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 137 of 145
- View details
create-slidesSkillFiles & storage
Creates a single HTML file presentation based on vertical scrolling + scroll-snap. Implemented in pure HTML+CSS without slide libraries, supporting dark/light themes, frontend-design skill integration, and highlight.js·Mermaid·KaTeX·Chart.js·Iconify CDNs. Triggers: "make a presentation", "create sli
Ready to connect
- View details
desktop-agentSkillFiles & storage
Native Windows desktop bridge — breaks out of Claude Code's Git Bash sandbox to open terminal windows, launch URLs, open files, run commands, and send toast notifications on the user's actual desktop. Use when: (1) user says "open", "launch", "start", "show me", "pop up", "new window", (2) you need
Ready to connect
- View details
direct-integrationsSkillFiles & storage
Query Gmail, Google Calendar, Asana, Slack, Google Sheets, Google Docs, and Google Drive directly via Python APIs. Use when the user asks to check email, view calendar, list tasks, check Slack messages, read/write spreadsheets, read documents, or find files in Drive. Triggers on requests like "check
Ready to connect
- View details
environment-config-auditorSkillFiles & storage
Reviews .env/config files for consistency and missing required variables across environments. Use when comparing dev/staging/prod config, or debugging an "it works locally but not in prod" issue.
Ready to connect
- View details
example-skillSkillFiles & storage
Duplicate this file to create a project skill. Write the trigger conditions specifically in the description.
Ready to connect
- View details
explainSkillFiles & storage
Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whether it's good.
Ready to connect
- View details
file-hygieneSkillFiles & storage
1C file hygiene loop: encoding, BOM, disallowed control characters, dashes instead of ASCII hyphens, line ending consistency. A cheap byte-level check run on any change to 1C files. Invoked by the quality-gate orchestrator; directly — on request like "check encodings", "why does the platf
Ready to connect
- View details
flySkillFiles & storage
Use when executing a preflight checklist. Triggers: 'fly', 'launch execution', 'run the checklist', or when given a preflight checklist file path.
Ready to connect
- View details
geo-llmstxtSkillFiles & storage
Analyzes and generates llms.txt files -- a lightweight anti-hallucination facts hedge that tells AI systems your canonical business facts and key pages. NOT an AI-visibility or citation lever (debunked by Google, Zyppy, and SE Ranking). Can validate existing llms.txt files or generate new ones from
Ready to connect
- View details
gns-hazards-nzSkillFiles & storage
Use when a task needs source-derived New Zealand active-fault features, ArcGIS layer metadata, latest modelled shaking contours, or versioned GeoNet ShakingLayers event files and contour GeoJSON. Provides read-only GNS Science and GeoNet discovery, count, ID, paging, metadata, and spatial-query prim
Ready to connect
- View details
homie-self-mapSkillFiles & storage
Framework architecture map for The Homie. Use when an agent needs to understand the framework's vertical slice structure, locate key files, or extend the framework (add a skill, slash command, integration, or lane). Load this skill BEFORE attempting to modify or extend the framework.
Ready to connect
- View details
hyaloSkillFiles & storage
Use the hyalo CLI instead of read/edit/grep/write when working with markdown (.md) files that have YAML frontmatter. This skill MUST be consulted whenever pi is working with markdown documentation directories, knowledgebases, wikis, notes, Obsidian-compatible collections, Zettelkasten systems, itera
Ready to connect
- View details
hyalo-changelogSkillFiles & storage
Maintain Keep a Changelog files with Hyalo's changelog profile and add/release commands.
Ready to connect
- View details
instruction-evalSkillFiles & storage
Evaluate whether changes to skills and CLAUDE.md files have helped or harmed Claude's operational posture. Use when: (1) after trimming or refactoring skills/CLAUDE.md files, (2) doing a periodic regression check, (3) validating that factored reference files are still accessible, (4) confirming hard
Ready to connect
- View details
iparq-parquet-inspectorSkillFiles & storage
Inspect Parquet file metadata with the iParq CLI, including compression, encodings, physical and logical types, row groups, sort order, statistics, geospatial statistics, dictionary pages, page indexes, page locations, Bloom filters, and storage sizes. Use when an agent needs to explain how one or m
Ready to connect
- View details
mcp-bridgeSkillFiles & storage
Connect arbitrary Model Context Protocol (MCP) servers as on-demand tool sources for the agent, with progressive disclosure so tool definitions don't bloat the context window. Use when the user wants to add an external MCP server (Zapier, filesystem, GitHub, a custom server), list its tools, or call
Ready to connect
- View details
memory-factcheckSkillFiles & storage
Cross-check agent persistent memory against actual sources — verifies each memory's key claims against code, DB, issue trackers, and the filesystem to correct stale entries and report dead ones as archive candidates. Use when memory exceeds 30 entries, right after major stack/infrastructure changes
Ready to connect
- View details
mm-clear-gateSkillFiles & storage
A gate before /clear — a read-only check of "whether everything has been saved", with the verdict taken from the script's exit code, not from the model's reply. Checks the freshness of the GSD-handoff in the project repository, the freshness of vault files for Project Knowledge, the state of the vau
Ready to connect
- View details
mm-focusSkillFiles & storage
RETIRED 2026-08-02 — the command no longer loads anything. Its stage detection duplicated /gsd-resume-work and diverged from the actual GSD layout, causing it to load the wrong files without saying so. Replacement: /gsd-resume-work; for silent loading without a menu, directly ask to read the phase f
Ready to connect
- View details
mm-handoffSkillFiles & storage
Generates handoff.md — a compact summary for a new claude.ai chat when the current context is full. Includes a 15-category Session Guide (inspired by context-mode), a digest of recent sessions, current state, open questions, and (if GSD is present) the current phase + last 3 SUMMARY.md files. Use wh
Ready to connect
- View details
naming-consultantSkillFiles & storage
Suggests consistent, well-reasoned names for variables, functions, files, or classes given context. Use when a name feels off, ambiguous, or inconsistent with surrounding conventions.
Ready to connect
- View details
onboarding-guide-generatorSkillFiles & storage
Generates a new-engineer onboarding guide from a codebase's actual structure - setup steps, architecture overview, key files, and where to start. Use when a project has no onboarding doc or an outdated one.
Ready to connect
- View details
pin-recordSkillFiles & storage
Use when you need to record a single pin entity to the knowledge graph. Invokes lib/pins record() to validate and write a canonical .md file. Triggers on "record pin", "pin this", "save this as a pin".
Ready to connect
- View details
pin-setupSkillFiles & storage
Use when initializing the pins knowledge graph for the first time in a project. Guides the user through creating pins.yaml (the storage manifest). Triggers on "setup pins", "initialize pins", "create pins.yaml", "first-run pins".
Ready to connect
- View details
readme-builderSkillFiles & storage
Creates professional README files for GitHub projects, covering purpose, installation, usage, and contribution info. Use when a repo has no README or an outdated/thin one.
Ready to connect
- View details
self-improvementSkillFiles & storage
Capture user feedback and corrections to enhance repository documentation and skills. Transforms conversational feedback into persistent knowledge by updating the appropriate CLAUDE.md files, skills, or other documentation.
Ready to connect
- View details
slides-reviewSkillFiles & storage
HTML design review skill using Gemini CLI. Passes generated HTML files to Gemini to receive visual design improvement guidance, then fixes CSS/HTML in the main session. Includes an in-session fallback when Gemini is unavailable. Triggers: "디자인 리뷰", "gemini review", "design review", "디자인 검토", "디자인 보완
Ready to connect
- View details
source-command-qcheckSkillFiles & storage
Skeptical staff-engineer code review of changed files against coding-standards.md.
Ready to connect
- View details
subagent-task-orchestratorSkillFiles & storage
Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates subagent task layer. Pair this skill with an AgentDef whose tool filter strips the implementation tools (terminal, file, web, code) — that's how 'don't do the work yourself' is enforced
Ready to connect
- View details
sync-claudeSkillFiles & storage
Validate and synchronize Claude documentation (CLAUDE.md files and skills) against actual codebase state. Two modes: full (all docs) or changed (only docs affected by current branch, default).
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.