typescript
TypeScript and React/TSX coding conventions and patterns
api-design
REST API design patterns for endpoints, responses, errors, and conventions
testing
Testing strategy, patterns, and best practices for unit, integration, and e2e tests
security-check
Security audit patterns for identifying vulnerabilities and security issues
python
Python coding conventions, type hints, and FastAPI patterns
project-structure
Project organization conventions for files, modules, and directory structure
go
Go idioms, error handling, and API patterns
code-review
Systematic code review checklist for quality, correctness, and maintainability
database-migration-create
Safely creates database migrations
madappgang-claude-code-debugging-strategies
Universal debugging strategies and techniques applicable across all technology stacks. Use when approaching unknown bugs or need language-agnostic debugging methodology.
git-commit-standard
Generates conventional commits based on file changes. Analyzes diffs and creates properly formatted commit messages.
test-suite-create
Creates a comprehensive test suite for a feature
resilience-check
Checklist for reliability engineering
react-component-create
Create new React components following project patterns and best practices. Includes proper typing, testing, and documentation.
professor-for-testing-agentic-qe-skill-builder
Build comprehensive testing skills with TDD, quality engineering, and automated test generation. Use when creating test suites or improving testing practices.
planning-with-files
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
pattern-extraction
Extracts reusable patterns from code changes
obra-superpowers-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
obra-superpowers-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
obra-superpowers-test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
obra-superpowers-systematic-debugging
Systematic debugging approach with 4-phase root cause analysis. Use when troubleshooting complex bugs, identifying root causes, or following structured debugging methodology.
obra-superpowers-brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
muratcankoylan-agent-skills-for-context-engineering-memory-systems
Context management and persistent memory systems for AI agents. Use when optimizing context windows or building agent memory systems.
modu-ai-moai-adk-moai-tool-opencode
Multi-agent orchestration using MoAI framework for complex task coordination. Use when orchestrating multiple agents or building multi-agent workflows.
maxritter-claude-codepro-backend-models-standards
Backend development standards and best practices for API design, database, security, and performance. Use when designing or reviewing backend systems.
security-audit
Procedure for analyzing code or dependencies for vulnerabilities
typescript-refactor
Safely refactor TypeScript code while maintaining type safety and test coverage. Includes verification steps.
git-commit-message
Auto-generates conventional commit messages from git diffs with tiered format enforcement. Analyzes staged changes to produce meaningful commit messages following Conventional Commits specification.
ci-pipeline-update
Updates CI/CD pipelines for DevOps Engineer
api-endpoint-create
Standard procedure for creating robust API endpoints
code-review-checklist
Generates a code review checklist for the Code Reviewer agent
dependency-audit
Audit npm dependencies for security vulnerabilities, outdated packages, and license compliance.
docs-update
Standard procedure for updating documentation
rules-optimizer
Create and optimize .claude/rules/*.md files for repository-specific coding conventions. Use when asked to create, optimize, or review rules, when a pattern keeps recurring that Claude gets wrong, or when codifying a convention. Not for editing CLAUDE.md — edit that file directly.
session-insights
Analyze the current conversation for inefficiencies and improvement opportunities. Use when "how did this session go", "what went wrong", "what could I have done better", or reviewing session quality. Not for personal reflection — use retrospect. Not for logging work — use diary.
constructive-feedback
Transform harsh, vague, or emotionally charged feedback text into actionable form using the Situation-Behavior-Impact-Suggestion framework. Use when "sounds too harsh", "how should I say this", "draft feedback", or "rephrase this message".
code-critic
Brutally honest code review targeting over-engineering, premature abstraction, and defensive excess. Use when "is this over-engineered", "check complexity", "too much abstraction", or "what do you think of this code". Not for PR comments — use conventional-comments for that.
bonsai
Maintain and groom config files in the current repository. Use when "bonsai", "tidy up", "prune configs", "clean up", "spring cleaning", or reviewing config health. Not for code quality review — use code-critic for that.
1on1-prep
Prepare for 1on1 meetings using a Psychological Safety x Responsibility framework. Use when preparing for a 1on1, noticing behavioral changes, or planning a difficult conversation with a report.
conventional-comments
Format code review comments using Conventional Comments labels and decorations. Use when writing inline review comments on a PR diff. Not for creating PRs — use pr for that. Not for complexity analysis — use code-critic for that.
decision-log
Record or search technical decisions in a persistent SQLite database. Default mode records the most recent decision from conversation with alternatives and reasoning. Use with "search" argument to query past decisions.
devils-advocate
Structured critical analysis using parallel advocate and critic agents. Use when asked to evaluate a decision, play devils advocate, challenge an approach, or weigh pros and cons of architecture/technology choices.
diary
Append completed tasks and learnings to an Obsidian daily note. Use when "diary", "log", "record what I did", "end of day", or "wrap up". Not for session quality — use session-insights. Not for personal reflection — use retrospect.
npm-update-report
Dependency update workflow with vulnerability assessment and verification. Use when asked to check outdated packages, bump dependencies, run audit, do periodic dependency maintenance, or when security vulnerabilities are reported.
pr
Create or update a GitHub pull request. Use when asked to create a PR, submit for review, or push changes as a PR. Not for code review comments — use conventional-comments for that.
retrospect
Guided personal reflection that separates fact, interpretation, and emotion through structured inquiry. Use when "something feels off", "need to process this", "had a conflict", or decisions feel unclear. Not for technical decision analysis — use devils-advocate for that.
speclet-council
Run parallel reviews on draft/spec/ticket inputs and emit Council artifacts
speclet-loop
Execute one autonomous iteration - implement the next story from spec.json
speclet-ticket
Convert a large draft into individual tickets for isolated implementation sessions
speclet-spec
Convert a draft document into an executable spec.json with trackable stories
Page 1550 of 1560 · 77982 results
