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
8,868 results · page 96 of 296
- View details
principle-migrate-callers-then-delete-legacy-apisSkillAI & models
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Ready to connect★ 390
- View details
principle-minimize-reader-loadSkillAI & models
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Ready to connect★ 390
- View details
principle-never-block-on-the-humanSkillAI & models
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
Ready to connect★ 390
- View details
principle-outcome-oriented-executionSkillAI & models
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
Ready to connect★ 390
- View details
principle-sequence-verifiable-unitsSkillAI & models
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Ready to connect★ 390
- View details
principle-subtract-before-you-addSkillAI & models
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
Ready to connect★ 390
- View details
principle-test-behavior-not-implementationSkillAI & models
Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.
Ready to connect★ 390
- View details
principle-type-system-disciplineSkillAI & models
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
Ready to connect★ 390
- View details
reflectSkillAI & models
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
Ready to connect★ 390
- View details
swarmSkillAI & models
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
Ready to connect★ 390
- View details
teachSkillAI & models
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
Ready to connect★ 390
- View details
- View details
what-did-i-get-doneSkillAI & models
Summarize authored commits over a user-specified time period into a concise update
Ready to connect★ 390
- View details
agentsop-agent-topology-selectionSkillAI & models
Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools enough? do agents need to know about each other? does the output need one voice? — maps the answer to single-agent / supervisor / swarm / sequential /
Ready to connect★ 412
- View details
agentsop-code-execution-decisionSkillAI & models
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent
Ready to connect★ 412
- View details
agentsop-dspySkillAI & models
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "a
Ready to connect★ 412
- View details
agentsop-framework-selectionSkillAI & models
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, n
Ready to connect★ 412
- View details
agentsop-http-tool-wrappingSkillAI & models
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a m
Ready to connect★ 412
- View details
agentsop-hybrid-retrievalSkillAI & models
Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate when a calling agent is building, reviewing, or debugging a retrieval pipeline whose corpus contains exact-match tokens — identifiers, error codes, SKUs, API/function names, proper no
Ready to connect★ 412
- View details
agentsop-llm-tool-idempotencySkillAI & models
Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the t
Ready to connect★ 412
- View details
agentsop-map-reduce-fanoutSkillAI & models
Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool f
Ready to connect★ 412
- View details
agentsop-module-shape-selectionSkillAI & models
ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by ta
Ready to connect★ 412
- View details
agentsop-prompt-history-inspectSkillAI & models
Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite
Ready to connect★ 412
- View details
agentsop-repo-state-gatingSkillAI & models
A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor
Ready to connect★ 412
- View details
agentsop-selfhost-decisionSkillAI & models
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing whe
Ready to connect★ 412
- View details
agentsop-state-reducerSkillAI & models
Tool skill for declaring reducers on LangGraph state keys so parallel writes merge instead of crashing. Activates whenever a coder agent designs a StateGraph with parallel branches, fan-out via Send, multi-agent topologies, or whenever a run raises `InvalidUpdateError: At key '<k>': Can receive only
Ready to connect★ 412
- View details
agentsop-streaming-outputSkillAI & models
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial
Ready to connect★ 412
- View details
agentsop-vllmSkillAI & models
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI
Ready to connect★ 412
- View details
cozempic-doctorSkillAI & models
Run health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (cozempic — does not shadow Claude Code's built-in /doctor)
Ready to connect★ 412
- View details
opus-4-5-migrationSkillAI & models
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
Ready to connect★ 412
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.
53,585 of the 54,017 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.