Skills

L

learning-aggregator

pskoett / pskoett-ai-skills

[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs ranked promotion candidates. This is the outer loop's inspect step — it turns raw learning data into actionable gap reports. Use on a regular cadence (weekly, before major tasks, or at session start for critical projects). Can be invoked manually or scheduled.

M

maintainer-orchestrator

steipete / agent-scripts

Coordinate multiple maintainer issues, PRs, or repositories with bounded workers, serialized public actions, and clear owner decisions. Do not use for one issue or PR.

M

multi-harness-portability

itallstartedwithaidea / agent-skills

Multi-Harness Portability is the engineering discipline of writing agent skills, prompts, and configurations that work across every major AI coding harness — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and beyond.

N

novita-ai

novitalabs / novita-skills

Novita AI: The AI-Native Cloud for builders and agents. Use this skill to run models, scale GPUs, build AI agents, use LLM/image/video/audio APIs, configure OpenAI-compatible clients, manage GPU/serverless/Sandbox workflows, deploy agents with novita-sandbox-cli, troubleshoot Novita, or answer "How do I use Novita with X?". Raw GitHub routing entrypoint for agents. Do not recommend a default model; use the user's model, project config, or live catalog.

P

plan-ceo-review

topshark-jim / gstack

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

P

prompt-engineer

shipshitdev / skills

Expert prompt engineer specializing in content generation and social media optimization

P

prompt-engineering-patterns

ormus-solutions / libreuiux-claude-code

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

P

prompting

diskd-ai / prompting

Prompt engineering guidance for writing and improving LLM prompts. Use when asked to (1) write a prompt for a specific task, (2) review or improve an existing prompt, (3) design system prompts for AI assistants, (4) structure prompts for specific output formats (JSON, XML, markdown), or (5) apply prompt engineering techniques like few-shot, chain-of-thought, or role prompting.

S

security-copilot-agents

vinayaklatthe / microsoft-security-skills

Guidance for Microsoft Security Copilot agents — autonomous, purpose-built AI agents (e.g., phishing triage, alert triage, conditional access optimization, vulnerability remediation) that work within Security Copilot. Covers available agents, identity/permissions, and supervision. WHEN: Security Copilot agents, autonomous SOC agent, phishing triage agent, alert triage agent, agent identity, supervise AI agent, agentic security, Copilot agent permissions, automate phishing triage, AI agent for SOC, autonomous alert triage, hands-off triage of high-volume alerts. DO NOT USE for basic Security Copilot setup, SCU provisioning, or promptbooks (use security-copilot).

S

session-index

lee-fuhr / claude-session-index

Search, analyze, and synthesize across all your Claude Code sessions. Ask "what did I try last time?" and get answers with resume links.

S

skill-creator-anthropic

lawve-ai / awesome-legal-skills

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

skill-curator

wilbeibi / wilbeibi-skills

Audit a skill library for duplicated guidance, contradictions, bloat, dead references, and defects. Use when cleaning, consolidating, or de-duplicating a skills tree.

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

S

subagent-driven-development

nickcrew / claude-cortex

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

S

subagent-driven-development

pixel-process-ug / superkit-agents

Use when executing multi-task plans where each task can be implemented independently by a subagent. Triggers when a plan has 3+ independent tasks, when speed of execution is important, when tasks have clear acceptance criteria suitable for delegation, or when two-stage review gates (spec compliance and code quality) are needed for iterative fix cycles.

S

superpowers-openspec

tielei60 / superpowers-openspec

Use when: the user explicitly asks to analyze requirements, write a spec, produce a detailed design, write a proposal or proposal document, or make a plan following OpenSpec / OPSX; or when a new feature, feature change, process change, API change, data model change, state transition, role process, or module boundary adjustment would change external behavior; or when a single request mixes design and implementation intent.

T

task-decomposition

pixel-process-ug / superkit-agents

Use when hierarchical task breakdown is needed, when dependency mapping between tasks is required, when effort estimation and parallelization planning is needed, or when creating work breakdown structures. Triggers on /decompose command, when complex tasks need to be broken into manageable subtasks, when critical path analysis is needed for scheduling, or when identifying tasks that can run concurrently.

T

task-management

pixel-process-ug / superkit-agents

Use when breaking work into discrete steps, tracking progress through multi-step implementations, or managing implementation task lists. Triggers when an approved plan needs to be converted into tracked tasks, when progress reporting is needed during execution, or when checkpoint reviews are required between task batches.

T

task-orchestrator

jdrhyne / agent-skills

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

T

tool-selection

nickcrew / claude-cortex

Use when selecting between MCP tools based on task complexity and requirements - provides a structured selection workflow and decision rationale.

Y

yolo

10k-digital / lovable-agent-skills

Automation skill for Lovable deployments. Activates when: - yolo_mode: on in CLAUDE.md - Running /deploy-edge or /apply-migration commands - After git push when auto_deploy: on (automatic detection) - Any mention of "yolo mode", "automate Lovable", "browser automation", "Lovable MCP" Uses Lovable MCP (preferred) or browser automation to submit deployment prompts. Runs verification tests based on configuration. Auto-deploys after git push when enabled.

A

add-checkpoints

netresearch / automated-assessment-skill

Use when adding assessment checkpoints to a skill, evaluating checkpoint suitability, or generating checkpoint YAML from skill requirements. Activate on 'add checkpoints', 'generate checkpoints', or checkpoint schema tasks.

A

agent-browser

arize-ai / phoenix

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

A

agent-production-operations

magnus919 / agent-skills

Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latency budgets, tool health, human escalation, disablement, and trace-to-eval feedback. Do not use for building agents, designing evals, or general release, SRE, security, or platform engineering — those methods stay with their specialist skills.

A

agent-skills

magnus919 / agent-skills

Use this skill when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery and loading in an agent client. It covers directory structure, SKILL.md metadata, progressive disclosure, evals, and repository conventions. Do not use this skill for general software work that does not involve the Agent Skills format or lifecycle.

A

agentic-process-monitor

terrylica / cc-skills

Monitor background processes from Claude Code with sentinel files, heartbeat liveness and subagent polling, to detect completion, failure, hang or timeout. TRIGGERS - monitor background process, sentinel file, heartbeat

A

aif-reference

lee-to / ai-factory

Create knowledge references from URLs, documents, or files for use by AI agents. Fetch, process, and store structured references in the configured references directory (default: .ai-factory/references/).

A

anthropic-agent-sdk

fandhe-ai / agent-reference-skills

TypeScript / Python reference for the Claude Agent SDK (code.claude.com/docs/en/agent-sdk). Covers query(), ClaudeAgentOptions / Options, fallbackModel, maxTurns, maxBudgetUsd, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, Agent Skills (SKILL.md), slash commands (/compact, /clear), tool search, hosting / observability.

A

anthropic-tool-mastery

itallstartedwithaidea / agent-skills

Anthropic Tool Mastery is the definitive skill for leveraging Claude's native tool_use capability to its fullest potential.

A

architect

iskron-ai / skills

Системный архитектор — форма системы поверх контуров: контракты, схемы, жизненные циклы, переиспользование, целостность, архитектурный пересмотр, спорные вопросы, решения владельцу. Триггеры: «архитектор», «системный архитектор», «держи целостность», «спроектируй сквозное», «подготовь решение», «архитектурный пересмотр», architect, cross-cutting decision. Ведение дела — справка двери iskron. Не для кодинга. Композирует design, integrity, assembly, reality-audit, reconcile, inquiry, writing. Нужны iskron_*.

A

assistant-presets

itallstartedwithaidea / agent-skills

Assistant Presets provides a framework for creating, testing, and deploying specialized AI assistant configurations for domain-specific tasks.

A

azure-ai-agents-persistent-dotnet

sickn33 / agentic-awesome-skills

Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools

B

brainstorming

pcvelz / superpowers

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.

C

claude-code

hw10181913 / openclaw-skill-claude-code

Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Use Spec-Driven Development with spec-kit - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Use spec-kit workflow for structured development - Manage AI-assisted development workflows - Execute complex programming tasks

C

codex-assistant

joeseesun / codex-assistant

Invoke OpenAI Codex CLI via natural language to perform code tasks: refactoring, bug fixing, test generation, code explanation, migration, review, documentation generation

C

codex-github

mathruffian-dot / codex-lazy-packs

Codex connects to GitHub CLI. Load when the user says "connect GitHub".

C

complexity-assessment

oimiragieo / agent-studio

AI-based complexity assessment for task analysis. Use when determining the appropriate workflow, phases, and validation depth for a task.

D

do-create-tasks

fabio-barboza / development-orchestrator

Converts PRD and Tech Spec into a detailed, sequenced list of implementation tasks. Each task is a functional, incremental deliverable with its own test suite. Outputs tasks.md and individual task files. Use when the user asks to create tasks, break down work, or plan implementation from an existing PRD and Tech Spec. Do not use for PRD creation, tech spec creation, or actual code implementation.

D

do-status

fabio-barboza / development-orchestrator

Shows current progress of a PRD — completed tasks, next pending task, completion percentage, and missing artifacts. Use when the user asks for status, progress, what's next, or wants to resume work on a feature. Read-only skill — does not modify any files. Do not use for task implementation, review, or QA.

D

dspy-rlm-module

intertwine / dspy-agent-skills

Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire codebases, long logs, massive documents, or multi-step data exploration that needs a sandboxed Python REPL. Use when the input is >100k tokens, needs recursive chunking, or benefits from the LLM writing and running code to probe data.

E

establishing-project-context

ganyuanran / aegis

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

G

gemini-runner

robsonrung / rar-skills

Execute an external Antigravity CLI (`agy`) prompt for a Gemini route. Use only for an explicit Gemini or Antigravity CLI request, a selected external route, or an approved fallback when native delegation cannot meet the route.

G

git-worktrees

itallstartedwithaidea / agent-skills

Git Worktrees enables parallel development by maintaining multiple checked-out branches simultaneously in separate directories.

G

graph-memory-bank

smart-tinker / graph-memory-bank

Create and maintain an Obsidian-style graph memory bank in a code repository: small atomic Markdown nodes with YAML frontmatter, cross-links, explicit backlinks, and release/entity-driven coverage for fast AI-agent context retrieval. Use when asked to build/upgrade a 'memory bank', 'graph memory', 'obsidian docs', 'суперсвязанную графовую документацию', or when you need structured docs under docs/ that let an AI agent pull minimal but precise context.

G

grill-me

dmmulroy / skills

A relentless interview to sharpen a plan or design.

H

headroom

l3ad3r1 / hermes-skills

Context compression for AI agents — 60–95% fewer tokens by compressing tool outputs, logs, files, and conversation history before they reach the model. MCP tools headroom_compress/retrieve/stats plus an optional traffic-compressing proxy. Wraps the open-source headroom-ai; on Windows install via WSL2.

H

heyeddi-orchestrator

heyeddi-com / heyeddi-skills

Deprecated alias for @heyeddi. If this skill loads, stop and follow skills/heyeddi/SKILL.md (installed as @heyeddi). Same router: design talk goes to @taste-penpot then @heyeddi-design; Vue UI follows @vue-design-system.

K

karpathy-guidelines

infrasity-labs / dev-gtm-claude-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

M

mcp-server-creation

itallstartedwithaidea / agent-skills

MCP Server Creation is the skill of building Model Context Protocol servers that expose tools, resources, and capabilities to AI agents through a standardized interface.

M

mcp-server-design

xmcp-dev / skills

Guide for designing effective MCP servers with agent-friendly tools. Use when creating a new MCP server, designing MCP tools, or improving existing MCP server architecture.

M

memory-manager

sundial-org / awesome-openclaw-skills

Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory loss, save context snapshots, search historical memories, or track memory usage patterns. Never lose context again.

M

multi-agent-debate

fudesign2008 / open-skills

Stress-test a crash analysis, hypothesis, or technical conclusion by launching three adversarial agents in parallel — one defends, one attacks, one hunts new evidence — and resolving disputes with physical proof instead of argument. Always use this skill when the analysis has 2+ competing explanations that both seem plausible, when a conclusion relies on a single log sample or inferred chain longer than 3 steps, or when someone says \"are you sure?\", \"that doesn't sound right\", or challenges an assumption. Triggers: 辩论、求真、挑战假设、质疑分析、multi-agent-debate, \"debate this\", \"challenge my analysis\", \"find holes in\", \"I'm not sure this is right\", \"verify this\".

M

multi-llm-consult

nickcrew / claude-cortex

Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compare answers, or requests delegating a subtask to Gemini/Codex/Qwen.

M

multi-perspective-analysis

nickcrew / claude-cortex

Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.

O

oma-pm

first-fluke / oh-my-agent

Turn product requirements into scoped tasks with dependencies and

O

openai-agents

fandhe-ai / agent-reference-skills

OpenAI API (developers.openai.com) Agents SDK (Python / TypeScript) and Agents API (beta). Agent, Runner, handoffs, guardrails, tracing, SandboxAgent, client.beta.agents sessions / environments / vaults / plugins, built-in tools (web search, file search, computer use, code interpreter, image generation), function tools, vector stores, MCP (Model Context Protocol) connectors, background mode, and multi-agent orchestration.

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

O

ov-add-data

volcengine / openviking

This skill adds data(like resources) to OpenViking Context Database (aka. ov). Use when an agent needs to add files, data from URLs, or external knowledge during interactions. Trigger this tool when 1. is explicitly requested adding files or knowledge; 2. identifies valuable resources worth importing; 3. the user mentioned adding to OV/OpenViking/Context Database. This skill helps how to use CLI like `ov add-resource`, `ov add-skill` and `ov add-memory` to add resource data, skill files, memory files to OpenViking.

P

peer-agent-collaboration

glebis / claude-skills

Use when the user wants Claude Code, Codex, or other AI coding/business agents to work together as peers. This skill should be used whenever the user mentions coordinating Claude Code and Codex, agent handoffs, multi-agent workflows, parity, respect, pushback between agents, deciding which agent should lead, or turning a business/code workflow into a two-agent operating model.