Skills

G

google-gemini

membranedev / application-skills

Google Gemini integration. Manage Users, Conversations. Use when the user wants to interact with Google Gemini data.

I

implement-plan-preflight

terrylica / cc-skills

Run the Preflight phase of the ITP workflow to create ADR and design spec artifacts. Use whenever the user asks to create an ADR, write a design.

I

inquiry

iskron-ai / skills

Используй для ЖИЗНИ вимарши и работы с ПОЛЕМ вопрошания — не постановка (это writing), а жизненный цикл: якорение, разрешение, закрытие, принятие как есть, вытеснение, кристаллизация, привязка к превращению. Триггеры: «разбери вимарши», «поле вопрошания», «закрой/оставь вимаршу», «разреши вопрошание», «триаж вимарш», work the field of inquiry, resolve the question, много висящих вимарш в orient, закрытие сессии. Не проход по всему графу (assembly). Нужны тулы iskron_*.

I

integrity

iskron-ai / skills

Используй для задач интеграции и целостности превращения. Триггеры: «интеграция», «интегрировать X с Y», «спецификация интеграции», integrate, integration spec — режим 0: сначала граф; «область интеграции изменения», integration scope, cold review — режим 1: холон + steward + узлы изменения; «проверь бяньхуа на целостность», «что затронет превращение», «кого заденет», integrity check — волновой фронт; «подкреплено ли графом», «не театр ли», claim audit — обратный аудит прозы. Distinct from assembly и design. Нужны iskron_*.

I

iterate-from-user

probabl-ai / skills

Source the next ML experiment proposal from the user via one of three entry points selected by `AskUserQuestion`: (a) a scientific article URL the agent must read and synthesize, (b) a resource link or path (GitHub issue / spec file / reference repo), or (c) free-text the user types directly. In every branch, the agent reads the source, synthesizes its understanding of what to implement, and confirms with the user *before* returning the Proposal block. Hand the confirmed Proposal back to `iterate-ml-experiment`, which writes it into `journal/NN_short_name.md` and seeks the user's design-note approval. Stops at "Proposal returned, user-confirmed"; never writes a design note, never authors acceptance criteria. TRIGGER when: `iterate-ml-experiment` is picking a sourcing strategy and the user picks `user` from the menu; the user volunteers a concrete idea ("I want to try X"); the user pastes or links a scientific article, GitHub issue, spec file, or reference repo and asks us to read it. SKIP when: the user wants to mine the previous report (use `iterate-from-skore`); the user is asking for a symbol lookup or pipeline mechanics (use the `python-api` skill); the work is evaluation mechanics on a single report (route to `evaluate-ml-pipeline`). HOW TO USE: open with an `AskUserQuestion` for the entry point — article-link / resource-link / free-text. In each branch: gather the source material with the appropriate tool (`WebFetch`, `gh issue view`, `Read`), synthesize what you understand into the three shaping questions, and **confirm with the user via plain text** (one or two sentences: "you'd like to implement X by changing src/<pkg>/<file>.py — right?") before returning the Proposal. Do not write any design note. Do not author acceptance criteria.

I

iterating-with-ai-and-mcp

skydoves / compose-performance-skills

Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a Kotlin file, trigger a hot reload, capture a device screenshot, evaluate the result against a design intent, and iterate without a human in the loop. Covers the seven HotSwan MCP tools (hotswan_get_status, hotswan_reload, hotswan_take_screenshot, hotswan_start_snapshot, hotswan_stop_snapshot, hotswan_select_variant, hotswan_build_and_install), the canonical edit-reload-screenshot loop, snapshot-based rollback, and when to fall back to a full install for schema changes. Use when the developer says "get the AI to tune this screen until it matches a mock", asks "can the AI see what changed?" or "can the AI screenshot the device?", sets up a Claude Code or Cursor workflow that needs MCP tool access, or wants AI-driven UI iteration.

M

maggy

alinaqi / maggy

Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.

M

mcp-installer

lintendo / axhub-skills

Install and configure MCP servers across desktop and CLI clients (Claude, Cline, Windsurf, Cursor, VSCode, Gemini CLI, Codex, Trae, Antigravity, etc.) on macOS/Windows/Linux, preferring @smithery/cli when supported and otherwise performing manual JSON config updates and path discovery.

O

openai-assistants

secondsky / claude-skills

OpenAI Assistants API v2 for stateful chatbots with Code Interpreter, File Search, RAG. Use for threads, vector stores, or encountering active run errors, indexing delays. ⚠️ Sunset August 26, 2026.

O

overthink

s0md3v / overthink

Use when the response requires complex reasoning, creativity, nuance, evaluation, decision-making, subjectivity, or communication-sensitive work. If the task is simple and the user has not manually invoked this skill, do not use it.

P

pipeline

yeachan-heo / oh-my-codex

Sunset stub — use $plan and $team directly instead

P

plugin-installer

igorwarzocha / opencode-workflows

Find, install, and configure OpenCode plugins from the catalog or community. Use proactively when user asks about plugins, requests new capabilities, or mentions extending OpenCode functionality. Examples: - user: "Is there a plugin for Tailwind CSS?" → list catalog, read tailwind plugin details, install if available - user: "How do I add a custom slash command?" → suggest command-creator skill or guide through opencode.json setup - user: "What plugins are available for database work?" → list catalog, filter for database-related plugins - user: "Install the playwright plugin" → read plugin file, add to opencode.json, verify installation

P

poteto-help

mdsmithaustin / pstack

Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

P

prompt-engineering

oakoss / agent-skills

Prompt engineering and agentic orchestration patterns. Use when crafting prompts for reasoning models, implementing chain-of-thought or Tree-of-Thoughts, designing ReAct loops, building few-shot examples, optimizing prompt performance, structuring system prompts, using extended thinking, or designing tool use workflows. Use for prompt templates, multi-step agent workflows, structured thinking protocols, and multimodal prompting.

S

self-reflection

ninehills / skills

Daily self-reflection and personal growth. Triggered by heartbeat at end of day. Review the day's experiences, extract lessons, update personality, and write a diary entry.

S

setup-ralph

glittercowboy / taches-cc-resources

Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

S

skill-creator

vercel-labs / portless

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

S

swarm

xgent-ai / skills

For /swarm, requests for multi-agent collaboration, deciding whether to spin up a team, or complex tasks that clearly need work split across people. First choose a single person, subagent, workflow, or team mechanism, then orchestrate roles, execution and acceptance.

Z

zenforge-soul

venhdev / skills

Bootstrap session context, align architectural posture, enforce strict execution gates, and govern SSOT invariants across the agent workflow.

A

agile-onboarding

djalmajr / skills

Onboarding guide for new team members in the agile flow with AI. Use when someone new joins the team and needs to understand how the planning, execution, and tracking flow works with AI agents.

B

beads-implement

btraut / skills

Implement Beads or beads_rust work items from an issue id. Use when the user runs $beads-implement <bead-id> or asks to implement a bead/epic; if it is an epic, implement all sub-tasks, committing after each one and only interrupting when blocked or a decision is needed.

B

bmad-workflow-builder

bmad-code-org / bmad-builder

Builds, edits, and analyzes workflows and skills. Use when the user requests to "build a workflow", "modify a workflow", "quality check workflow", or "analyze skill".

B

brainstorming

fradser / dotclaude

Designs new software features and multi-component changes for the current repo into implementation-ready BDD specs via autonomous codebase research, then commits the design for review (runs to completion without mid-design questions). Scope covers new features, greenfield design, and multi-component changes. Not for hardware/physical-system design, out-of-repo questions, single-file refactors, or known-root-cause bugs (those go to direct edits or systematic-debugging).

C

cheese-factory

paulnsorensen / easy-cheese

Parallelize an approved spec across 5+ independent behavioural curds into reviewable PRs, running the whole pipeline fanned out at once. Use when the user has such a spec — phrases like "/cheese-factory .cheese/specs/<slug>.md", "send through the factory", "parallelize this spec", "many curds", "fan out the implementation", "cheese-factory this". Runs inline and spawns full-peer general-purpose sub-agents per phase (decomposer, per-curd workers, wiring, post-merge review, PR planner), ending in 1–N reviewable PRs via `/pr-stack`. Use even when the user mentions `/fromagerie` — `/cheese-factory` is the portable harness-agnostic sibling. Supports `--hard` propagation and `--resume <slug>` to continue a crashed pipeline. Do NOT use for single coherent specs (`/cook`, `/ultracook`), fuzzy planning (`/mold`), review-only work (`/age`), or specs with fewer than 5 curds (`/ultracook`).

C

claude-memory

melvynx / aiblueprint

Create and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Comprehensive guidance on file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness.

E

example-skill

sendaifun / skills

Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.

G

gpt-review

davidondrej / skills

Launch an independent GPT-6.1-Sol Max code review and return it verbatim. Use only when the user explicitly invokes /gpt-review.

Use when guiding or implementing the Inkbox agent self-signup flow, including verification, resend-verification, signup restrictions, and optional signup fields like agent handles or mailbox local parts.

M

my-agent-browser

briqt / my-agent-browser

Browser automation guidance and patterns. Trigger this skill BEFORE starting any browser interaction (navigating pages, logging in, scraping, filling forms, testing UI) to learn the correct workflow and avoid common pitfalls. Also trigger when browser MCP tools misbehave: element not found, click does nothing, page crashes, timeout, "target closed", snapshot returns empty, or any unexpected browser behavior. This skill teaches you HOW to use the browser MCP tools effectively — without it you will hit avoidable failures like stale UIDs, heavy-page crashes, and silent navigation failures.

O

owasp-agentic

microsoft / hve-core

OWASP Agentic Security Top 10 knowledge base for identifying, assessing, and remediating AI agent system security risks.

R

reasoning-trace-optimizer

muratcankoylan / agent-skills-for-context-engineering

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

R

roblox-studio-workflow

ashexplained / roblox-skills

Use Roblox Studio MCP safely and productively from Claude. Use when connecting to Studio, inspecting a Roblox place, editing scripts or instances, inserting assets, generating models/materials, or playtesting through MCP tools.

Skill Finder. Helps discover and install ClawHub Skills. Answers 'what skill can X', 'find a skill'. Trigger words: 找 skill, find skill, search skill.

S

swain-doctor

cristoslc / swain

Auto-invoked at session start when swain-preflight detects issues. Also user-invocable for on-demand health checks. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run any time.

Create and manage Telnyx Missions — automated workflows, tasks, and sub-resources for AI-driven telecom operations. This skill provides JavaScript SDK examples.

T

thealgorithm

danielmiessler / lifeos

LifeOS — The universal AI Harness designed to move you from your current to ideal state in both life and work.

T

tools-ui

skills-101 / superpowers

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

V

volcengine-find-skills

volcengine / volcengine-agent-toolkit

List, select, and install Volcengine skills from the volcengine-skills marketplace. Use when a user asks which Volcengine skill or plugin handles a task, wants to browse every available skill, needs an optional skill that is not currently installed, or asks to install or check the installation status of a Volcengine skill. Also use to discover any core skill, including this finder. Use as a fallback during a Volcengine operation when the currently loaded or installed skills cannot cover the required product, tool, or workflow; inspect the full catalog, select the missing capability, and install it.

Z

zenforge-init

venhdev / skills

Scaffold repository task tracking, test harness anchor, dev environment profile, Git ignore privacy, documentation index, and agent constitution

A

add-agent

berriai / litellm-skills

Create a new AI agent on a live LiteLLM proxy. Asks for agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.

A

agile-router

djalmajr / skills

Routes to the appropriate agile skill based on context. Use when you need guidance on which skill to use — planning, ceremonies, tracking, prototype/UX, TDD, or memory.

A

ai-models

mnhkahn / cyeam-cli

AI free model lookup — fetch free model leaderboards for various platforms from cyeam.com, with filtering by platform/type/name. [Important] You must first read the original skill text to get the correct command format; do not guess.

A

ai-rag-pipeline

skills-101 / superpowers

Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabilities: research, fact-checking, grounded responses, knowledge retrieval. Use for: AI agents, research assistants, fact-checkers, knowledge bases. Triggers: rag, retrieval augmented generation, grounded ai, search and answer, research agent, fact checking, knowledge retrieval, ai research, search + llm, web grounded, perplexity alternative, ai with sources, citation, research pipeline

A

antigravity-obsidian

mathruffian-dot / antigravity-lazy-pack

Connect Obsidian project notes in AntiGravity (read and write the vault directly, without installing MCP). Load when the user says "connect Obsidian" or "set up Obsidian."

A

authoring-claude-md

sammcj / agentic-coding

Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't obvious from code inspection, (4) organising instructions into path-scoped rule files.

B

beads-create

btraut / skills

File Beads or beads_rust epics/issues from a finalized plan/spec AND do the polish pass (clarity, acceptance criteria, sizing, deps). Use when asked to create Beads from a plan/spec (OpenSpec, PRD, design doc), convert an external plan into issue tracker structure, or review/refine an existing Beads set.

B

br

dicklesworthstone / beads_rust

Official skill for beads_rust (`br`), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.

B

build-feature

lwlee2608 / agent-skills

Use when implementing a phased feature plan file. Builds each phase on its own branch and PR into a feature integration branch, reviews and fixes in rounds, merges, then runs the plan's demo and leaves the final merge to main to the user.

C

claude-managed-agents-webhooks

hookdeck / webhook-skills

Receive and verify Anthropic Claude Managed Agents (CMA) webhooks. Use when setting up Claude Managed Agents webhook handlers, debugging signature verification, or handling agent session and vault events like session.status_idled, session.status_terminated, session.thread_created, vault.created, or vault_credential.refresh_failed.

C

command-creator

feiskyer / claude-code-settings

Create Claude Code custom slash commands with proper structure, frontmatter, and best practices. Use this skill whenever the user wants to create a new command, add a slash command, build a custom command, or mentions "create-command", "new command", "add command", or "make a command" for Claude Code. Also trigger when the user wants to turn a workflow into a reusable command.

F

factory-setup

tikalk / adlc-team-skills

Use when configuring the factory tracker provider for a repo (first factory run, missing .adlc/issues-provider.yml), verifying provider wiring, or switching trackers.

F

frappe-agent-interpreter

impertio-studio / frappe_claude_skill_package

Use when receiving vague or unclear ERPNext/Frappe development requests that need interpretation. Transforms requirements like 'make invoice auto-calculate' or 'add approval workflow' into concrete technical specifications. Determines which Frappe mechanisms to use and maps to the full 61-skill catalog. Keywords: vague requirement, clarify scope, translate business need, technical spec, implementation plan, what does this mean, unclear requirement, translate to code, how to build this.

G

graph-mode

rheinmir / setup

Enable the evidence-chain rule (R19) for the CHAT portion — every reasoning chain must terminate in observable evidence (observed/tool-record/graph-edge/web/parametric/absence), unlike fable5 (general reasoning discipline, no citation requirement). Use when the user says 'graph-mode', 'bật graph mode', 'evidence mode', or invokes /graph-mode. Token-heavy (forces more citations/file opens per answer) so it is NOT auto-injected every session — enable only when invoked manually. Once invoked it stays active for the rest of the session (toggle off with 'tắt graph mode' / 'graph-mode off' / 'normal mode').

G

grill-me

tkersey / dotfiles

Reduce unresolved user-owned judgments before planning or implementation. Research discoverable facts, resolve model-owned technical choices, order remaining decisions by dependency, ask only the material current frontier, and route questions that conversation cannot settle to the smallest deciding observation. Use explicitly for `$grill-me` or implicitly only when a non-discoverable user-owned decision materially blocks the requested outcome. Do not seize direct implementation when safe reversible defaults suffice.

L

laravel:code-review-requests

jpcaparas / superpowers-laravel

Request effective code reviews—specify focus areas, provide context, ask for architectural feedback, reference Laravel conventions

M

mastra

dhruvjainin / absolute

Absolute skills to 10x your development lifecycle

M

mastra

maddhruv / absolute

Absolute skills to 10x your development lifecycle

M

methodology-curator

athola / claude-night-market

Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.

M

migrating-deep-agents-to-pydantic-ai-harness

pydantic / skills

Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use `migrating-langchain-to-pydantic-ai` for plain LangChain, LangGraph, or LCEL migrations and `pydantic-ai-harness` for greenfield Harness usage.

How to drive Muxy 2 from a shell with the `muxy` command — start terminals that keep running, type into them, read and wait on their output, and manage projects and Git worktrees. Use this when you are an agent running inside a Muxy terminal (or any script on the same computer) and want work to run in its own terminal instead of blocking yours, or to drive the desktop app's built-in browser.