ai-rag-patterns
Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking strategies,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,648 results
devops-engineer-agent
DevOps Engineer Agent — CI/CD pipelines, containerization and K8s, infrastructure as code, observability
harness-engineer-cli
Bootstrap a complete agent-first project OR retrofit an existing project with the harness framework — AGENTS.md, CLAUDE.md, execution plans, PRD, and…
gen-ai-local-files
Turn a local file into a URL for Picsart MCP tools.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
accept-no-substitutes
This skill should be used when agents generate placeholder tokens like "pseudo-", "mock-", "temporary", "TODO", "demo-", or similar incompleteness markers.…
polli
polli — an installable skill for AI agents, published by pollinations/pollinations.
refurbish-demos
Upgrade demo agent knowledge — clears old summaries, scrapes real pages via MCP Tavily (advanced mode), falls back to WebFetch, fixes icons, republishes. Pass…
ch-project-context
Initialize a project-level context management system with a structured docs/ directory, automatic session and subagent context injection, docs validation, and…
shadcn-ui
Give the assistant project-aware shadcn/ui context: components.json, composition patterns, CLI, registries, theming, and MCP. Use when working on web UI,…
qwen-mm-plugins-edu-agent
Generate step-by-step math problem-solving tutorial videos in Chinese (Mandarin). Use when: (1) a user provides a math problem and wants an explanation…
moai-connector-notion
Enterprise Notion integration with MCP server architecture, database operations, and content management
openclaw-multi-channel-ai-assistant
Self-hosted multi-channel AI assistant platform with unified Gateway, supporting WhatsApp, Telegram, Discord, and 20+ chat platforms with Claude, GPT, DeepSeek…
foreman
Delegate implementation work to external coding-agent CLIs (OpenAI Codex `codex exec`, Google Antigravity/Gemini `agy -p`, or any harness with an adapter)…
caveman-stats
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on…
council
Run a Karpathy-style LLM council (3-stage multi-agent evaluation) on top of the existing orca orchestration: N seats independently answer a question, the…
doyourmagic
Given a freshly-cloned external repo/tool, run clone→explore→verify→write to produce a bundle of RUNNABLE workflow skills under…
fable5
Reasoning protocol distilled from Claude Fable 5 — Floor check, multi-hypothesis diagnosis, adversarial self-review, Constraint Loop for hard output…
failure-flywheel
Capture each agent failure, bucket and count it deterministically, and when a failure class recurs past a threshold, scaffold a candidate rule/skill stub into…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
frontier-scan
The English introduction is being prepared.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any…
graph-mode
The English introduction is being prepared.
hallmark
The English introduction is being prepared.