Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm prompting, image prompt, ai prompting, prompt optimization, prompt template, prompt structure, effective prompts, prompt techniques
Use when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved to raise the score against their own evaluation command. Makes one targeted quality edit per iteration — clarity, context, specificity, structure, examples, decomposition, guardrails — re-runs the user's eval to measure the metric, and keeps the edit only if the metric improves, else reverts; loops to a target, plateau, or budget. The metric is whatever the user's eval command prints (task accuracy, an LLM-judge score, a pass rate, a tool-call success rate); the loop is metric-agnostic and never edits the eval. Not for writing a prompt from scratch, not for tuning model weights or hyperparameters, and not for one-off manual prompt edits without a score.
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".
Summarize a research project conducted with Asta skills and submit it to the asta-research-challenge repository. Use when the user wants to reflect on a finished (or in-progress) project and/or share it with the Asta team. The user may say "reflect on this project", "submit my research challenge", or "write up what we did".
Use after run-plan completes to independently verify the implementation. Reads only the plan document and inspects the codebase from scratch — information-isolated from the execution context. Produces a structured review document with PASS/FAIL verdict. Triggers when the user says "review the work", "verify the implementation", "check if the plan was executed correctly".
Use when the user asks for a second-opinion review from another agent (e.g., "get a second opinion", "review with pi", "review using gpt-6-astra", "/second-opinion"), or when review-code runs with `--second-opinion`. Runs a fresh pi session (or Claude Code, when already inside pi) on the review-code skill and relays its review.
Self-improving correction capture system. After ANY user correction, detect it, generalize the lesson, and store it as a reusable rule in MEMORY.md. Ensures Claude's mistake rate drops over time by compounding corrections into permanent knowledge. Load this skill when a user corrects Claude's output, mentions "remember this", "don't do that again", "learn from mistakes", "update memory", or when starting a new session (to review existing rules).
CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and scheduled runs. When a CI check fails (test, build, lint, deploy, scan), this skill diagnoses the failure from CI logs, proposes a verified patch as a PR comment or follow-up commit, and commits a HEAL entry to `.learnings/HEALS.md`. Verify-before-persist discipline preserved: a HEAL is only `verified` if a re-run check passes in the same workflow; otherwise it ships as `pending-verify` for human follow-up. Recurrent heal patterns across PRs accumulate `Recurrence-Count` and append a `Handoff` block at ≥3 to flag promotion via self-improvement-ci. Use this skill when: you want headless heal-loop execution in CI/scheduled pipelines, you want recurring failure patterns captured automatically, or you want PRs that surface non-obvious environmental / tooling fixes without human triage. For interactive/local sessions, use `self-healing` instead.
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code patterns, workflows, and documentation to identify harvestable skills, then generates comprehensive skill definitions with best practices, examples, and structured templates.
Manage, audit, and maintain your skill ecosystem. Use when the user asks to "check my skills", "audit skills", "find duplicate skills", "which skills am I using", "prune unused skills", "are my skills synced", "check for skill updates", "skill report", "skill health", or mentions skill maintenance, cleanup, or organization.
Once you have chosen a new developer tool, SDK, API or hosted service to add to a project, look it up on agent.reviews to see how other coding agents got on setting it up and coding against it (install, docs, auth, SDK, errors), and plan around that friction. The reviews do not measure how good a tool is (result quality, accuracy, speed, price, the end user's experience), so never use them to pick or rank tools, or in place of the docs, a web search or benchmarks. Skip it for a tool the project already uses and for questions about which tool performs best.
Use when the user explicitly invokes this skill to create, refresh, or localize a repository's agent instruction files — AGENTS.md, CLAUDE.md, and personal local rules in AGENTS.override.md and CLAUDE.local.md — or to check that instruction-file policy against current best practice. Do not use for ordinary documentation edits, for implicit mentions of AGENTS.md, or for any request that does not explicitly invoke it.
Create or revise Claude Code-compatible Agent Skills (SKILL.md with optional references/, scripts/, and assets/). Use when designing a new skill, improving an existing skill, or updating/refactoring an existing skill while preserving the original author's intent (avoid semantic drift unless explicitly requested/approved by the author). Also use when integrating skills with subagents (context fork, agent).
Accept or apply for a task on OpenAnt. Use when the agent wants to take on work, accept a bounty, apply for a job, pick up a task, or volunteer for an assignment. Handles both OPEN mode (direct accept) and APPLICATION mode (apply then wait for approval). After accepting, use files list/download/url to get task reference files. Covers "accept task", "take this task", "apply for", "pick up work", "download task attachments", "get task files".
Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools: inference.sh CLI, bash scripting, Python SDK, webhook integration. Use for: content automation, data processing, monitoring, scheduled generation. Triggers: ai automation, workflow automation, batch processing, ai pipeline, automated content, scheduled ai, ai cron, ai batch job, automated generation, ai workflow, content at scale, automation script, ai orchestration
Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS, OmniHuman, media merger, upscaling. Use for: YouTube videos, social media content, marketing materials, automated content. Triggers: content pipeline, ai workflow, content creation, multi-step ai, content automation, ai video workflow, generate and edit, ai content factory, automated content creation, ai production pipeline, media pipeline, content at scale
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
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.