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: Docs & knowledge
4,535 results · page 83 of 152
- View details
agent-swarm-memory-managerSkillDocs & knowledge
Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager
Ready to connect★ 132
- View details
agent-v3-memory-specialistSkillDocs & knowledge
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
Ready to connect★ 132
- View details
pironman5-miniSkillDocs & knowledge
Guide Raspberry Pi 5 builds that live inside the SunFounder Pironman 5 Mini enclosure. Use this skill for assembly notes, cooling/RGB control, NVMe provisioning, pironman5 CLI/dashboard operations, and OpenClaw automations that target the compact Mini case.
Ready to connect★ 132
- View details
ppt-visual-replicaSkillDocs & knowledge
Recreate a user-provided flat infographic, diagram, or presentation image as a visually faithful, object-level editable PowerPoint deck. Use for image-to-PPTX visual replicas that require minimum semantic-unit decomposition, imagegen/API-generated semantic assets, native editable text and layout geo
Ready to connect★ 132
- View details
systematic-foundations-tutorialSkillDocs & knowledge
Rewrite scattered computer science notes into coherent, dependency-aware tutorials with a clear learning path, causal explanations, and grouped headings.
Ready to connect★ 132
- View details
design-briefSkillDocs & knowledge
Lets your agent turn a structured design brief into a concrete design spec with palette, typography, and layout choices.
Ready to connect★ 129
- View details
hax-content-chunking-auditSkillDocs & knowledge
Audit a HAX site page (JSON Outline Schema node, raw HTML in pages/, or markdown) against cognitive-load and content-chunking instructional-design standards, then return actionable HAX web-component remediation. Use when the user asks to review a course page, textbook module, or HAX site for readabi
Ready to connect★ 129
- View details
oerschema-auditSkillDocs & knowledge
READ-ONLY diagnostic: review authored HAX page HTML, site.json outline nodes, VitePress markdown directives, JSON-LD blocks, and Google Docs export HTML against the OER Schema vocabulary (Course/Unit/Module/Lesson, LearningObjective, Assessment/Quiz/Activity/Project, Task/Practice, Rubric family, Su
Ready to connect★ 129
- View details
- View details
urban-design-foundationsSkillDocs & knowledge
Comprehensive urban design knowledge base containing theories, principles, quantitative standards, and rules of thumb from 40+ theorists and global frameworks. Provides foundational knowledge for all urban design tasks including masterplanning, site analysis, street design, public space design, dens
Ready to connect★ 129
- View details
wjs-publishing-wechatSkillDocs & knowledge
Use when the user wants to write or publish WeChat Official Account articles — they provide scattered ideas, drafts, or notes, and you polish them, generate cover images and explanatory diagrams, or prepare content for upload to mp.weixin.qq.com. Trigger words: "写一篇微信文章", "公众号", "润色", "题图", "发公众号",
Ready to connect★ 129
- View details
project-analyzerSkillDocs & knowledge
A skill for analyzing code repositories and generating project documentation. Triggered when the user explicitly asks to analyze a project or use the project analysis feature. Typical trigger phrases include "帮我梳理这个项目", "梳理一下这个代码仓", "使用项目梳理", etc. This skill reads the project's code repository and g
Ready to connect★ 127
- View details
community-llm-wikiSkillDocs & knowledge
Karpathy's LLM Wiki — build and maintain a persistent, interlinked
Ready to connect★ 126
- View details
community-ocr-and-documentsSkillDocs & knowledge
Extract text from PDFs and scanned documents. Use web_extract for
Ready to connect★ 126
- View details
community-planSkillDocs & knowledge
Plan mode for ArgentOS — inspect context, write a markdown plan into
Ready to connect★ 126
- View details
hig-project-contextSkillDocs & knowledge
Create or update a shared Apple design context document that other HIG skills use to tailor guidance. Use when the user says "set up my project context," "what platforms am I targeting," "configure HIG settings," or when starting a new Apple platform project. Also activates when other HIG skills nee
Ready to connect★ 126
- View details
ai-project-managerSkillDocs & knowledge
Create and maintain repository planning documents, phased implementation plans, approval checkpoints, task status, and validation evidence for AI-assisted development work.
Ready to connect★ 125
- View details
docs-ciSkillDocs & knowledge
docs-as-code CI/CD pipeline scaffolding + documentation drift detection — link checking, OpenAPI lint/breaking gates, mermaid validation, documentation freshness checks, CHANGELOG automation, docs.yaml manifest. Use when installing docs CI/documentation pipelines, detecting documentation drift or st
Ready to connect★ 125
- View details
docs-interfacesSkillDocs & knowledge
Interface/API documentation generation — OpenAPI 3.1/AsyncAPI 3.0 specs, API diagrams, interface flow diagrams (sequence), API change history. Use when writing API docs/specs (OpenAPI, swagger, AsyncAPI), interface/API diagrams, endpoint documentation, or an API changelog. For overall system archite
Ready to connect★ 125
- View details
hermes-profile-auditSkillDocs & knowledge
Use when a Hermes profile must be audited for role clarity, authority boundaries, configuration fit, skills, memory posture, credential scope, handoffs, and recurring operational failures.
Ready to connect★ 125
- View details
lsp-docsSkillDocs & knowledge
Three-tier documentation lookup for any symbol — hover → offline toolchain doc → source definition. Use when hover text is absent, insufficient, or the symbol is in an unindexed dependency.
Ready to connect★ 125
- View details
agent-memory-provenanceSkillDocs & knowledge
Design attributable, privacy-aware memory for AI agents. Use when an agent needs session context, durable memory, retrieval, summaries, source citations, client isolation, compaction, retention rules, or an append-only decision and evidence record.
Ready to connect★ 124
- View details
api-doc-commentsSkillDocs & knowledge
Guide for writing Rust doc comments that produce accurate generated contract documentation. Use when editing Instantiate/Execute/Query/Response types or any public schema-facing API.
Ready to connect★ 123
- View details
consulting-writingSkillDocs & knowledge
Management-consulting writing craft — McKinsey SCR (Situation·Complication·Resolution), Minto Pyramid/MECE, BCG bold-bullet executive summary, so-what upfront, numeric precision, Forrester Landscape. Use when writing or reviewing an executive summary for decision-makers or a roll-up/landscape overvi
Ready to connect★ 124
- View details
doc-generationSkillDocs & knowledge
Guide for regenerating Axone contract schemas and rendered Markdown docs. Use when contract APIs or metadata change, when checking generated-doc drift, or when preparing documentation commits.
Ready to connect★ 123
- View details
docmancerSkillDocs & knowledge
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentatio
Ready to connect★ 124
- View details
docmancer-memorySkillDocs & knowledge
Recall and write source-attributed local memory.
Ready to connect★ 124
- View details
docmancer-memory-writingSkillDocs & knowledge
Write deliberate source-attributed local memory.
Ready to connect★ 124
- View details
docmancer-onboardingSkillDocs & knowledge
Set up machine-wide agent memory and open the local project workbench.
Ready to connect★ 124
- View details
documentation-templateSkillDocs & knowledge
Generate structured documentation templates for components, patterns, or guidelines within a design system.
Ready to connect★ 124
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.
54,764 of the 55,196 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.