Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,017 results · page 260 of 301
- View details
ax-learnSkillAI & models
This skill helps an LLM generate correct AxLearn code using @ax-llm/ax. Use when the user asks about self-improving agents, trace-backed learning, feedback-aware updates, or AxLearn modes.
Ready to connect
- View details
ax-signatureSkillAI & models
This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.
Ready to connect
- View details
deprecation-and-migrationSkillAI & models
Manage deprecation and migration. Use when removing legacy systems, APIs, or features; when migrating users from one implementation to another; or when deciding whether existing code should be maintained or taken offline.
Ready to connect
- View details
dont-reinventSkillAI & models
Vets whether to build a feature from scratch, use an existing free/open-source solution, or pay for a third-party API/service. Use this whenever the user asks Claude to implement, add, integrate, or write code for a feature or capability, especially one that sounds like it could already be a solved
Ready to connect
- View details
dotnet-agent-guardrailsSkillAI & models
Deterministic guardrails for defining the review/validation process in .NET/C# development agents and agent squads: .editorconfig + dotnet format, TreatWarningsAsErrors, custom Roslyn analyzers, full test suites, Aspire telemetry, and Copilot/Claude Code hooks as the gates a change must pass. USE FO
Ready to connect
- View details
fail-closed-code-hygieneSkillAI & models
Odylith stops coding agents from confidently doing the wrong thing
Ready to connect
- View details
find-codeSkillAI & models
Find where a C# symbol is defined and what calls it in AlRunner/, using the language server instead of grep. Use BEFORE grepping for a type, method, or field name — "who calls X", "where is X defined", "what would break if I change X", "find every path that reaches X". Works inside subagents, where
Ready to connect
- View details
gap-loopSkillAI & models
Cyclical dogfooding loop: test AI-AGENT-STORIES.md against the live graph, discover new stories, analyze gaps, fix root causes, re-test, write report. Use when: (1) user says "/gap-loop", (2) periodic dogfooding session, (3) after a release or major feature to re-validate stories, (4) before sprint
Ready to connect
- View details
odylith-github-issue-triageSkillAI & models
Odylith stops coding agents from confidently doing the wrong thing
Ready to connect
- View details
odylith-github-release-closeoutSkillAI & models
Odylith stops coding agents from confidently doing the wrong thing
Ready to connect
- View details
odylith-guidance-behaviorSkillAI & models
Use when guidance behavior pressure cases or high-risk agent guidance contracts need deterministic validation.
Ready to connect
- View details
odylith-subagent-orchestratorSkillAI & models
Plan Odylith delegation ownership, bounded fanout, and merge-safe orchestration.
Ready to connect
- View details
odylith-subagent-routerSkillAI & models
Choose local execution versus bounded delegation for Odylith slices and shape routed payloads.
Ready to connect
- View details
orchestrating-a-sessionSkillAI & models
How to run a coordinator session on this repo — what you decide versus what you delegate, the implementation-agent identity pool and when to reuse it, corpus-PR authority, when to re-run triage, the merge bar, the measurement rules, and the environment traps that silently produce wrong answers. Use
Ready to connect
- View details
plugin-directory-listing-writerSkillAI & models
Use when a validated ChatGPT/Codex Plugin needs accurate Plugin Directory fields, discovery metadata, starter prompts, and reviewer-facing listing details grounded in the packaged product.
Ready to connect
- View details
release-benchmark-publishingSkillAI & models
Odylith stops coding agents from confidently doing the wrong thing
Ready to connect
- View details
spec-driven-developmentSkillAI & models
Create a spec before coding. Use when starting a new project, feature, or major change that doesn't yet have a specification; also when requirements are unclear, ambiguous, or just a vague idea.
Ready to connect
- View details
swe-bench-grafema-experimentsSkillAI & models
SWE-bench pipeline for A/B testing Grafema with Claude Code. Use when: (1) running SWE-bench experiments, (2) comparing baseline vs grafema conditions, (3) evaluating results, (4) debugging container issues.
Ready to connect
- View details
token-disciplineSkillAI & models
Reference only (do NOT invoke as an action): token-reduction conventions (subagent isolation, artifact compaction). Applied throughout the other skills.
Ready to connect
- View details
toonSkillAI & models
Convert data to/from TOON (Token-Oriented Object Notation) for lower-token LLM context. Use when: encoding JSON/YAML to TOON; decoding TOON back to JSON; estimating token savings vs JSON; sending tabular data in a prompt; choosing a delimiter (comma, tab, pipe); validating model-generated TOON with
Ready to connect
- View details
wolpSkillAI & models
Wake or shut down LAN devices from the agent host using raw Ethernet Wake-on-LAN Magic Packets.
Ready to connect
- View details
workflow-to-skill-compilerSkillAI & models
Use when a repository has a valuable agentic workflow, prompt chain, playbook, command, or runbook that should become a portable ChatGPT/Codex Skill without losing its real decision logic.
Ready to connect
- View details
aidd-orchestratorSkillAI & models
Autonomous iteration orchestrator for the AIDD workflow. Use when: run the orchestrator, run an iteration, orchestrate feat-XXX, implement an iteration autonomously, conduct subagents, AIDD pipeline, iteration pipeline.
Ready to connect
- View details
anthropic-sdk-upgraderSkillAI & models
Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upg
Ready to connect
- View details
aweskill-creatorSkillAI & models
Use when creating, authoring, or improving a skill: scaffold a new skill, draft SKILL.md content, write trigger descriptions, test with realistic prompts, iterate wording, turn a repeated workflow from the current conversation into a reusable skill, or customize an installed skill. 中文触发词：制作技能、创建技能、新
Ready to connect
- View details
chat-customizations-editorSkillAI & models
Use when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
Ready to connect
- View details
connect-local-agentSkillAI & models
Use this skill when the user wants to make THIS machine's coding agent reachable for live agent-to-agent collaboration — start the Aicoo local-agent bridge so paired peers can send requests to their running Claude Code / Codex, with per-tool owner approval. Triggers on: 'connect my local agent', 'st
Ready to connect
- View details
craft-promptSkillAI & models
Advanced surface, separate from Foreman's core roadmap job — a standalone prompt builder for work that has no roadmap entry behind it. Guides you through assembling a self-contained spawned-session prompt following Foreman's template — asks which optional sections to include, gathers required info v
Ready to connect
- View details
create-hookSkillAI & models
Create a hook (.json) to enforce policy or automate agent lifecycle events.
Ready to connect
- View details
documenting-codeSkillAI & models
Create or update human-facing docs, agent-facing instructions, architecture
Ready to connect
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,004 of the 55,435 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.