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: Files & storage
4,334 results · page 108 of 145
- View details
storeSkillFiles & storage
Use when tasks need local market Parquet data, factor artifacts, backtest data, or model files through DataManager.
Ready to connect★ 59
- View details
task-completion-validatorSkillFiles & storage
Task completion validator. Cross-references task file research findings, implementation checklist, and acceptance criteria against the actual git diff and test suite. Catches planned work that was never executed. Mandatory before archiving any task.
Ready to connect★ 59
- View details
test-writeSkillFiles & storage
Write or review Olympus V3 Solidity tests, including external-function coverage matrices, authorization, enabled-state, numeric boundaries, state transitions, accounting, preview/write consistency, fuzzing, invariants, file structure, naming, and error handling.
Ready to connect★ 59
- View details
verify-citationsSkillFiles & storage
Lets your agent fact-check citations and references in a document against real sources.
Ready to connect★ 59
- View details
add-footerSkillFiles & storage
Add a professional footer to README files with engagement prompts, community channels, and call-to-action for subscriptions. Use when you need to enhance your README with a footer that encourages interaction and builds community.
Ready to connect★ 58
- View details
add-resourceSkillFiles & storage
Add new learning resources (books, articles, courses, papers) to the appropriate resources.md file. Use when user mentions adding, saving, or tracking learning materials.
Ready to connect★ 58
- View details
agent-context-managerSkillFiles & storage
Lets your agent automatically load AGENTS.md instruction files alongside CLAUDE.md.
Ready to connect★ 58
- View details
agent-expert-creationSkillFiles & storage
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
Ready to connect★ 58
- View details
agent-handoffsSkillFiles & storage
Agent parameter passing, memory files, and data handoffs between agents
Ready to connect★ 58
- View details
agent-initSkillFiles & storage
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude
Ready to connect★ 58
- View details
agent-integratorSkillFiles & storage
Use this skill to create or update the root AGENTS.md file to register AgenticDev skills for AI agent discovery. Triggers include "register AgenticDev", "update AGENTS.md", "setup agent guide", or initializing a new project.
Ready to connect★ 58
- View details
agent-md-generatorSkillFiles & storage
A workflow for interactively generating GitHub Copilot agents.md files. Use when the user asks to create an agent, build a custom Copilot agent, generate agents.md, or needs help configuring GitHub Copilot custom agents. Trigger phrases include "创建代理", "生成 agent.md", "做一个文档代理", "生成测试代理", and similar
Ready to connect★ 58
- View details
agent-ops-impl-detailsSkillFiles & storage
Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to reference files for team discussion and handoff.
Ready to connect★ 58
- View details
agent-ops-optimize-instructionsSkillFiles & storage
Optimize agent instruction files by extracting sections into separate files and referencing them. Reduces context size while preserving information.
Ready to connect★ 58
- View details
agent-ops-plan-previewSkillFiles & storage
Transform implementation plans into concise stakeholder-friendly summaries with file change overviews, component listings, and optional flow diagrams.
Ready to connect★ 58
- View details
agent-ops-selective-copySkillFiles & storage
Create clean git branches from feature work, excluding agent-ops files. Use for PR preparation.
Ready to connect★ 58
- View details
agent-ops-stateSkillFiles & storage
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Ready to connect★ 58
- View details
analyze-codeSkillFiles & storage
Use when asked to analyze a file, a directory, or the whole codebase to understand structure, architecture, dependencies, complexity, duplication, dead code, or technical debt — e.g. "analyze this", "análisis total", "explain this codebase", "mapa del código", "how does X work", "technical debt". Pr
Ready to connect★ 58
- View details
competitor-aggregateSkillFiles & storage
Synthesize multiple per-competitor research files (produced by /competitor-research) into a single canonical threat matrix. Writes to marketing/competitors/aggregate.md as the locked canonical version every downstream skill reads. Triggers - "competitor aggregate", "synthesize competitors", "competi
Ready to connect★ 58
- View details
mdx-pdf-formatSkillFiles & storage
Use whenever creating, renaming, or editing any file under docs/ in this repo, or when asked to compile/build the book PDF. Enforces the exact .mdx frontmatter, ID scheme, and heading-depth rules required by the go-pretty-pdf tool (https://github.com/sazardev/go-pretty-pdf) so the whole book keeps c
Ready to connect★ 58
- View details
writing-e2e-testsSkillFiles & storage
Use when creating, modifying, or reviewing E2E tests in pkg/e2e/tests/. Triggers on "e2e test", "add e2e test", "new e2e test", or when working with files under pkg/e2e/tests/.
Ready to connect★ 58
- View details
writing-go-codeSkillFiles & storage
Use when writing, modifying, or reviewing .go files, implementing new Go functions or packages, or when Go code style and conventions are relevant.
Ready to connect★ 58
- View details
advisorSkillFiles & storage
Consult an independent, read-only GPT-5.6 advisor before committing to a substantive interpretation, approach, or final result. Not for routine work, implementation, or file edits. Always gpt-5.6-sol at xhigh effort, the flagship tier at its strongest routine setting.
Ready to connect★ 57
- View details
deck-design-pdfSkillFiles & storage
Create presentation decks as high-fidelity PDF files using web technology (HTML, CSS, Tailwind, Font Awesome). Use when the user wants a polished, pixel-perfect deck with responsive layouts, rich typography, icons, and modern design. For editable PPTX output, use deck-design-ppt instead.
Ready to connect★ 57
- View details
deck-design-pptSkillFiles & storage
Create new presentation decks as native editable PPTX files with consulting-quality design. Use when the user wants to build a new slide deck, presentation, or pitch deck from a brief or topic. For editing existing .pptx files, use the pptx skill instead.
Ready to connect★ 57
- View details
doc-to-markdownSkillFiles & storage
Read or convert any document a research workflow hands you — PDF, Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, or CSV. Use whenever a document has to be read, opened, quoted, summarized, searched, extracted, or added to a source library. Decides whether to read the file directly or convert it,
Ready to connect★ 57
- View details
Falcon Next-Gen SIEM Lookup FilesSkillFiles & storage
Create, list, download, update, and delete CrowdStrike Falcon Next-Gen SIEM lookup files. Upload CSV or JSON files for use with the match() function in CrowdStrike Query Language (CQL) queries. Use this skill when asked to manage lookup files, upload CSV data to CrowdStrike, create reference tables
Ready to connect★ 57
- View details
gptproSkillFiles & storage
Export a monorepo into review-ready zip bundles for a non-agentic frontier model (GPT Pro on the ChatGPT web UI, or any chat model with file upload) — node_modules-free, secret-free, split by subsystem so a model with no shell and a bounded context can navigate the codebase a part at a time. Use for
Ready to connect★ 57
- View details
gsxSkillFiles & storage
Use when writing or editing .gsx files — gsx templating components, JSX-style markup in Go, or when asked about gsx syntax (component declarations, interpolation, attributes, control flow, class/style, children/fallthrough).
Ready to connect★ 57
- View details
mac-storage-cleanupSkillFiles & storage
Find wasted disk space on macOS and propose cleanup candidates. Use when the user asks Codex to scan a Mac/MacBook for useless files, wasted storage, large caches, logs, downloads, build artifacts, Xcode simulator data, Docker/container leftovers, package-manager caches, node_modules, duplicate arch
Ready to connect★ 57
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.