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 687 of 2,357
- View details
commit-narratorSkillCommunication
Generate a conventional commit message from the staged diff
Ready to connect★ 1k
- View details
commitment-ladder-designSkillMedia
Use when designing or auditing onboarding, activation flows, habit loops, pledges, public commitments, progressive profiling, retention programs, behavior-change plans, pricing flows, or lowball-risk funnels where consistency pressure may shape user decisions.
Ready to connect★ 1k
- View details
comparative-synthesisSkillDev tools
Compare and synthesize findings across multiple completed DeepScan reports. Use when the user wants cross-run analysis, trend comparison, or a unified summary from several research sessions.
Ready to connect★ 1k
- View details
competitor-alertsSkillSearch
Lets your agent set up competitor alerts on pricing, ads, and search ranking changes, delivered via Slack or email.
Ready to connect★ 1k
- View details
completion-verifierSkillDev tools
Use before claiming a feature, plugin change, UI, API, backend, or full-stack implementation is complete.
Ready to connect★ 1k
- View details
complexity-detectionSkillProductivity
Classify a task or feature as quick, standard, or thorough so the rest of the pipeline (budget sizing, model routing, review depth) can right-size itself. Used by /ck:sketch to default the kit's complexity, by /ck:map to assign task depth, and by /ck:make for per-task budgets. Also invoked by the ck
Ready to connect★ 1k
- View details
compress-onboardingSkillFiles & storage
Use to compress any agent-instruction file (AGENTS.md, CLAUDE.md, .claude/rules/*.md, legacy AIBOARDING.md) into terse, high-signal prose without altering commands, code, URLs, or paths. Standalone compression engine with levels (off/lite/full/ultra), byte-preservation verification, and token receip
Ready to connect★ 1k
- View details
computer-usage-summarySkillWeb & browsing
Use when the user asks what they did on a Mac, requests a daily or multi-day ActivityWatch report, needs foreground app time, browser page or tab summaries, local-time activity timelines, or copyable Markdown, TSV, or CSV usage tables.
Ready to connect★ 1k
- View details
configure-canvas-mcpSkillDev tools
Lets your agent set up the Canvas coauthoring server connection when it isn't working or isn't configured.
Ready to connect★ 1k
- View details
configure-reviewSkillProductivity
Use when configuring or changing a repository's tracked branches, layered review policy, ignored tracked paths, retrieval limits, summary depth, or non-secret task-board metadata.
Ready to connect★ 1k
- View details
consistencySkillCommunication
Apply the principle of Consistency — making similar things look and behave similarly so users can transfer learning across the interface. Use when designing component libraries, defining naming conventions, choosing whether to invent or borrow patterns, auditing across surfaces (web, mobile, email,
Ready to connect★ 1k
- View details
consistency-externalSkillDev tools
Apply external consistency — honoring conventions from outside your product (platform conventions, category conventions, established interaction patterns) so users can transfer their learning into your product. Use when designing for a specific platform (iOS, Android, web), entering an established p
Ready to connect★ 1k
- View details
consistency-internalSkillMedia
Apply internal consistency — making your product coherent with itself across all surfaces, components, and flows. Use when designing or auditing component libraries, defining design tokens, settling cross-team naming conventions, planning a design-system rollout, integrating acquired or legacy code,
Ready to connect★ 1k
- View details
constraintSkillMedia
Use this skill whenever the design must structurally prevent invalid actions — input validation, disabled states, required fields, type-restricted inputs, mode locks, role-based gates, hardware lockouts. Trigger when designing forms, picking input types, designing destructive flows, gating multi-ste
Ready to connect★ 1k
- View details
constraint-physicalSkillMedia
Use this skill when designing structural constraints that prevent invalid actions through the shape, layout, or behavior of the design itself — paths (channels of motion), axes (rotary controls), barriers (blocks). Trigger when designing input controls, drag-and-drop affordances, modal dialogs, or h
Ready to connect★ 1k
- View details
constraint-psychologicalSkillDev tools
Use this skill when designing constraints that work through perception, expectation, and learned convention — symbols, conventions, mappings. Trigger when designing iconography, picking control conventions, or designing for behavioral predictability. Sub-aspect of `constraint`; read that first.
Ready to connect★ 1k
- View details
contam-mcpSkillFiles & storage
Use when working with CONTAM projects through the local contam MCP server, including discovering CONTAM executables and API integrations, listing .prj/.sim/.wth/.ctm files, inspecting or diagnosing project references, cloning scenario folders, running baseline/intervention case matrices, using conta
Ready to connect★ 1k
- View details
content-calendarSkillProductivity
Lets your agent generate a content calendar with topics, dates, platform mapping, SEO keywords, and owners.
Ready to connect★ 1k
- View details
content-decay-scanSkillDev tools
Lets your agent scan your content library for stale pages and rank which ones are worth refreshing.
Ready to connect★ 1k
- View details
contextSkillFiles & storage
Working-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction. Compaction timing is the host's job.
Ready to connect★ 1k
- View details
context-guardSkillProductivity
Preserve requirements and verified evidence across Codex compaction, resume, and delegation. Use $context-guard, context-guard on, or for long, complex, or resumed tasks requiring an immutable private completion ledger.
Ready to connect★ 1k
- View details
context-item-creationSkillDocs & knowledge
Guides you through creating context items — instructions, skills, knowledge pointers, and memory events — that give the AI analyst persistent knowledge about your organization. Covers when to create each type, naming conventions, folder organization, and the hard boundary between context (rules and
Ready to connect★ 1k
- View details
context-lifecycleSkillDocs & knowledge
Lets your agent follow a context Claude skill that manages memory tiers, compression, and recall across task phases.
Ready to connect★ 1k
- View details
context-mgmtSkillDocs & knowledge
Context engineering: compaction, progressive disclosure, structured notes via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.
Ready to connect★ 1k
- View details
context-packSkillFiles & storage
Lets your agent create handoff briefings — a context Claude skill that packages tasks for subagents.
Ready to connect★ 1k
- View details
context-recallSkillSearch
Lets your agent recall archived context claude skill notes by keyword, phase, type, or decision to recover lost details.
Ready to connect★ 1k
- View details
continuous-improvement-loopSkillDev tools
Lets your agent combine review, feedback, competitive, and operating signals into quarterly or quick improvement briefs.
Ready to connect★ 1k
- View details
contract-builderSkillDev tools
Maintain an execution contract only for an existing legacy change that requires one. New direct/planned changes do not invoke this skill when a contract is absent.
Ready to connect★ 1k
- View details
contrast-framingSkillCommunication
Use when sequencing offers, pricing tiers, proposals, negotiation anchors, product demos, before-after comparisons, concession framing, reason-giving, request wording, or comparative messaging where contrast effects or shallow reasons may distort decisions.
Ready to connect★ 1k
- View details
controlSkillProductivity
Apply the principle of Control — the level of autonomy a system gives the user, and how that level should be matched to the user''s expertise and the task''s stakes. Use when designing for novice vs. expert audiences, choosing between fully automated and manually controlled behaviors, deciding what
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.