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 132 of 151
- View details
m14-mental-modelSkillDocs & knowledge
Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, comin
Ready to connect
- View details
memory-leak-detectionSkillDocs & knowledge
Detect and fix NAPI memory leaks in OpenHarmony Ability Runtime. Use when reviewing NAPI code for memory leaks, especially functions that: (1) Return napi_value, (2) Have napi_value& parameters, (3) Call napi_create_* functions, (4) Set properties with temporary napi_value variables, (5) Work in asy
Ready to connect
- View details
mtg-wikiSkillDocs & knowledge
Magic: The Gathering full knowledge base assistant. Answers MTG rules questions, looks up cards in Chinese and English, analyzes card interactions, explains formats and strategies, and tells lore. Triggered when the user asks about Magic: The Gathering topics (card names, rules concepts, formats, st
Ready to connect
- View details
oh-doc-knowledge-verifierSkillDocs & knowledge
Verifies the correctness of documentation knowledge. Reviews technical descriptions in OpenHarmony API docs for consistency with authoritative standards (W3C, CSS, etc.), mathematical definitions, or industry facts. When knowledge issues are found, further compares against the business code implemen
Ready to connect
- View details
oh-pdd-design-doc-generatorSkillDocs & knowledge
Automatically generates HarmonyOS design documents from PRD documents, including architecture design documents and functional design documents. Before generation, it analyzes the existing OpenHarmony code structure to ensure compatibility with the current architecture. Chapter 2 of the architecture
Ready to connect
- View details
oh-pdd-prd-analysisSkillDocs & knowledge
Analyzes HM Desktop PRD documents: extracts requirement information, verifies completeness, checks chapter order (requirement source → background → value analysis → competitive analysis → requirement description), checks KEP definitions, detects requirement conflicts, and generates a structured anal
Ready to connect
- View details
ohos-issue-graphics-cppcrash-analysisSkillDocs & knowledge
Use when analyzing OpenHarmony cppcrash faultlogs to locate root cause of native process crashes, investigating SIGSEGV/SIGABRT signals, memory corruption patterns, or call stack anomalies.
Ready to connect
- View details
ohos-req-intake-orchestrationSkillDocs & knowledge
Use when orchestrating OHOS Phase 0 intake workflow, from raw requirement to IR + proposal splitting + handoff contract. Triggers: requirement intake, Phase 0, requirement review, generate IR, 需求导入, 需求评审, 生成IR. Do NOT use for single-feature design work, Phase 1-9 delivery, ad-hoc document generation
Ready to connect
- View details
ohos-req-review-ppt-genSkillDocs & knowledge
Use when converting an OpenHarmony requirement document, spec, or design proposal into an OpenHarmony review slide deck (需求评审 / 需求变更评审 / 设计评审 PPTX) — produces the fixed OpenHarmony-branded review-deck structure (OH logo on every page) with architecture/flow diagrams and field tables. Triggers on "需求
Ready to connect
- View details
omcustom-release-notesSkillDocs & knowledge
Generate structured release notes from git history and closed issues within Claude Code session
Ready to connect
- View details
- View details
omcustom:wikiSkillDocs & knowledge
Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)
Ready to connect
- View details
openharmony-cppSkillDocs & knowledge
Expert coding guide for OpenHarmony C++ development. Use this skill when writing, refactoring, or reviewing C++ code for OpenHarmony projects. It enforces strict project-specific conventions (naming, formatting, headers) and critical security requirements (input validation, memory safety).
Ready to connect
- View details
paddleocr-doc-parsingSkillDocs & knowledge
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF
Ready to connect
- View details
paddleocr-skills-setupSkillDocs & knowledge
Install and configure two PaddleOCR Agent Skills for text recognition and structured document parsing in Codex, Claude Code, GitHub Copilot, Cursor, OpenCode, OpenClaw, and other compatible agents. Use for OCR and image-to-text from screenshots, photos, scans, and PDFs; Chinese/CJK text and bounding
Ready to connect
- View details
presentation-creationSkillDocs & knowledge
Create polished, audience-tailored presentations from outlines or documents, with support for Marp, reveal.js, Google Slides, and PPTX output formats.
Ready to connect
- View details
qa-lead-routingSkillDocs & knowledge
Coordinates QA workflow across planning, writing, and execution agents. Use when user requests testing, quality assurance, or test documentation.
Ready to connect
- View details
translationSkillDocs & knowledge
Translate text between languages with cultural adaptation, terminology consistency, and support for multiple document types including technical docs, marketing copy, and UI strings.
Ready to connect
- View details
unsafe-checkerSkillDocs & knowledge
CRITICAL: Use for unsafe Rust code review and FFI. Triggers on: unsafe, raw pointer, FFI, extern, transmute, *mut, *const, union, #[repr(C)], libc, std::ffi, MaybeUninit, NonNull, SAFETY comment, soundness, undefined behavior, UB, safe wrapper, memory layout, bindgen, cbindgen, CString, CStr, 安全抽象,
Ready to connect
- View details
writing-adrsSkillDocs & knowledge
Document architectural decisions. Use when making significant technical decisions that should be recorded. Covers ADR format and decision documentation.
Ready to connect
- View details
writing-pr-faqsSkillDocs & knowledge
Write Press Release / FAQ documents. Use when proposing new products or features using Amazon's working backwards method. Covers PR/FAQ format.
Ready to connect
- View details
writing-prdsSkillDocs & knowledge
Create Product Requirements Documents. Use when defining new features, projects, or initiatives. Covers user stories, acceptance criteria, and scope definition.
Ready to connect
- View details
alphaxiv-paper-lookupSkillDocs & knowledge
Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.
Ready to connect
- View details
analyze-codebase-for-mcpSkillDocs & knowledge
Analyze an arbitrary codebase to identify functions, APIs, and data sources suitable for exposure as MCP tools, producing a tool specification document. Use when planning an MCP server for an existing project, auditing a codebase before wrapping it as an AI-accessible tool surface, comparing what a
Ready to connect
- View details
analyze-kernel-bottleneckSkillDocs & knowledge
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, ti
Ready to connect
- View details
build-parameterized-reportSkillDocs & knowledge
Create parameterized Quarto or R Markdown reports that can be rendered with different inputs to generate multiple variations. Covers parameter definitions, programmatic rendering, and batch generation. Use when generating the same report for different departments, regions, or time periods; creating
Ready to connect
- View details
build-pkgdown-siteSkillDocs & knowledge
Build and deploy a pkgdown documentation site for an R package to GitHub Pages. Covers _pkgdown.yml configuration, theming, article organization, reference index customization, and deployment methods. Use when creating a documentation site for a new or existing package, customizing layout or navigat
Ready to connect
- View details
card-creatorSkillDocs & knowledge
Create atomic Obsidian knowledge cards from user-provided ideas, sources, notes, or confirmed learning outcomes. Use when the user asks to save, record, create, or turn material into a reusable knowledge card, even without naming a card type.
Ready to connect
- View details
check-healthSkillDocs & knowledge
Periodically review the health of an Obsidian knowledge base, including: detecting contradictory viewpoints, checking for broken bidirectional links, and identifying orphan cards. Trigger this skill when the user says 「检查知识库健康」, 「检查链接」, 「查孤立卡片」, 「审查观点矛盾」 or similar expressions.
Ready to connect
- View details
check-relocation-documentsSkillDocs & knowledge
Verify document completeness for each bureaucratic step of an EU/DACH relocation, flagging missing items and translation requirements. Use after creating a relocation plan and before beginning bureaucratic procedures, when preparing for a specific appointment (Buergeramt, Finanzamt), when unsure whi
Ready to connect
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.