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.
pattern-extraction
Extracts reusable patterns from code changes
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.
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.
react-component-create
Create new React components following project patterns and best practices. Includes proper typing, testing, and documentation.
resilience-check
Checklist for reliability engineering
security-audit
Procedure for analyzing code or dependencies for vulnerabilities
test-suite-create
Creates a comprehensive test suite for a feature
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.
docs-update
Standard procedure for updating documentation
dependency-audit
Audit npm dependencies for security vulnerabilities, outdated packages, and license compliance.
database-migration-create
Safely creates database migrations
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
speclet-loop
Execute one autonomous iteration - implement the next story from spec.json
speclet-council
Run parallel reviews on draft/spec/ticket inputs and emit Council artifacts
speclet-draft
Generate a collaborative draft document with clarifying questions for a new feature
speclet-learn
Generate explanatory lessons after completing speclet stories to develop mechanical coding fluency
workbench-docs
Documentation workflows for Workbench CLI. Use when creating or updating specs, ADRs, runbooks, guides, or general docs, and when syncing backlinks or change notes.
workbench-work-items
Work item management for Workbench CLI. Use when creating, updating, linking, or closing work items and tracking execution status.
workbench-sync
Sync workflows for Workbench CLI. Use when aligning local work items with GitHub issues, creating branches, or reconciling doc backlinks.
workbench-architecture
Architecture and ADR workflows for Workbench CLI. Use when documenting system design, decisions, tradeoffs, or rationale that must be tracked over time.
workbench-github
GitHub workflows for Workbench CLI. Use when creating pull requests from work items or wiring GitHub-specific actions.
workbench-quality
Generate and inspect repo-native testing evidence for Workbench quality reports.
context7-search
Retrieve real-time technical documentation and code snippets from third-party libraries using the Context7 V2 API.
project-init
|
dev-workflow
|
kubernetes-health-check
Verify Kubernetes cluster health, resource availability, and readiness before deploying applications
agents-md-generator
Automatically generate comprehensive AGENTS.md files that teach AI agents how to work with a repository's structure, conventions, and guidelines
Page 1477 of 1487 · 74319 results
