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
4,446 results · page 80 of 149
- View details
skill-perfectionSkillFiles & storage
Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.
Ready to connect★ 123
- View details
adversarial-reviewSkillFiles & storage
Adversarial edge-case hunt over the branch diff or a single file: challenges every change for unhandled scenarios, silent failures, scope/timing/variable traps, and logic gaps rule-based review misses. Use when asked to adversarially review, stress-test, or find edge cases in a change.
Ready to connect★ 122
- View details
auditSkillFiles & storage
Comprehensive pre-merge review of one file or the whole branch diff: dispatches parallel reviewer agents (correctness, adversarial edge cases, performance, simplification, content) and merges findings. Use when asked to audit or fully review a branch or file. Replaces /review-branch.
Ready to connect★ 122
- View details
content-reviewSkillFiles & storage
Check a file or the branch diff against the full MD content review checklist (economic, political, visual, military, AI, code) with blocker tags. Use when asked to content-review country content or verify content-guideline compliance before merge.
Ready to connect★ 122
- View details
market-breadth-analyzerSkillFiles & storage
Quantifies market breadth health using TraderMonty's public CSV data. Generates a 0-100 composite score across 6 components (100 = healthy). No API key required. Use when user asks about market breadth, participation rate, advance-decline health, whether the rally is broad-based, or general market h
Ready to connect★ 122
- View details
md-tick-profilerSkillFiles & storage
Visualize and explain MD's recurring per-tick scripted workload (the daily/weekly/monthly on_action hooks and everything they run) as an interactive flamegraph sized by script ops with file:line links, plus a text report and bounded static spot checks. Use for any question about MD performance, lag,
Ready to connect★ 122
- View details
new-focusSkillFiles & storage
Scaffold a new country focus tree file with a correctly structured root focus and localisation stubs. Use when asked to create, start, or scaffold a focus tree for a country, e.g. "/new-focus SER". Takes the 3-letter TAG.
Ready to connect★ 122
- View details
sector-analystSkillFiles & storage
This skill should be used when analyzing sector rotation patterns and market cycle positioning. It fetches sector uptrend data from CSV (no API key required) and optionally accepts chart images for supplementary analysis. Use this skill when the user requests sector rotation analysis, cyclical vs de
Ready to connect★ 122
- View details
skill-integration-testerSkillFiles & storage
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity. Use when adding new workflows, modifying skill outputs, or verifying pipeline health before release.
Ready to connect★ 122
- View details
standardizeSkillFiles & storage
Auto-standardize a MD focus/event/decision/idea/MIO file with the tools/standardization/ scripts and report what changed. Use when asked to standardize, reformat, or bring a mod file up to MD conventions. Takes the file path as argument.
Ready to connect★ 122
- View details
testing-dbt-modelsSkillFiles & storage
Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task mentions "test", "validate", "data quality", "unique", "not_null", or "accepted_values" (3) Ensuring data integrity - primary keys, foreign key
Ready to connect★ 122
- View details
validateSkillFiles & storage
Run the Millennium Dawn validation tools and summarize errors by category as file:line. Use only when the user explicitly asks to validate, e.g. "/validate", "run the validators". Args: "staged" and/or "strict".
Ready to connect★ 122
- View details
qa-project-contextSkillFiles & storage
Create and fill .agents/qa-project-context.md with the project's tech stack, test frameworks, CI/CD pipeline, environments, quality goals, risk areas, team structure, and conventions. This is the one file every other QA skill reads first, so they skip redundant discovery and give context-aware advic
Ready to connect★ 121
- View details
selector-drift-recoverySkillFiles & storage
Bulk-regenerate broken test selectors after a UI refactor or redesign. Detects drift between old and new DOM with an aria-snapshot diff, maps old locators to new equivalents using role-first + region scoping, validates against the new build, and produces a single PR with grouped per-file selector up
Ready to connect★ 121
- View details
askSkillFiles & storage
Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets,
Ready to connect★ 120
- View details
deckprobeSkillFiles & storage
Inspect PDF, Microsoft Office (docx/xlsx/pptx and legacy doc/xls/ppt), and Apple iWork (key/numbers/pages) files without opening or rendering them. Use for page and slide and sheet counts, title/author/created metadata, encryption and macro and digital-signature and JavaScript risk signals, sheet an
Ready to connect★ 120
- View details
requirement-ledgerSkillFiles & storage
Run the advanced, evidence-bound Requirement Ledger CLI workflow from an explicit target, window, scope, and files; create private evidence, candidates, exact report bindings, and a read-only handoff check. Use for reproducible review/continuity, not the Codex host-selected quick audit, history disc
Ready to connect★ 120
- View details
review-codeSkillFiles & storage
Review code for quality, correctness, and fit. Use when the user wants judgment on code that already exists — their own changes, a teammate's patch, a PR, branch, commit, diff, staged changes, or one or more files to look over. Activate on requests like review, look over, sanity check, critique, cod
Ready to connect★ 120
- View details
agents-md-managerSkillFiles & storage
Audit, generate, update, and lint AGENTS.md files across all projects. Use when asked to check project context files, scaffold AGENTS.md for new projects, update stale ones, or run a cross-project audit.
Ready to connect★ 119
- View details
comfyui-node-updateSkillFiles & storage
Write and improve documentation for ComfyUI nodes in per-node JSON files. Use when asked to document nodes, write node descriptions, add tips to nodes, improve node docs, enrich node content, fill in empty node descriptions, or batch-write documentation for new/updated nodes. Also triggers on "write
Ready to connect★ 119
- View details
docstring-generatorSkillFiles & storage
Generate and update language-idiomatic doc comments for TypeScript (TSDoc/JSDoc) and Rust (Rustdoc). Use when asked to "add docs", "document this file", "generate docstrings", "add JSDoc", "add Rustdoc", "write TSDoc", or when working with TypeScript or Rust source files that need documentation comm
Ready to connect★ 119
- View details
google-workspaceSkillFiles & storage
Manage Google Workspace via the gws CLI — Drive, Gmail, Sheets, Docs, Slides, People, Chat, Meet, Forms, and cross-service workflows. Use when asked to send email, read/write spreadsheets, upload files to Drive, manage contacts, create presentations, send Chat messages, create docs, or any Google Wo
Ready to connect★ 119
- View details
pdf-readerSkillFiles & storage
Read and extract content from PDF files — text, tables, metadata, and images. Use when asked to read a PDF, extract text from a PDF, summarize a PDF, analyze a PDF document, get tables from a PDF, or check PDF metadata. Also triggers on "open this PDF", "what does this PDF say", "parse PDF", "PDF to
Ready to connect★ 119
- View details
project-learningsSkillFiles & storage
Use PROACTIVELY, without being asked, at the START of any multi-step task in a git repo, project folder, or vault (before reading files) and at the END of one (to reflect and save). Applies whenever the user asks to implement, fix, refactor, debug, or investigate something in a project, whenever a f
Ready to connect★ 119
- View details
cue-sheetsSkillFiles & storage
.cue sheet support — direct-play virtual split (open a .cue or an audio file with a sibling .cue → N playlist rows from one backing file, gapless) and library physical split-on-import (ffmpeg per-track files, off by default). Use when working on cue parsing, the AudioEngine cue boundary detector, in
Ready to connect★ 118
- View details
diagram-reports-generatorSkillFiles & storage
This skill generates comprehensive diagram and MicroSim reports for the geometry course by analyzing chapter markdown files and creating table and detail reports. Use this skill when working with an intelligent textbook (specifically geometry-course) that needs updated visualization of all diagrams
Ready to connect★ 118
- View details
excalidraw-diagram-generatorSkillFiles & storage
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system arc
Ready to connect★ 118
- View details
geiss-portSkillFiles & storage
Implementation reference for NullPlayer's Geiss visualization engine — the BSD-3-Clause port of Ryan Geiss's Win32/DirectDraw/Winamp-2 visualizer onto macOS as a ProjectM-peer engine. Covers the CGeissCore C ABI, upstream-vs-port file split, indexed-framebuffer + palette-LUT render pipeline, Acceler
Ready to connect★ 118
- View details
generate-cli-docsSkillFiles & storage
Regenerate the HTML docs site (CLI Reference, Configuration, content sections) from decorators, the pydantic config schema, and markdown source files
Ready to connect★ 118
- View details
gpu-vis-modesSkillFiles & storage
Per-mode shader and algorithm internals for the GPU visualization modes shared by both the main window and spectrum window — Fire, JWST, Lightning, Matrix, Snow, EKG. Includes Metal pass counts, audio mappings, color schemes, intensity presets, and the shader file names. Use when editing a specific
Ready to connect★ 118
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.
54,764 of the 55,196 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.