AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Ai

  by @butterbase-ai

  Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

• Rag Dev

  by @butterbase-ai

  Use when building knowledge bases, ingesting documents, running semantic search, or adding LLM-synthesized Q&A over private content with Butterbase RAG

• Hf Mem

  by @waybarrios

  Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub.

• Browser Search

  by @Johell1NS

  Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.

• Excalidraw Pr Diagrams

  by @greenfield-inc

  Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments. Use when the user wants to visualize workflows, architectures, concepts, pull request changes, before/after behavior, or a shareable…

• Orchestrate Sessions

  by @greenfield-inc

  Coordinate authorized work through host-managed workspaces and planning, implementation, and bug-report sessions without taking over their work or polling them.

• Create Ticket

  by @greenfield-inc

  Capture work and evolving intent during discussion as one or more GitHub tickets, Grain briefs, or both. Use for ticket or issue creation, follow-ups, backlog capture, delegation, and revisions as decisions change. Preserve the…

• Session Trace

  by @greenfield-inc

  Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened. Use when asked for a trace or "how did this run go", or…

• Prepare Pr

  by @greenfield-inc

  Prepare a branch for review by committing scoped changes, rebasing on main, running builds, and creating or updating a pull request. Use when the user wants the branch ready for PR review. Also use for rewriting an existing PR…

• Brief

  by @greenfield-inc

  Use when a problem, idea, or change of intent is worth capturing as a long-form page, or the person asks to write it up. Never chooses a solution; the tracker issue belongs to create-ticket.

• Page

  by @greenfield-inc

  House standard for any HTML page written for a person. Use when another skill says to render a page.

• Ui Mockup

  by @greenfield-inc

  Create three UI mockup options per round, then refine the user's favorite until they approve one. Works from screenshots of the current product or from agreed references for something new, with whatever tools are available (an…

• Refactor

  by @greenfield-inc

  Post-PR refactor pass. Sizes the diff against the remote default branch, fans out refactor-simple (and refactor-deep on large changes) as fresh subagents that run blind to each other, merges their plans once with max-severity…

• Pr Test Automation

  by @greenfield-inc

  Run first-pass automated manual testing for PRs that are reviewed or nearly ready to merge. Use when the user asks to test a PR/branch/worktree, validate product flows, exercise browser or CLI workflows, map changed UI journeys…

• Explain Visually

  by @greenfield-inc

  Complement an answer or discussion with a first-principles visual HTML explanation, saved in Grain when connected. Use when explaining how something works, why it changes, or how options differ and a visual would materially help…

• Handoff

  by @greenfield-inc

  Prepare a verified resumption brief when moving work to another agent, device, or session, including local-to-cloud coding handoffs, and start the receiving agent with `runpane handoff`. Use for "hand this off," "continue on my…

• Babysit Pr

  by @greenfield-inc

  Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings, replies with a reason to false positives, rebases when the base moves, and stops when bots and required checks are…

• Quick Verify

  by @greenfield-inc

  Use while working to confirm a change does what you meant before moving on. Observe its real effect the way a user or caller would, compare that with your intent, fix what is off, and observe again.

• Review

  by @greenfield-inc

  Review a PR against its linked issue, repository checks, correctness, architecture, and applicable conventions. Post structured findings as a PR review.

• Options

  by @greenfield-inc

  Use when the person asks what to do or for trade-offs, or more than one design is live. Waits for a pick. Never plans.

• Bug Intake

  by @greenfield-inc

  Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.

• Cold Read

  by @greenfield-inc

  Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions, code. It reports what's broken, confusing, or contradictory. A fresh perspective on something…

• Html Explainer

  by @greenfield-inc

  The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm, graphic-first look. Use when a…

• Pane Work

  by @greenfield-inc

  Answer questions about the user's own work in Pane, read-only. Recap what they worked on, finished, or shipped over a time window, or rank what to do next across panes, pull requests, issues, checks, and reviews. Use for "what…

• Eli5

  by @greenfield-inc

  Teach an unfamiliar topic from first principles with a picture-first HTML explanation, saved in Grain when connected. Use for "explain from scratch," "I'm lost," "what does this mean?", "explain in plain English," beginner…

• Refactor Deep

  by @greenfield-inc

  Read-only comprehensive analysis of the branch against the remote default branch for large features - derives conventions per layer, hunts for correctness defects in the new code paths, and writes a prioritized refactor plan to…

• Refactor Apply

  by @greenfield-inc

  Applies a refactor plan written by refactor-simple, refactor-deep, or the refactor orchestrator's merged report - auto-fixable items first, then manual items one at a time with the user, verifying with the repo's own checks…

• Refactor Simple

  by @greenfield-inc

  Read-only code quality analysis of the branch against the remote default branch for small to medium changes - classifies the diff, derives conventions from the target repo, and writes a refactor plan to ./tmp/. Usually run by…

• Runpane

  by @greenfield-inc

  Drive Pane through the runpane CLI. Covers dispatching work to agents in panes, confirming delivery, handling external text safely, checking PR readiness, and reporting progress. Use when an agent coordinates one or many Pane…

• Discussion

  by @greenfield-inc

  Have an interactive discussion about a topic, approach, feature, or bug without making code changes. Researches the codebase as needed and talks through options. Use to think through an approach before planning or coding.

• Smallest Test

  by @greenfield-inc

  Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach. Use for "how could we test this?", "is this worth building?", or choosing a small experiment to resolve an assumption.

• Investigate

  by @greenfield-inc

  Investigate a bug or broken behavior through hypothesis-driven root cause analysis and report what is wrong without jumping straight to a fix. Use when something is failing or behaving unexpectedly.

• Research Web

  by @greenfield-inc

  Perform technical web research using authoritative sources, synthesize the results, and save a cited research note in the repo. Use when external documentation or up-to-date behavior matters.

• Codebase Explorer

  by @greenfield-inc

  Explore the codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the task is understanding what exists, not proposing changes.

• Pane Manage And Message Agents

  by @greenfield-inc

  Use when the user asks to start, kick off, spawn, check on, nudge, follow up with, or babysit another coding agent (Claude, Codex, or Cursor) in Pane, or to create a Pane for that work.

• Rewrite Simply

  by @greenfield-inc

  (foundational) Answer first, cut clutter, keep the human in it. The structural layer above line-level editing, and the standing default for anything a person reads.

• Gather Evidence

  by @greenfield-inc

  Use when handed one factual question about the code or a running system. Returns evidence. Never proposes a fix.

• Spike

  by @greenfield-inc

  Use only when a decision is blocked on a fact nobody has. One time-boxed question, one answer.

• Explain

  by @greenfield-inc

  Use when the person wants to understand a concept or how something works today. Never plans.

• Interceptor Ios

  by @Hacker-Valley-Media

  Drive any installed app on an owned, unlocked, Developer-Mode iPhone via interceptor ios *: ref-tagged element trees, deterministic coordinate taps (click), reliable text entry (type/keys), scroll, drag, multi-touch gestures…

• Occ Use

  by @ruvnet

  Run Open Claude Code (OCC) for coding tasks and verify its CLI installation. Use when asked to use OCC, select its provider, or perform a bounded coding task through its CLI.

• Misakanet Failure Memory

  by @Ikalus1988

  Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.

• Ai Data Engineering

  by @ancoleman

  Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking…

• Model Serving

  by @ancoleman

  LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment),…

• Prompt Engineering

  by @ancoleman

  Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or…

• Embedding Optimization

  by @ancoleman

  Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require…

• Spine Animation

  by @GenielabsOpenSource

  Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image). Use this skill whenever the user wants to animate a 2D character, create Spine JSON…

• Bug Hunter

  by @codexstar69

  Precision-first adversarial bug hunting for runtime, logic, data, concurrency, and security defects. Uses deterministic risk triage, evidence-bounded retrieval, Hunter/Skeptic/Referee review, optional hybrid verification, and…

• History Explorer

  by @clawdotnet

  Inspect recent session conversation turns and meta-run history. Returns structured JSON summaries of turn counts, role distribution, tool usage, meta-skill executions, and co-occurrence patterns. Use this before running…

• Hunter

  by @codexstar69

  Deep behavioral code analysis agent for Bug Hunter. Performs multi-phase scanning to find logic errors, security vulnerabilities, race conditions, and runtime bugs. Uses doc-lookup (Context Hub + Context7) for framework…

• Skeptic

  by @codexstar69

  Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune…

• Meta Skill Creator

  by @clawdotnet

  Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills. It uses multi-skill…

• Security Review

  by @codexstar69

  Run a focused STRIDE-based security review using Bug Hunter-native artifacts. Use whenever the user asks for a full security audit, repository security review, weekly security scan, PR security review with deeper validation, or…

• Threat Model Generation

  by @codexstar69

  Generate or refresh a STRIDE-based threat model for the current repository using Bug Hunter-native artifacts. Use whenever the repository has no threat model yet, the architecture changed materially, a security review needs…

• Commit Security Scan

  by @codexstar69

  Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context. Use whenever the user asks for PR security review, commit-diff scanning, staged-change security checks, branch-comparison…

• Revyl Workspace

  by @RevylAI

  Open Revyl Atlas maps and existing device viewers inside a compatible host, or manage an explicitly authorized device session through connected Revyl workspace tools. Use revyl-cloud-app for cloud builds and exploration, or the…

• Vulnerability Validation

  by @codexstar69

  Validate security findings for exploitability, reachability, and real-world impact using Bug Hunter-native findings artifacts. Use after security scans, before patch generation, or whenever the user wants confirmation that a…

• Revyl Cloud App

  by @RevylAI

  Create or edit a mobile app in ChatGPT Work's cloud coding workspace, build it with revyl build --remote, run cloud tests and device verification, and map it with revyl explore. Also use for other explicitly requested Revyl CLI…

• Fixer

  by @codexstar69

  Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs…

• Doc Lookup

  by @codexstar69

  Unified documentation lookup for Bug Hunter agents. Uses Context Hub (chub) as primary source with Context7 API fallback. Provides verified library/framework documentation to prevent false positives and ensure correct fix…

• Referee

  by @codexstar69

  Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.

• Community Research Insight

  by @clawdotnet

  Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

• Recon

  by @codexstar69

  Codebase reconnaissance agent for Bug Hunter. Maps architecture, identifies trust boundaries, classifies files by risk priority, and detects service boundaries. Does NOT find bugs — finds where bugs hide.

• Software Developer

  by @clawdotnet

  Operates as an autonomous software engineer, capable of writing code, running tests, and managing git repositories.

• Data Analyst

  by @clawdotnet

  Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.

• Deep Researcher

  by @clawdotnet

  Conducts comprehensive web research, synthesizes data from multiple sources, and produces detailed reports.

• Email Triage

  by @clawdotnet

  Triage inbox into “needs reply”, “FYI”, “urgent”, and “safe to archive”, with a short plan for each.

• Summarize

  by @clawdotnet

  Summarize, condense, or digest content into structured key points, details, and action items.

• Homeassistant Operator

  by @clawdotnet

  Safely operate Home Assistant by resolving targets first and validating state before writes.

• Daily News Digest

  by @clawdotnet

  Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.

• Mqtt Operator

  by @clawdotnet

  Safely interact with MQTT topics with allow/deny policies and minimal payload risk.

• Nacos Router Weather

  by @clawdotnet

  Opt-in Nacos Router weather PoC; requires a registered weather-mcp server.

• Nacos Router Weather Retry

  by @clawdotnet

  Opt-in Nacos Router weather PoC: dynamic capability slot with step retry.

• Nacos Router Weather Dynamic

  by @clawdotnet

  Opt-in Nacos Router weather PoC with a dynamic capability slot.

• Nacos Router Weather Explore

  by @clawdotnet

  Opt-in model-driven Nacos Router weather baseline.

• Vet

  by @imbue-ai

  Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

• Evidence Brief

  by @nightly-labs

  Synthesize supplied sources into a cited brief that separates facts, interpretation, and unresolved questions.

• Reflect Performance Review

  by @Nunchi-trade

  Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review

• 02 Project Memory

  by @ai-driven-dev

  Build the project's memory of its architecture, conventions, and decisions, and wire it into your AI tools. Use when the user wants to set up or refresh project memory, or rewire it into a tool. Not for editing one existing…

• 00 Async Dev

  by @ai-driven-dev

  Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status…

• 02 User Stories

  by @ai-driven-dev

  Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.

• 00 Onboard

  by @ai-driven-dev

  Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface.

• 10 Learn

  by @ai-driven-dev

  Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.

• 12 Cook

  by @ai-driven-dev

  Manage project recipes/how-to sheets by listing, creating, updating, researching, or applying a recipe. Use for recipe, cook, /cook, list, new, update, research, apply.

• 02 Backlog

  by @ai-driven-dev

  Orchestrates a product backlog end to end. Use when the user wants to ask what it holds, or to run intake, triage, refinement, review, lifecycle events, ordering, health checks, or repair. Not for one known artifact step.

• 04 Skill Generate

  by @ai-driven-dev

  Generate a router-based skill across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a skill, or turn a workflow into one. Not for other artifacts like rules, agents, commands, hooks.

• 01 Brainstorm

  by @ai-driven-dev

  Clarify a vague product or technical intent through natural discovery. Use when the user has a half-formed idea, ambiguous request, or asks to brainstorm, discover, refine, or clarify. Not for artifact gap scans, planning, or…

• 06 Product Brief

  by @ai-driven-dev

  Produces a concise Product Brief before requirements. Use when the user wants to frame or revisit a product opportunity and how it will be validated. Not for requirements, technical design, or planning.

• 10 Task

  by @ai-driven-dev

  Produces or refines a backlog Task for bounded delivery work without independent user value. Use when the user wants to create, link, order, estimate, transition, or complete one. Not for User Stories, Spikes, Defects, or…

• 09 Defect

  by @ai-driven-dev

  Produces or refines a backlog Defect from an observed product mismatch. Use when the user wants to report, assess, link, order, transition, or verify a defect. Not for incident response, debugging, or implementation.

• 05 Spike

  by @ai-driven-dev

  Produces an evidence-bounded spike for an uncertainty blocking estimation, feasibility, or design. Use when the user wants to frame, investigate, resume, or conclude one. Not for general research or implementation.

• 07 Epic

  by @ai-driven-dev

  Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation.

• 04 Audit

  by @ai-driven-dev

  Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a…

• 01 Bootstrap

  by @ai-driven-dev

  Design and validate a new SaaS's architecture into an INSTALL.md via Q&A and stack comparison. Use when the user starts a project, chooses a stack, or picks an architecture pattern. Not for editing an existing stack or…

• 03 Shadow Areas

  by @ai-driven-dev

  Scan a markdown artifact (idea, stories, PRD, spec) for blind spots into a shadow report grouped by category and severity. Use to find gaps or what is missing in a written artifact. Not for interactive Q&A or code review.

• 01 Plan

  by @ai-driven-dev

  Turn a request, ticket, or file into a phased implementation plan. Use to plan a feature before building, or to turn a ticket into phases. Do NOT use to write code or review a diff.

• 05 Improve

  by @ai-driven-dev

  Reads complete conversation evidence, measures visible cost, and recommends minimal improvements. Use when the user wants to improve a conversation, reduce wasted time or tokens, or choose files to revise. Not for delivery…

• 08 Hook Generate

  by @ai-driven-dev

  Generate a hook, a handler that runs at a lifecycle event, across the host AI tools. Use when the user wants to create, scaffold, or refactor a hook, or automate an action at a lifecycle point. Not for other artifacts like…

• 04 Fact Check

  by @ai-driven-dev

  Verify factual claims in a text against authoritative sources and rewrite it with footnote citations, hedging the unconfirmed. Use to fact-check, verify a claim, or cite sources on request. Not for judging code or clarifying…

• 01 Acceptance Qa

  by @ai-driven-dev

  Validate a reviewed candidate's observable behavior against its acceptance criteria and record short named videos as reviewer evidence. Use when acceptance criteria exist and a browser-observable journey needs proof it holds. Do…