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.
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.
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-test-driven-development
Use when implementing any feature or bugfix, before writing implementation 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-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
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.
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.
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.
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.
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".
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.
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.
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
speclet-spec
Convert a draft document into an executable spec.json with trackable stories
speclet-ticket
Convert a large draft into individual tickets for isolated implementation sessions
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
simple-task-management
This skill should be used when the user asks to "generate tasks from a spec", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions working from specification documents. Provides guidance for transforming specifications into structured, actionable task lists organized under missions.
spec-task-management
This skill should be used when the user asks to "analyze a specification", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions working from specification documents. Provides comprehensive guidance for transforming specifications into structured, actionable task lists optimized for AI coding agents.
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-sync
Sync workflows for Workbench CLI. Use when aligning local work items with GitHub issues, creating branches, or reconciling doc backlinks.
workbench-work-items
Work item management for Workbench CLI. Use when creating, updating, linking, or closing work items and tracking execution status.
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-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.
anipy-cli
This skill should be used when the user asks to play, watch, stream, search, download, or binge anime; continue watching or check anime history; install, setup, configure, update, or fix anipy-cli; change video player or set anime quality; troubleshoot anime playback issues; or mentions anipy-cli by name. Triggers on "play anime", "watch frieren", "stream one piece dubbed", "download anime episodes", "binge naruto 1-10", "show anime history", "next episode", "continue watching", "change player to mpv", "set quality to 1080", "anipy-cli not working", "player not found", "anipy-cli", "anime from terminal".
spec-writing
This skill should be used when the user wants to create project specifications, feature specifications, design system documentation, or update existing specs. Triggers on "create spec", "plan project", "design system", "plan feature", "write specification", "generate SPEC.md", "document my project", "scaffold a spec", "plan my app", "spec out a feature", "create a project plan", "create a CLAUDE.md", "document architecture", "set up my project", "bootstrap a new app", "help me plan", "redesign my UI", "audit my design", "update my spec", or "revise the spec". Covers interview-based specification workflow with codebase analysis, tech stack recommendations, gap analysis, design audit, and optional SPEC/ supplements.
suno
This skill should be used when the user wants to compose songs for Suno AI, write lyrics, create style prompts, or generate Suno v5 metatags. Supports J-pop, K-pop, EDM, ballads, rock, and Latin genres, plus album/EP composition, variations, and song continuations. Also handles reference-based composition ("like YOASOBI", "in the style of Aimer") and J-pop tier presets ("anisong", "mainstream", "doujin"). Triggers on "write a song", "Suno prompt", "Suno metatags", "style of music", "song lyrics", "Suno AI", "acoustic version", "create an album", "extend this song", "like [artist]", "in the style of", "/suno", "anisong", "doujin", "negative prompting", "ad-libs".
project-init
|
dev-workflow
|
agents-md-generator
Automatically generate comprehensive AGENTS.md files that teach AI agents how to work with a repository's structure, conventions, and guidelines
caps-format-validator
Validate CAPS (Coding Agent Playbook Spec) playbooks for correctness, completeness, and compatibility with Claude Code and Goose
Page 1152 of 1445 · 72242 results