan", "design a solution", "how should I implement", "design an approach for", "what's the best way to build", "architect a solution", or wants an implementation plan for a feature, refactor, or change. Also use when the user describes a feature or change that would benefit from structured planning before coding.
development2
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans
tools2
writing-checklist
Use when a plan needs verification checkpoints to measure whether completed work meets requirements and quality standards. Called by the plan skill — not invoked directly by users.
testing2
fix-issue
This skill should be used when the user asks to "fix issue", "resolve issue", "address bug in issue", "fix
tools2
translate-markdown
Translates a markdown file to a target language, preserving structure. Use when the user needs a markdown file translated.
tools2
build-knowledge
Capture and save development knowledge — what was done, why, challenges faced, and key decisions — to a persistent knowledge base folder. Use this skill after completing a feature, fixing a bug, finishing a plan, resolving a tricky issue, or when the user says 'save what we did', 'document this work', 'build knowledge', 'capture learnings', 'save development notes', 'log this work', or wants to record development context for future reference. Also trigger when wrapping up a significant piece of work that involved non-obvious decisions or debugging. This skill MUST run as a subagent (never in main context) to avoid polluting the conversation.
development2
jira-ticket-analyzer
Fetch and analyze Jira tickets to produce actionable development plans. Use this skill whenever the user provides a Jira ticket number (e.g., XY-12345), a Jira URL, or asks to analyze/plan work for a Jira issue. Also trigger when the user says things like 'what needs to be done for [ticket]', 'plan the work for [ticket]', 'analyze [ticket]', 'look at this Jira ticket', or mentions working on a specific ticket. This skill fetches the ticket via the Atlassian MCP server, analyzes the problem, searches the codebase for relevant files, and produces a structured development plan including reproduction steps (for bugs), implementation steps, and test coverage guidance.
tools2
rtk-setup
Use this skill when the user wants to install or configure rtk (Rust Token Killer), a token-optimized CLI proxy for Claude Code. Triggered by "install rtk", "set up rtk", "configure rtk", or as part of the get-started flow.
tools2
auth
Implements authentication, OAuth, sessions, payments, and billing. Use when adding auth flows, route protection, RBAC, or payment webhooks.
development2
agent-browser
Automates browser workflows — visiting URLs, clicking, filling forms, scraping, and taking screenshots. Use when automating web interactions or UI testing.
tools2
bump-plugin-version
Bumps version, commits, and tags a Claude Code plugin. Use when releasing a new plugin version.
tools2
crud
Scaffolds CRUD endpoints, database models, and REST resources. Use when generating create/read/update/delete operations for an entity.
data-ai2
push
Push the current branch to remote, setting upstream if needed. Use when the user asks to push, push to remote, push changes, or sync with remote.
tools2
create-pr
Use when the user asks to "create a PR", "open a pull request", "submit changes", "push and create PR", "send this for review", "make a PR", "pr this", or wants to turn their current work into a reviewed pull request. Also use when the user finishes a build and wants to get their changes merged. This skill handles branch creation, PR formatting with mermaid diagrams, and automated review — use it even if the user just says "PR" or "ship it".
development2
dig-knowledge
Search the development knowledge base for past work, decisions, and lessons learned on a project. Use this skill when the user asks 'how did we fix X', 'what did we do last time', 'any past notes on this', 'check knowledge base', 'dig knowledge', 'what do we know about this project', or asks questions about past development context. Also trigger during explore and plan workflows to silently load relevant project history. If no knowledge base is configured or the project has no entries, skip silently — never block the user's workflow.
development2
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
testing2
explore
Use when the user asks to "explore", "explore the codebase", "map the architecture", "understand the codebase", "what does this module do", "give me an overview of", "analyze how X works", "walk me through", "how is this project structured", or wants a structured overview of a project or module saved for future reference. Also use when the user seems unfamiliar with a codebase area and would benefit from a saved exploration before planning or building.
development2
harness-implement
Use when the user asks to "implement end to end", "build this feature from scratch", "harness implement", "full pipeline", "do everything", "explore plan build and PR", or gives a feature description and expects the entire pbl pipeline to run autonomously — from exploration through to a reviewed pull request. Use this even when the user describes a feature and says "just do it" or "handle it". This is the hands-off, full-auto version of the pbl workflow.
development2
kb-setup
Sets up or updates the knowledge base config at ~/.kb/config.json. Use when configuring the KB or when kb/kb-search fails due to missing config.
data-ai2
update-overview
Use when the user asks to "update overview", "refresh diagrams", "regenerate overall.md", "show the big picture", "update project diagrams", or wants to see the cumulative state of what's been built. Also called by the lodge skill after moving specs to lodge.
tools2
writing-tasks
Use when a plan needs discrete implementation tasks with step-by-step ordering, file targets, and dependency mapping. Called by the plan skill — not invoked directly by users.
tools2
skill-usage-report
Shows a report of skill invocations and usage frequency.
business2
commit
Stage all relevant changes and commit with an auto-generated conventional commit message. Use when the user asks to commit changes, commit work, make a commit, or save progress.
tools2
notebook-lm
Creates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
development2
update-skill
Refines an existing project skill in .claude/skills/ with new learnings from the current session. Use when updating or improving an existing skill, or when distill-session identifies the learning extends an existing skill rather than warranting a new one.
tools2
get-started
This skill should be used when the user asks to "set up claude code", "initialize plugins", "get started with powerball", or "run setup". Sets up global CLAUDE.md, statusline, Claude Code settings, and installs plugins.
tools2
deploy
Deploys to Vercel or Netlify, runs health checks, and monitors post-deploy. Use when deploying to production or checking deployment status.
testing2
creative-writing
Generates written content — blog posts, social posts, emails, and marketing copy — matched to the project's existing voice. Use when the user needs written material.
testing2
sync
Use when archiving specs to detect drift between spec artifacts and actual code changes. Called by the lodge skill at Step 1 — not invoked directly by users.
development2
designer
Analyze UI and UX for usability improvements across web, mobile, and CLI interfaces. Suggest and implement changes to make things easier to use and understand. Use when the user asks to review UI/UX, improve usability, simplify an interface, audit accessibility, or optimize user flows.
tools
planner
Create step-by-step plans for solving problems, debugging issues, building features, or architecting complex solutions. Always includes pros/cons analysis and risk consideration. Use when the user asks to plan, create a roadmap, break down a task, design an approach, outline steps, or needs a structured path forward.
development
tester
Write unit tests for code changes across multiple stacks including JavaScript/TypeScript (Jest, Vitest), React (Testing Library), PHP (PHPUnit), Python (pytest), Django (TestCase), Hono.js, Express.js, and Flutter (Dart). Use when the user asks to write tests, add test coverage, create unit tests, or when making code changes that need test coverage. Automatically suggests tests for new or modified code.
development
testing-skills-with-subagents
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
development
migrate-to-vinext
Migrates Next.js projects to vinext (Vite-based Next.js reimplementation for Cloudflare Workers). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM conversion, and Cloudflare deployment setup.
devops
executing-plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
testing
writing-plans
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
development
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-ai
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
development
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
testing
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
development
brainstorming
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
development
defense-in-depth
Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible
testing
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
testing
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
tools
coordinator
Orchestrate multiple skills through a phased workflow to solve problems, generate ideas, create plans, or build software. Use when the user asks to coordinate roles, run a full workflow, or when a task benefits from brainstorming, challenging, planning, and implementing in sequence.
development
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
data-ai
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
development
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
testing
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding
development
reviewer
Review code changes from git commit history for quality, security, and adherence to codebase patterns. Use when the user asks to review commits, review code changes, review git history, or perform a code review on recent changes.
development
sharing-skills
Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository
development
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
development
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
development
brainstormer
Generate brainstorm ideas from multiple thinking frameworks and perspectives. Use when the user asks to brainstorm, ideate, explore options, think through a problem, generate alternatives, or needs creative input on any topic.
development
challenger
Aggressively challenge solutions, implementations, designs, and ideas by finding potential issues across performance, UX, security, bugs, scalability, maintainability, and edge cases. Use when the user asks to challenge, critique, stress-test, poke holes in, or review code, architecture, or ideas.
development
condition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
testing
testing-anti-patterns
Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
development