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
9,018 results · page 211 of 301
- View details
composeSkillAI & models
Create full arranged tracks with timeline structure. Use when user asks to "compose", "create a track", "make a song", or specifies a duration.
Ready to connect★ 65
- View details
create-agent-skill-fallbackSkillAI & models
Create an Agent SKILL.md fallback for an existing find-XXXX finder that relies on a fragile discovery foundation — above all LLM_DECOMPILE (patterns C/D/E), which matches the decompiled shape of a predecessor function against a stored reference and breaks when a symbol is inlined or de-inlined in a
Ready to connect★ 65
- View details
curate-componentsSkillAI & models
Identify repeated blocks across existing ModernTSF models, verify semantic and runtime-contract equivalence, and safely extract reusable components. Use for deliberate cross-model consolidation; not for reorganizing models into families or sharing code based only on similar names.
Ready to connect★ 65
- View details
deep-research-proSkillAI & models
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports.
Ready to connect★ 65
- View details
find-CNetworkGameServerBase_CheckTimeouts-decompilesSkillAI & models
Agent fallback for the find-CNetworkGameServerBase_CheckTimeouts-decompiles preprocessor. Locates the CNetworkGameServerBase_IsHLTV virtual function in CS2 engine2.dll / libengine2.so by decompiling its caller CNetworkGameServerBase_CheckTimeouts and reading the virtual dispatch made on the server t
Ready to connect★ 65
- View details
find-CNetworkGameServerBase_GetChallengeTypeSkillAI & models
Agent fallback for the find-CNetworkGameServerBase_GetChallengeType preprocessor. Locates the CNetworkGameServerBase_GetChallengeType virtual function in CS2 engine2.dll / libengine2.so by decompiling its caller CNetworkGameServerBase_ReplyChallenge and reading the first virtual dispatch made on the
Ready to connect★ 65
- View details
find-OnServerVoiceData_IsPlayingDemo_CalleeSkillAI & models
Generate the Windows-only OnServerVoiceData_IsPlayingDemo_Callee patch YAML from IVEngineClient2_IsPlayingDemo.windows.yaml using a deterministic preprocessor script. Use when locating the IVEngineClient2::IsPlayingDemo indirect call inside C_ServerVoiceHandler::OnServerVoiceData without LLM decompi
Ready to connect★ 65
- View details
implement-modelSkillAI & models
Implement or replace one ModernTSF forecasting model as local code after checking its paper and pinned official implementation when available. Use after structure extraction and component matching; not for paper discovery, scaffolding alone, or experiment reproduction.
Ready to connect★ 65
- View details
integrate-foundation-modelSkillAI & models
Integrate a released pretrained time-series foundation model through its official package and local checkpoint path. Use for zero-shot or inference-only foundation runtimes; not for ordinary paper architecture implementations.
Ready to connect★ 65
- View details
pr_workflowSkillAI & models
Guide and instructions on how coding agents should format code, commit changes, run pre-commit checks, push branches, and create pull requests using the project templates.
Ready to connect★ 65
- View details
report-defectSkillAI & models
Reproduce, diagnose, and draft a ModernTSF defect report. Use for bugs, regressions, incorrect model behavior, or repository failures; do not publish an issue or pull request without explicit authorization.
Ready to connect★ 65
- View details
smoke-modelsSkillAI & models
Run fast end-to-end smoke checks for one or more ModernTSF models. Use after implementation changes or when validating training and output shape quickly; not for exhaustive repository or paper audits.
Ready to connect★ 65
- View details
tutorialSkillAI & models
Learn Strudel step by step. Use when the user wants to learn live coding, understand the syntax, or improve their skills.
Ready to connect★ 65
- View details
tweet-writerSkillAI & models
Write viral, persuasive, engaging tweets and threads.
Ready to connect★ 65
- View details
visualsSkillAI & models
Add psychedelic visual feedback to Strudel patterns. Use when you want trippy, colorful, or informative visualizations.
Ready to connect★ 65
- View details
11labs-acsetSkillAI & models
Model ElevenLabs voice synthesis as an ACSet schema with Unison ability handlers for typed voice operations. Use when integrating ElevenLabs TTS into category-theoretic pipelines, building typed voice synthesis workflows, or managing multi-voice narration with GF(3) conservation.
Ready to connect★ 64
- View details
aaif-governance-interleave <<<<<<< HEADSkillAI & models
Bridge layer connecting the Agentic AI Foundation (AAIF) governance structure — Linux Foundation stewardship of MCP, goose, AGENTS.md — to the plurigrid/asi skill graph. Formalizes AAIF-compatible skill registration, IPSIE identity profiles, and the cross-protocol interoperability surface. Maps the
Ready to connect★ 64
- View details
abap-cloudSkillAI & models
Help with ABAP Cloud development including the 3-tier extensibility model, ABAP Cloud language version restrictions, wrapper patterns for unreleased APIs, clean core principles, and key user vs developer extensibility. Use when users ask about ABAP Cloud, ABAP for Cloud Development, clean core, 3-ti
Ready to connect★ 64
- View details
abductive-oracleSkillAI & models
Formal oracle for abductive inference that selects the minimal hypothesis best explaining a set of observations. Provides three sub-oracles: MCMC via monad-bayes, Gemini for natural language, and propagator networks for constraint domains. Use when performing hypothesis selection, explaining observa
Ready to connect★ 64
- View details
abductive-replSkillAI & models
Hypothesis-Test Loops via REPL for Exploratory Abductive Inference
Ready to connect★ 64
- View details
acp-commonsSkillAI & models
Atlas of Agent Client Protocol (ACP) clients, agents, and OCapN/CapTP-grounded actors. Use when picking a coding agent surface, threading ACP over CapTP, locating the local Zoad implementation, or navigating the Hermes-as-OCapN-actor family.
Ready to connect★ 64
- View details
active-inference-roboticsSkillAI & models
Bridge active inference theory with robot control using K-Scale's JAX/MuJoCo stack. Use when connecting predictive coding to locomotion policies, mapping KL divergence minimization to RL training, applying mean field approximation to robotics state estimation, or implementing sim2real as inference a
Ready to connect★ 64
- View details
active-interleaveSkillAI & models
Interleaves context from recently active Claude/Amp threads into current activity via random walk.
Ready to connect★ 64
- View details
ads-auditSkillAI & models
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says "audit", "full ad check", "analyze my ads", "account health c
Ready to connect★ 64
- View details
affective-taxisSkillAI & models
Implement affective valence as directional derivative of interoceptive energy landscapes for AI alignment. Use when building alignment-aware RL agents, validating GF(3) conservation in reward signals, training Langevin-based policies, or analyzing fold-change detection signals in POMDP environments.
Ready to connect★ 64
- View details
agent-o-ramaSkillAI & models
' Layer 4: Learning and Pattern Extraction for Cognitive Surrogate Systems'
Ready to connect★ 64
- View details
ai-appSkillAI & models
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications.
Ready to connect★ 64
- View details
alife-commonsSkillAI & models
Artificial Life atlas covering open-ended evolution, chemical reaction networks, morphogenesis, self-replication, and programmable chemistry. Use when picking a simulation framework, wiring ALife models into the skill graph, or onboarding contributors to the ALife cluster.
Ready to connect★ 64
- View details
alife2025SkillAI & models
ALIFE 2025 Proceedings - 337 pages, 80+ papers on artificial life, evolution, emergence, cellular automata, neural networks, agent-based models. Full Mathpix extraction with equations and figures.
Ready to connect★ 64
- View details
amp-skillSkillAI & models
Interruption pattern detection and retrieval from Amp thread history. Use for analyzing tool rejection patterns and improving agent behavior.
Ready to connect★ 64
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.
54,826 of the 55,257 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.