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.
Filter by category
70,704 results · page 686 of 2,357
- View details
claude-code-harnessSkillDocs & knowledge
Design a real harness for an agentic system using Claude Code-inspired patterns. Use when the user needs a harness blueprint, request assembly design, execution loop, tool runtime, memory layering, permission model, transcript or recovery strategy, or wants to turn a vague agent idea into a harness-
Ready to connect★ 1k
- View details
claude-md-drift-checkSkillFiles & storage
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Ten checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness, session-file existence, command-count sync, session-config-parity (mandatory templat
Ready to connect★ 1k
- View details
clean-roomSkillProductivity
Use for authorized clean-room, reverse-engineering, source-to-implementation, compatibility rewrite, or migration tasks. Produces clean behavioral specs, implementation plans, clean code changes, verification reports, QC reports, open questions, and test plans without moving source expression into t
Ready to connect★ 1k
- View details
clean-room-loopSkillProductivity
Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room / reverse-engineering / source-to-clean-implementation task hands-off but without paying per-toke
Ready to connect★ 1k
- View details
clickSkillDev tools
Record revision-aware evidence for software work by default, or bind higher-risk execution to one human-readable approval contract in Guarded mode. Use when Click Hook context enables Evidence or Guarded mode, or when the user explicitly selects Click. Do not use for questions or explanations.
Ready to connect★ 1k
- View details
client-proposalSkillDocs & knowledge
Lets your agent draft a full client proposal with summary, scope, pricing options, KPIs, and terms.
Ready to connect★ 1k
- View details
client-reportSkillDev tools
Lets your agent generate branded client marketing reports with KPI scorecards, channel breakdowns, and recommendations.
Ready to connect★ 1k
- View details
client-side-jsSkillWeb & browsing
Use when a val needs to ship JavaScript that runs in the browser — React apps, vanilla DOM scripts, canvas/games, htmx/Alpine, or any client-side module beyond a single inline snippet. Explains how Val Town serves transpiled .ts/.tsx/.jsx modules with no build step, how the browser resolves their im
Ready to connect★ 1k
- View details
client-validation-documentSkillDocs & knowledge
Lets your agent compile audit findings into a client validation document with accept or reject decision blocks.
Ready to connect★ 1k
- View details
closureSkillCommerce & finance
Apply the Gestalt principle of Closure — the perceptual tendency to see incomplete shapes as whole. Use when designing icons (a few strokes can imply a closed shape), illustrations (negative space defines forms), logos (the IBM stripes, the WWF panda, the FedEx arrow), card layouts (cards don''t nee
Ready to connect★ 1k
- View details
closure-completion-costSkillMedia
Recognize when closure is the wrong choice — when the perceptual completion work it asks of the user is too costly, ambiguous, or risky. Use when designing for accessibility audiences, novice users, high-stakes interfaces (medical, financial, safety), small rendering sizes that strain perception, or
Ready to connect★ 1k
- View details
closure-implied-shapesSkillMedia
Design forms that exploit closure — suggesting shapes through partial outlines, negative space, or strategic gaps so the user''s perception completes them. Use when designing icons that need to read at small sizes, logos that need memorability, illustrations with restraint, card layouts with implied
Ready to connect★ 1k
- View details
code-navigationSkillAI & models
CodeGraph-first code navigation with LSP and grep fallback. Provides agents with a reusable strategy for semantic code exploration -- codegraph tools when available, LSP goToDefinition/findReferences/documentSymbol otherwise, grep as last resort.
Ready to connect★ 1k
- View details
code-sample-documentationSkillDocs & knowledge
Design, write, review, and test code samples in developer documentation, including executable examples, explanatory snippets, request and response pairs, placeholders, outputs, language choice, sandboxing, and autogenerated samples. Use when docs include API examples, SDK snippets, CLI commands, con
Ready to connect★ 1k
- View details
codebase-explorationSkillSearch
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are a
Ready to connect★ 1k
- View details
codebase-managementSkillFiles & storage
Set up, index, and manage SocratiCode codebase indexing. Use when the user wants to index a project, check infrastructure health, start/stop file watching, configure context artifacts, troubleshoot indexing issues, manage the code graph, or any SocratiCode administrative task. Activates when the use
Ready to connect★ 1k
- View details
codebase-reconSkillDev tools
Use when entering an unfamiliar codebase, onboarding to a new project, or wanting to assess codebase health before reading code — analyzes git history to reveal hotspots, risk areas, team structure, and development momentum
Ready to connect★ 1k
- View details
codegraphSkillSearch
Lets your agent search code symbols, trace call chains, and analyze the impact of changes in a codebase.
Ready to connect★ 1k
- View details
codetrussSkillFiles & storage
Operate CodeTruss local acceptance gates for coding-agent changes. Use when a developer asks to bind an agent task to allowed or denied files, configure repository verification, install or diagnose Claude Code or Codex hooks, review a working-tree or staged diff before commit, interpret or verify a
Ready to connect★ 1k
- View details
codex-auth-setupSkillDev tools
Install or refresh codex-multi-auth for the official Codex CLI, run first login, and verify account health and routing.
Ready to connect★ 1k
- View details
codex-resetSkillDev tools
Drop the runtime markers and deadline without deleting the owner's work or evidence.
Ready to connect★ 1k
- View details
codex-skin-pack-installerSkillDev tools
Lets your agent find, download, and apply Codex desktop themes and skin packs via a codex claude skill.
Ready to connect★ 1k
- View details
codex-tasklistSkillDev tools
Maintain the current Codex session's user-request queue and terminal panel, or set up its simple launcher with tmux fallback. This queue tracks user requests, not implementation steps or GitHub issues.
Ready to connect★ 1k
- View details
codiris-agentizerSkillWeb & browsing
Lets your agent turn an existing website into an agent-first experience.
Ready to connect★ 1k
- View details
cognition-routerSkillDocs & knowledge
Use this skill whenever a design task involves cognition, mental models, learnability, complexity reduction, defaults, memory, scanning, or comprehension — regardless of framework or platform. Trigger when the user is designing forms, settings, onboarding, dashboards with many widgets, complex table
Ready to connect★ 1k
- View details
colorSkillDev tools
Use this skill whenever color decisions matter — picking the brand primary, defining a neutral ramp, designing status semantics (success/warning/error), choosing chart palettes, selecting accent hues, supporting dark mode, ensuring colorblind-safe contrast, or auditing an existing UI for color noise
Ready to connect★ 1k
- View details
color-accessibility-and-modeSkillDev tools
Use this skill when designing color systems that must satisfy accessibility requirements, work in both light and dark modes, support high-contrast preferences, and remain meaningful for users with color blindness or low vision. Trigger when picking text colors, designing for global compliance (WCAG,
Ready to connect★ 1k
- View details
color-math-accessibilitySkillAI & models
Calculate, review, and generate web color systems using RGB, HSL, LAB, OKLCH, contrast ratios, luminance, opacity, blend modes, and light/dark mode transformations. Use when auditing accessible colors, converting color models, deriving palettes, checking WCAG contrast, building theme tokens, or debu
Ready to connect★ 1k
- View details
color-semantic-systemsSkillDev tools
Use this skill when building or auditing a color system that encodes meaning — status colors (success / warning / error), category colors (department, product line, user segment), brand-role colors (primary, secondary, tertiary). Trigger when designing status badges, picking chart palettes, building
Ready to connect★ 1k
- View details
commercial-demand-researchSkillDev tools
Research commercial demand by niche, geography, product, or service via Wordstat before moving to advertising semantics.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.