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
9,105 results · page 186 of 304
- View details
build-alongSkillAI & models
Guide the learner through a hands-on exercise step by step, having them do the work rather than watching. Use when the learner wants to practice, build something, do the exercise, or learn by doing for a module.
Ready to connect★ 84
- View details
clean-worktreeSkillAI & models
Clean up an HQ git worktree — merge a detached worktree branch back into local main in the primary HQ tree, then remove the worktree and delete the branch. Use when HQ work happened in a separate worktree (e.g. .claude/worktrees/<name> on claude/*, or workspace/worktrees/<name> on codex/*) and needs
Ready to connect★ 84
- View details
convert-codexSkillAI & models
Add Codex support to older Claude-first HQ roots without breaking Claude setup.
Ready to connect★ 84
- View details
deep-planSkillAI & models
Deep project planning — research subagents (codebase / HQ / repo) + 3-tier 15-question interview (Strategic / Architecture / Quality) with smart-skip and pushback. Use for large or strategically important PRDs. For lightweight planning, use /plan instead. Adversarial spec review is delegated to /rev
Ready to connect★ 84
- View details
explain-eli5SkillAI & models
Re-explain a concept as simply as possible, using plain language and analogies. Use when the learner is confused, says they don't get it, asks for a simpler explanation, or asks to explain something "like I'm five".
Ready to connect★ 84
- View details
import-claudeSkillAI & models
Deprecated alias for /import-context — bootstrap HQ from your prior AI footprint (Claude Code, Codex, Grok, claude.ai history plus on-disk artifacts).
Ready to connect★ 84
- View details
import-contextSkillAI & models
Bootstrap HQ from your prior AI footprint — Claude Code, Codex, Grok, and claude.ai conversation history plus on-disk artifacts (skills, hooks, policies, repos, plans). Proposes companies, knowledge, policies, and projects for guided import.
Ready to connect★ 84
- View details
quiz-meSkillAI & models
Test the learner's understanding of a module or topic and track weak spots. Use when the learner asks to be quizzed, tested, checked, or wants to know if they're ready to move on. Never reveals answers before the learner attempts them.
Ready to connect★ 84
- View details
skill-to-sdkSkillAI & models
Turn an Anthropic Agent Skill into a runnable standalone Python app built on the Anthropic SDK. Use this whenever the user wants to "publish", "export", "package", or "turn into an app" a skill, or asks for the "SDK version" / "API version" / "standalone version" of a skill, or wants a script that l
Ready to connect★ 84
- View details
teach-moduleSkillAI & models
Run an interactive lesson for one course module. Use when the learner asks to learn, start, study, or be taught a module or topic, or to continue where they left off. Walks through the module's lesson.md one concept at a time with comprehension checks.
Ready to connect★ 84
- View details
warmupSkillAI & models
Run a quick ~15-minute pre-class review that recaps the previous module and previews the upcoming one. Use when the learner says they have class soon, wants to prepare, asks for a refresher or warm-up, or asks "what did we cover" / "what's next" right before a session.
Ready to connect★ 84
- View details
agent-evalSkillAI & models
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop,
Ready to connect★ 82
- View details
ai-coding-tools-stingerSkillAI & models
AI coding tool advisor for Cursor, Claude Code, Aider, Cline, Windsurf, Devin, and Bolt. Use when picking, comparing, or configuring an AI coding tool, or debugging one that misbehaves.
Ready to connect★ 83
- View details
ai-tools-platform-stingerSkillAI & models
The vibe coder's AI toolbox: AI gateways (Portkey, OpenRouter), cloud providers (Bedrock, Vertex AI), frontier model selection (Claude, GPT, Gemini), cheap-fallback routes (Haiku, Mini, Flash), local LLMs (Ollama, LM Studio), GPU cloud (Runpod, Modal, Together, Fireworks), and must-have MCPs and IDE
Ready to connect★ 83
- View details
audit-and-fixSkillAI & models
Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "
Ready to connect★ 83
- View details
bifrost-stingerSkillAI & models
Bifrost AI gateway specialist: maximhq/bifrost architecture, admin and inference API surface, virtual keys, semantic cache, .so plugins, tags, fork freeze and upgrade policy. Use for any Bifrost work.
Ready to connect★ 83
- View details
branching-strategy-stingerSkillAI & models
Branching strategy advisor for Git-based teams. Owns model selection (trunk-based development, GitHub Flow, GitFlow), release and hotfix branch patterns, the merge-vs-rebase argument, the long-lived-branch trap, and the feature-flag vs feature-branch decision. Use when the user says \\\\\\\"which br
Ready to connect★ 83
- View details
compose-multiplatformSkillAI & models
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cr
Ready to connect★ 82
- View details
course-storytellingSkillAI & models
Use when lesson or course content is correct but forgettable and a concept has to LAND: profiles the learner, breaks the blocking false belief, then rebuilds it as epiphany story → named model → grounded analogy → proof → so-what. NOT outcomes, assessment or module order (that is `course-builder`),
Ready to connect★ 82
- View details
djangoSkillAI & models
Use when building, reviewing, securing, testing or shipping a Django app — models, migrations, QuerySets/managers, FBV/CBV views, forms, the admin, settings split, and Django REST Framework (serializers, ModelViewSet, permissions). NOT async FastAPI/Pydantic services (that is `fastapi`), NOT Postgre
Ready to connect★ 82
- View details
electronSkillAI & models
Use when building, hardening, or shipping a cross-platform Electron desktop app — main/renderer/preload process model, typed contextBridge IPC, locking down nodeIntegration/contextIsolation/sandbox/CSP, or packaging with signing and auto-update. NOT a Rust-backed shell on the native webview (that is
Ready to connect★ 82
- View details
embeddings-runtime-stingerSkillAI & models
Picks and runs embedding models: hosted (OpenAI, Cohere, Voyage) vs self-hosted, cost tradeoffs, batching, caching. Use when choosing, swapping, or debugging an embedding model.
Ready to connect★ 83
- View details
finetuningSkillAI & models
Use when adapting an open-weight model to a target form or behavior — tone, output format, reasoning pattern — via LoRA/QLoRA or full fine-tuning with TRL SFTTrainer, then preference optimization (DPO/ORPO/KTO/GRPO), and for fine-tune vs prompt vs RAG. NOT adding facts to a model (that is rag); NOT
Ready to connect★ 82
- View details
flueSkillAI & models
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
Ready to connect★ 83
- View details
flutterSkillAI & models
Use when building, structuring, testing or optimizing a Flutter app — feature-first layering, Riverpod 3 or Bloc, typed go_router, freezed models, a dio data layer, Material 3, jank hunting, widget/golden tests. Targets Flutter 3.44 / Dart 3.12. NOT React Native (that is `react-native`), NOT Compose
Ready to connect★ 82
- View details
gamedev-pathingSkillAI & models
Use when making NPCs, enemies, or units navigate a level — grid vs waypoint vs navmesh, A*/JPS, navmesh baking and agent radius, off-mesh links, steering, RVO crowd avoidance, and flow fields in Godot 4.x, Unity, Unreal. NOT collision response or character controllers (that is gamedev-physics), NOT
Ready to connect★ 82
- View details
grantsSkillAI & models
Guides your agent through finding matching NIH grants for a research idea and drafting an editable funding strategy document.
Ready to connect★ 82
- View details
kotlin-androidSkillAI & models
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is `compose-multiplat
Ready to connect★ 82
- View details
llm-pipelineSkillAI & models
Use when wiring several LLM calls into a production flow: typed contracts between steps, a router/gateway so 429s, timeouts and outages fail over instead of taking you down, and cost control via caching, model tiers and abort caps. NOT single-prompt wording (that is `prompt-engineering`), NOT a mode
Ready to connect★ 82
- View details
makeSkillAI & models
Use when operating Make.com (formerly Integromat) programmatically — driving its REST API v2 or the Make MCP server from code or an agent to create, read, update, activate, run, clone or delete scenarios, connections, hooks and data stores. NOT designing what the flow should do (that is `automation-
Ready to connect★ 82
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.
55,111 of the 55,543 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.