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
4,502 results · page 107 of 151
- View details
claude-env-setupSkillDocs & knowledge
Installs and updates the agent's working environment: skills, rules, and commands from this set plus related tools (MCP servers, the EDT plugin, local transcription, document converters, 1C utilities). Works on both a clean machine and an already configured one - it first takes an inventory of what
Ready to connect★ 65
- View details
composing-1c-queriesSkillDocs & knowledge
Compose correct and optimized 1C:Enterprise query language queries. Covers ВЫБРАТЬ/ИЗ/ГДЕ structure, table naming (catalogs, documents, registers, virtual tables), field selection, joins, grouping, totals, temporary tables, and parameter usage. Includes accounting register virtual tables (Остатки, О
Ready to connect★ 65
- View details
docx-from-sampleSkillDocs & knowledge
Create a new DOCX styled after an existing sample: use another document as a style template and fill it with your own data, preserving the title page, numbered headings, table styles, column widths, header shading, headers and footers, and portrait/landscape sections. Use when asked to create a docu
Ready to connect★ 65
- View details
elm-add-panelSkillDocs & knowledge
Add a new app-wide "Shared panel" (like Accounts/Starred Posts/Markdown) to the Elm SPA (frontends/elm-spa). Use when asked to add a new global overlay/panel driven from Shared.Model, not page-local state.
Ready to connect★ 65
- View details
excalidrawSkillDocs & knowledge
Creating diagrams and charts in Excalidraw for Obsidian. Use when user says 'сделай схему', 'нарисуй диаграмму', 'excalidraw', 'схема в obsidian', 'визуализация'.
Ready to connect★ 65
- View details
mermaid-renderSkillDocs & knowledge
Renders mermaid diagrams to PNG/SVG/PDF via local mermaid-cli (mmdc). Use when the user asks to render mermaid, make a PNG from a diagram, turn mermaid into an image, convert .mmd to png/svg/pdf, extract mermaid from markdown into images, or save a mermaid block as an image.
Ready to connect★ 65
- View details
presentationSkillDocs & knowledge
Create presentations from text/outline using Marp (Markdown to slides). Use when user asks to create presentation, slides, pitch deck. Triggers on "презентация", "слайды", "presentation", "pitch deck", "сделай презентацию".
Ready to connect★ 65
- View details
project-context-mapperSkillDocs & knowledge
Gives the agent a photographic memory of massive repositories. Forces the creation and maintenance of a highly compressed CONTEXT_MAP.md to prevent context exhaustion and hallucination.
Ready to connect★ 65
- View details
punct-polishSkillDocs & knowledge
[Punctuation Polish] The most common flaw in AI-written Chinese is punctuation: half-width commas, missing CJK-Latin spacing, straight quotes, overused dashes... This skill fixes all of it in one pass. Covers four scenarios: Chinese prose, technical documentation, mixed Chinese-English text, and soc
Ready to connect★ 65
- View details
sarvam-aiSkillDocs & knowledge
Indian AI toolkit powered by Sarvam AI — text-to-speech, speech-to-text, document intelligence, translation, transliteration, language detection, and chat completion across 23 Indian languages. Use when working with Indian languages, Hindi/Tamil/Bengali text, Sarvam AI, or when the user needs transl
Ready to connect★ 65
- View details
scene-fitSkillDocs & knowledge
[L3.5 Scene Adaptation] Whatever platform you post to, follow that platform's rules. Five scenarios: technical docs, ad copy, PPT presentations, social media, Release Notes. It doesn't change the content — it adjusts the format to fit the target platform. Triggers: this is suitable for posting on XX
Ready to connect★ 65
- View details
self-evolving-memory-graphSkillDocs & knowledge
Grants the AI long-term episodic memory. The agent autonomously documents the user's coding preferences, past mistakes to avoid, and architectural decisions into a persistent learning graph.
Ready to connect★ 65
- View details
StreamFlow Documentation — Adding ExamplesSkillDocs & knowledge
This skill should be used when the user asks to "add an example", "write a tutorial", "document a new workflow example", or when creating a new worked example under `docs/source/examples/`.
Ready to connect★ 65
- View details
tech-doc-style-chineseSkillDocs & knowledge
Use when writing, rewriting, proofreading, or reviewing Chinese technical documentation, product copy, UI text, Markdown documents, API descriptions, user manuals, troubleshooting, or operations docs. Applies a restrained, accurate, scannable Chinese technical writing style; preserves facts, constra
Ready to connect★ 65
- View details
tubescribeSkillDocs & knowledge
YouTube video summarizer with speaker detection, formatted documents, and audio output.
Ready to connect★ 65
- View details
zero-to-prod-orchestratorSkillDocs & knowledge
Master orchestrator to build an application from scratch to a production-ready release, enforcing strict step-by-step progression and continuous documentation / Orkestrator utama untuk membangun aplikasi dari nol hingga rilis siap produksi dengan dokumentasi bertahap.
Ready to connect★ 65
- View details
address-sanitizerSkillDocs & knowledge
Use AddressSanitizer to detect memory safety bugs in C/C++ programs. Identifies use-after-free, buffer overflow, memory leaks, and other memory errors.
Ready to connect★ 64
- View details
agentic-top-10SkillDocs & knowledge
Reviews agentic AI systems against the OWASP Top 10 security risks for autonomous AI agents. Auto-invoked when reviewing multi-agent architectures, AI agent deployments, or systems where LLMs have tool access and act autonomously. Covers permission models, tool security, memory integrity, trust boun
Ready to connect★ 64
- View details
amp-continueSkillDocs & knowledge
Export AMP threads as markdown and fork continuation paths. Use when managing AMP conversation threads, exporting thread history, or branching thread execution across skills.
Ready to connect★ 64
- View details
amp-continue: Thread-based conversation continuation with GF(3)SkillDocs & knowledge
Combines AMP thread export with GF(3)-classified continuation for skill orchestration. Export threads as markdown, classify continuation choices as {-1:reductive, 0:neutral, +1:generative}, and fork parallel execution paths.
Ready to connect★ 64
- View details
capture-learningSkillDocs & knowledge
Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
Ready to connect★ 64
- View details
game-design-one-page-design-docSkillDocs & knowledge
Create a concise one-page game design document and export it as both markdown and PDF. Use when a user wants a one-page design doc, one-pager, pitchable design summary, or compact game concept sheet that captures identity, pillars, summary, features, interface, aesthetic direction, sound, audience,
Ready to connect★ 64
- View details
hsi-daily-weightSkillDocs & knowledge
Queries constituent weights of Hang Seng family indexes (HSI / HSCEI / HSAIT, etc.). Filter by trading day / date range / index / stock. Use when user asks about 港股指数权重, 恒生指数成份股权重, 国企指数权重, 恒生科技权重, hsi daily weight, 港股权重. Note: the HSAIT "恒生科技" mapping is uncertain (see cautions); HSI/HSCEI are usabl
Ready to connect★ 64
- View details
lamprey-docs-and-writingSkillDocs & knowledge
Maintaining Lamprey's documents of record — CLAUDE.md, DEVLOG.md, README.md, ARCHITECTURE/, PLANNING/ — with the exact DEVLOG entry template, the README-on-every-ship checklist, commit-message house style, the no-slop/no-fake-polish doctrine, and the rules for what may be claimed publicly. Load when
Ready to connect★ 64
- View details
llm-wiki-ingestSkillDocs & knowledge
Compile a Raw source into concise, linked Wiki notes. Use when a new source lands in Raw/Sources/ or when a source is marked Processed:false.
Ready to connect★ 63
- View details
llm-wiki-maintainSkillDocs & knowledge
Routine maintenance and safe commits. Use when committing changes, rebuilding indexes, or checking overall vault health.
Ready to connect★ 63
- View details
llm-wiki-querySkillDocs & knowledge
Answer questions from the compiled Wiki. Use whenever the user asks a knowledge question that this vault might cover.
Ready to connect★ 63
- View details
markdown-blockSkillDocs & knowledge
Outputs content inside a copyable fenced markdown code block so the user can copy the raw markdown verbatim. Activate whenever the user asks for "copyable markdown", "raw markdown", "the markdown source", "give me the markdown", "as a code block I can copy", or any variation of requesting markdown t
Ready to connect★ 64
- View details
plandeckSkillDocs & knowledge
A live visual Kanban board and continuity layer for long-running agentic tasks. Nobody wants to read a markdown plan or stare at raw HTML while an agent grinds for an hour, so Plandeck turns the plan into a board that organizes itself. Use it when a task is multi-step, long-running, or needs visual
Ready to connect★ 64
- View details
post-incident-reviewSkillDocs & knowledge
Conducts a structured post-incident review following NIST SP 800-61 Rev 2 Post-Incident Activity guidance. Auto-invoked when an incident has been resolved and the team needs to conduct a blameless retrospective, reconstruct the timeline, perform root cause analysis, document lessons learned, and tra
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.
53,789 of the 54,221 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.