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
8,992 results · page 199 of 300
- View details
liv-list-treeSkillAI & models
List vault items as a tree (Projects, Agents, Chats)
Ready to connect★ 74
- View details
mini-program-architecture-skillSkillAI & models
Translate a confirmed mini-program product specification or bounded feature into an implementable architecture covering modules, pages, components, services, canonical state sources, data models, interfaces, permissions, failures, caching, concurrency, idempotency, migration, rollback, external depe
Ready to connect★ 73
- View details
release-posterSkillAI & models
Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.
Ready to connect★ 73
- View details
tools-internalSkillAI & models
Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.
Ready to connect★ 73
- View details
unit-testSkillAI & models
Improves unit test coverage on demand — discovers testing gaps via a reconnaissance agent and writes new tests that follow project conventions. Requires /optimus:init to have set up test infrastructure. Conservative — only adds new tests, never modifies existing test logic or source code; untestable
Ready to connect★ 74
- View details
yandexgptSkillAI & models
OpenAI-compatible translation proxy for Yandex Cloud Foundation Models (YandexGPT)
Ready to connect★ 74
- View details
agent-fungibilitySkillAI & models
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.
Ready to connect★ 73
- View details
agents-introspectionSkillAI & models
Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not for routine post-success skill-evolution or agent self-improvement reviews.
Ready to connect★ 71
- View details
apex-profileSkillAI & models
Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.
Ready to connect★ 73
- View details
apex-routeSkillAI & models
Reach ANY tonone specialist on demand, even ones not installed in this session's roster — no restart needed. Use when asked "which agent handles this", "reach a specialist we didn't install", "route this to the right agent", or whenever a scoped apex-profile roster is missing the right hat for the j
Ready to connect★ 73
- View details
brace-playbookSkillAI & models
Write support playbook -- response templates, issue-type runbooks, tone guide, and common resolution paths. Use when asked to "write support templates", "build a support playbook", "train our support agents", or "standardize our support responses".
Ready to connect★ 73
- View details
budget-auditSkillAI & models
Audit AI spend — per-model cost breakdown, top consumers, waste identification, optimization levers. Use when asked "why is our AI bill so high", "audit LLM spend", or "where is our token waste".
Ready to connect★ 73
- View details
bvSkillAI & models
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
Ready to connect★ 73
- View details
cassSkillAI & models
Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history.
Ready to connect★ 73
- View details
cast-forecastSkillAI & models
Build a forecasting model for a time series — demand, revenue, or usage prediction. Use when asked to "forecast demand", "predict next quarter revenue", or "build a time series model".
Ready to connect★ 73
- View details
cast-reconSkillAI & models
Survey existing forecasting code or models in a codebase — find gaps, stale models, and missing validation. Use when asked "what forecasting models do we have", "audit our forecasts", or "find stale models".
Ready to connect★ 73
- View details
codex-handoffSkillAI & models
Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.
Ready to connect★ 71
- View details
copy-transcript-pathSkillAI & models
Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.
Ready to connect★ 71
- View details
cortexSkillAI & models
ML/AI engineer — LLM integrations, prompt engineering, model pipelines, evals, RAG. Use when asked to "add AI to this", "integrate an LLM", "build a RAG pipeline", "evaluate model accuracy", or "improve this prompt".
Ready to connect★ 73
- View details
cortex-evalSkillAI & models
Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or "model performance".
Ready to connect★ 73
- View details
cortex-modelSkillAI & models
Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression".
Ready to connect★ 73
- View details
cortex-promptSkillAI & models
Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".
Ready to connect★ 73
- View details
create-tests-for-demo-modelSkillAI & models
Create tests for Diff Studio demo models
Ready to connect★ 73
- View details
dotnet-cqrs-query-generatorSkillAI & models
Generates CQRS Queries with Handlers and Response DTOs for read operations. Uses Dapper for optimized read queries, bypassing the domain model for better performance.
Ready to connect★ 73
- View details
embed-reconSkillAI & models
Audit embedding infrastructure — model drift, index freshness, query latency, coverage gaps. Use when asked to "audit our embeddings", "is our index stale", or "find embedding coverage gaps".
Ready to connect★ 73
- View details
evm-atlasSkillAI & models
"Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop,
Ready to connect★ 71
- View details
fresh-eyes-sweepSkillAI & models
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.
Ready to connect★ 71
- View details
git-squashSkillAI & models
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
Ready to connect★ 71
- View details
lead-magnetsSkillAI & models
Plan, create and review lead magnets and capture funnels in a consent-based and transparent way. Use this skill for whitepapers, checklists, templates, calculators, webinars and courses behind a form, for deciding whether gating makes sense at all, and for reviewing an existing f
Ready to connect★ 73
- View details
mykgSkillAI & models
Run mykg knowledge-graph commands inside Claude Code from one slash command `/mykg`. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right `mykg` CLI command from the live `--help`
Ready to connect★ 73
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.
54,624 of the 55,055 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.