Back to categories
Category

Agent Skills in category: Uncategorized

72242 skills match this category. Browse curated collections and explore related Agent Skills.

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.

cpa03
cpa03
0

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.

cpa03
cpa03
0

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.

cpa03
cpa03
0

obra-superpowers-test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

cpa03
cpa03
0

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

cpa03
cpa03
0

obra-superpowers-writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

cpa03
cpa03
0

pattern-extraction

Extracts reusable patterns from code changes

cpa03
cpa03
0

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.

cpa03
cpa03
0

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.

cpa03
cpa03
0

react-component-create

Create new React components following project patterns and best practices. Includes proper typing, testing, and documentation.

cpa03
cpa03
0

resilience-check

Checklist for reliability engineering

cpa03
cpa03
0

security-audit

Procedure for analyzing code or dependencies for vulnerabilities

cpa03
cpa03
0

test-suite-create

Creates a comprehensive test suite for a feature

cpa03
cpa03
0

typescript-refactor

Safely refactor TypeScript code while maintaining type safety and test coverage. Includes verification steps.

cpa03
cpa03
0

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.

cpa03
cpa03
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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".

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

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.

hairihou
hairihou
0

speclet-draft

Generate a collaborative draft document with clarifying questions for a new feature

danielcastro-dev
danielcastro-dev
0

speclet-learn

Generate explanatory lessons after completing speclet stories to develop mechanical coding fluency

danielcastro-dev
danielcastro-dev
0

speclet-spec

Convert a draft document into an executable spec.json with trackable stories

danielcastro-dev
danielcastro-dev
0

speclet-ticket

Convert a large draft into individual tickets for isolated implementation sessions

danielcastro-dev
danielcastro-dev
0

speclet-council

Run parallel reviews on draft/spec/ticket inputs and emit Council artifacts

danielcastro-dev
danielcastro-dev
0

speclet-loop

Execute one autonomous iteration - implement the next story from spec.json

danielcastro-dev
danielcastro-dev
0

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.

sequenzia
sequenzia
1

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.

sequenzia
sequenzia
1

workbench-architecture

Architecture and ADR workflows for Workbench CLI. Use when documenting system design, decisions, tradeoffs, or rationale that must be tracked over time.

bravellian
bravellian
0

workbench-github

GitHub workflows for Workbench CLI. Use when creating pull requests from work items or wiring GitHub-specific actions.

bravellian
bravellian
0

workbench-sync

Sync workflows for Workbench CLI. Use when aligning local work items with GitHub issues, creating branches, or reconciling doc backlinks.

bravellian
bravellian
0

workbench-work-items

Work item management for Workbench CLI. Use when creating, updating, linking, or closing work items and tracking execution status.

bravellian
bravellian
0

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.

bravellian
bravellian
0

workbench-quality

Generate and inspect repo-native testing evidence for Workbench quality reports.

bravellian
bravellian
0

context7-search

Retrieve real-time technical documentation and code snippets from third-party libraries using the Context7 V2 API.

barrychen38
barrychen38
0

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".

Linaqruf
Linaqruf
1

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.

Linaqruf
Linaqruf
1

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".

Linaqruf
Linaqruf
1

project-init

|

lanmogu98
lanmogu98
0

dev-workflow

|

lanmogu98
lanmogu98
0

agents-md-generator

Automatically generate comprehensive AGENTS.md files that teach AI agents how to work with a repository's structure, conventions, and guidelines

asadullah48
asadullah48
0

caps-format-validator

Validate CAPS (Coding Agent Playbook Spec) playbooks for correctness, completeness, and compatibility with Claude Code and Goose

asadullah48
asadullah48
0

Page 1152 of 1445 · 72242 results