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 140 of 145
- View details
benchSkillFiles & storage
Lets your agent store and query knowledge graphs to answer questions using connected data.
Ready to connect
- View details
claude-md-generatorSkillFiles & storage
Generates smart CLAUDE.md files for consumer projects. Consumes Repo Auditor output, conducts a guided interview with the developer, and produces a specific, concise, actionable CLAUDE.md. Use after Repo Auditor (18) has mapped the repository. Trigger on: "gerar claude.md", "criar claude.md", "onboa
Ready to connect
- View details
claude-permissionsSkillFiles & storage
Apply when editing settings.local.json or debugging why a command still prompts. Esposter Claude Code permission-rule conventions for the allow-only .agents/settings.local.json — the shipped file is the standard (a command taking arguments is the trailing space-star form, colon sub-scripts get their
Ready to connect
- View details
code-connectSkillFiles & storage
Creates and maintains Figma Code Connect files (`*.figma.tsx`) that map Figma components to code via the parser-based `figma.connect()` API. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.tsx files.
Ready to connect
- View details
component-anatomySkillFiles & storage
Use when creating, naming, or placing a file or folder in libs/*, or when modifying or adding a file to an existing component (even when the barrel isn't touched) — component vs utility naming, the one-responsibility-per-file layout, when a folder needs an `index.ts` barrel (public API only), and th
Ready to connect
- View details
context-efficiencySkillFiles & storage
Apply when a task spans many files, when waiting on an external process from the shell, or when deciding what to pull into the session. Esposter context and turn efficiency — delegate wide reads and keep the dumps out of the session, never tail a subagent's transcript, read the range not the file, f
Ready to connect
- View details
cred-read-onlySkillFiles & storage
Reads a local dotenv file and prints keys, not values.
Ready to connect
- View details
deepenSkillFiles & storage
Use when the user wants to know where the design is hurting, before choosing what to fix: "this is getting messy", "where should we clean up?", "what is the worst part of this codebase?", "why is this so hard to change?", "it takes five files to add one field". Surveys an area, ranks the candidates,
Ready to connect
- View details
diptrace-production-packSkillFiles & storage
RAG-backed. Prepare and inspect a versioned DipTrace fabrication and assembly package with real native CAM files, reconciled BOM/CPL, production instructions, and release evidence. Use for Gerber/NC Drill, assembly files, JLCPCB handoff, or a fabrication release; «файлы на производство». Use when th
Ready to connect
- View details
ferrox-captureSkillFiles & storage
An idea, note or todo you do not want to lose right now. Files it where it belongs
Ready to connect
- View details
ferrox-mempalace-captureSkillFiles & storage
File a finished artifact into MemPalace and mirror its decisions into the temporal graph
Ready to connect
- View details
figma-token-syncSkillFiles & storage
Sync processed CSS design tokens with JavaScript theme objects for React Native. Use when aligning tokens after Figma sync, checking token consistency, or updating JS theme files manually.
Ready to connect
- View details
file-tech-debtSkillFiles & storage
File a new tech-debt GitHub issue for an out-of-scope code-review finding, building the dedup key, checking for an existing open or declined-closed match, and only if none exists, creating the issue with the right labels and touching the debt-count staleness sentinel. Trigger on natural-language ask
Ready to connect
- View details
formattingSkillFiles & storage
Lets your agent run Remotion formatting and style checks repeatedly until they pass.
Ready to connect
- View details
gemini-web-media-analysisSkillFiles & storage
Attach a local image or video to gemini.google.com through Chrome automation and get an analysis, without opening a native file dialog. Use when a second opinion on a screenshot, render, contact sheet, frame grid, or gameplay capture is wanted and the user is already signed in to Gemini in Chrome. B
Ready to connect
- View details
landingSkillFiles & storage
Lets your agent build a polished single-page HTML landing site with animations from your product description.
Ready to connect
- View details
lofn-step11-packagerSkillFiles & storage
Build complete Step 11 refinement prompt bundles (the "fable packager") for a Lofn music run — full personality YAML + Suno v5.5 rules + golden songs + full run context + step-10 (and any prior step-11 draft) + the canonical Manual Refinement Instructions, as paste-ready 120-200KB prompt files for C
Ready to connect
- View details
meta-muse-video-analysisSkillFiles & storage
Analyze local video files with the fixed Meta Model API model Muse Spark 1.2 Contributor and a user-defined prompt. Use when Codex or Claude Code is asked to inspect, summarize, transcribe, timestamp, inventory, review, or extract information from a video and the META_MUSE_KEY Windows environment va
Ready to connect
- View details
midi-synthSkillFiles & storage
Synthesize and render MIDI/MusicXML files to audio (WAV/MP3) and generate Strudel live-coding patterns for creative music manipulation. Uses analysis data (tempo, key, chords, dynamics) from audio-to-midi for intelligent ghost-note removal and accurate reproduction. Two workflows: (1) Convert MIDI/M
Ready to connect
- View details
new-componentSkillFiles & storage
Scaffold a new React component with optional Storybook story and Vitest test files. Use this skill whenever the user asks to "create a component", "make a button", "scaffold a card", "add a new component", or asks for a new file under `app/components/` following the project's component pattern (Pasc
Ready to connect
- View details
new-hookSkillFiles & storage
Scaffold a new custom React hook with a Vitest test file. Use this skill whenever the user asks to "create a hook", "make a useFoo hook", "scaffold a custom React hook", "add a hook under app/hooks", or describes a piece of reusable React state/effect logic that warrants extraction into a named `use
Ready to connect
- View details
new-routeSkillFiles & storage
Scaffold a new route with its page component, test, story, and optional i18n keys. Use this skill whenever the user asks to "create a route", "add a new page", "scaffold /dashboard", "wire up a new route under _public+ or _session+", or anything that implies adding a file under `app/routes/` with a
Ready to connect
- View details
oc-approveSkillFiles & storage
Approval gate for dangerous operations. Use internally before executing destructive commands, file deletions, git pushes, or external API calls from the web chat. Do NOT invoke directly.
Ready to connect
- View details
oc-filesSkillFiles & storage
Manage files and create temporary share links for the web chat. Use when the user says 'share file', 'send file', 'list files', 'download', or when you need to provide a file to the user via the chat. Also use when you generate a file (PDF, image, code, etc.) and want to let the user download it.
Ready to connect
- View details
pattern-conformitySkillFiles & storage
Extracts and encodes the coding patterns of the existing project (naming, file structure, error handling, testing style, import style, API design, async patterns) and uses these patterns as constraints on new code. Ensures the agent codes "like the rest of the project" instead of inventing conventio
Ready to connect
- View details
Preventing Subagent CollisionsSkillFiles & storage
Prevent task duplication, file conflicts, and coordination failures when multiple subagents work in parallel on the same Superagent project. Covers both Superagent→Subagent coordination and Master Agent→Superagent worktree coordination. Uses manage_plan and manage_tasks as the coordination hub.
Ready to connect
- View details
pulumi-infraSkillFiles & storage
Apply when modifying apps/infra. Esposter Pulumi infrastructure conventions for apps/infra — one resource per file under src/<provider>/resources/<ProviderNamespace>/<resourceTypes>/ named after the Azure resource, protect on imported resources, a parent on every new resource, resource outputs over
Ready to connect
- View details
release-planSkillFiles & storage
Use when generating or editing an Nx version plan in .nx/version-plans/ — the bump type must always be `patch`, one package per file.
Ready to connect
- View details
robust-editSkillFiles & storage
Robust, line-based file editing. Replace a range of lines in a file with new content by line number instead of exact string matching. Use when the user says 'robust-edit', '/robust-edit', 'replace lines', 'edit lines N to M', or when character-level matching with the Edit tool keeps failing on multi
Ready to connect
- View details
routeSkillFiles & storage
Use at the start of a task that spans multiple files, touches unfamiliar areas of a codebase, or where it isn't obvious what to load or where to begin. Skips itself for a one-line change or an already-scoped task.
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.
53,788 of the 54,220 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.