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 693 of 2,357
- View details
eval-contentSkillDev tools
Lets your agent score marketing content for quality, voice, accuracy, and readability with fix suggestions.
Ready to connect★ 1k
- View details
eval-regressionSkillDev tools
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
Ready to connect★ 1k
- View details
eval-suiteSkillFiles & storage
Lets your agent evaluate many content pieces at once and get a ranked report with grades, issues, and revisions.
Ready to connect★ 1k
- View details
evaluating-bgs-modsSkillDev tools
Lets your agent judge whether a game mod is worth adding to a modpack before you download it.
Ready to connect★ 1k
- View details
evergreen-technical-bookSkillCloud & infra
Keep technical nonfiction durable by separating timeless concepts, decision frameworks, and reader outcomes from fast-changing tool walkthroughs, UI steps, versions, vendor details, and companion resources. Use when scoping, outlining, revising, or updating technical books, self-hosting guides, soft
Ready to connect★ 1k
- View details
evolution-coreSkillMonitoring & ops
Unified evolution asset model and self-evolution closed-loop core. Defines a three-tier asset model — Gene (strategy DNA), Capsule (validated experience snapshot), and EvolutionEvent (append-only event log) — implementing a Detect→Select→Replay→Validate→Solidify→Reuse closed loop, so that when the a
Ready to connect★ 1k
- View details
evolution-networkSkillAI & models
Cross-agent gene sharing protocol for exchanging validated evolution patterns between Claude sessions with trust downgrades and local revalidation.
Ready to connect★ 1k
- View details
exa-web-searchSkillSearch
Use the Exa MCP server for internet search and full-page retrieval. Use whenever the user asks to search, browse, look up, verify, research, find sources, find current or latest online information, discover papers or repositories, compare web sources, or read and summarize a URL whose content was no
Ready to connect★ 1k
- View details
executive-dashboardSkillMonitoring & ops
Lets your agent design a build-ready executive marketing dashboard spec with metrics, charts, alerts, and layout.
Ready to connect★ 1k
- View details
expectation-effectSkillDev tools
Apply the Expectation Effect — the principle that prior expectations measurably change a person''s perception of a product or experience. Use when shaping the framing of new features, designing onboarding, choosing visual cues that signal premium vs. budget, or diagnosing why two functionally identi
Ready to connect★ 1k
- View details
expectation-effect-design-cuesSkillMedia
Apply in-product expectation cues — typography, animation, spacing, copy tone, micro-interactions, and visual register that signal "this is the kind of product you''re using" within seconds of opening it. Use when designing the first-screen experience, picking a typography system, deciding loading-s
Ready to connect★ 1k
- View details
expectation-effect-primingSkillDev tools
Apply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it. Use when planning a launch, choosing positioning copy, deciding pricing tier, designing the marketing surface, or frami
Ready to connect★ 1k
- View details
experimentSkillDev tools
Rules as hypotheses: falsifiable tests, confidence updates, graduate or kill. Triggers: experiment, hypothesis, prove, test rule, validate methodology, evidence.
Ready to connect★ 1k
- View details
experiment-sensitivity-optimizationSkillMonitoring & ops
Improve experiment sensitivity and reduce traffic or duration requirements. Use when choosing sensitive metrics, working with minimum detectable effect, reducing variants, applying capping metrics, CUPED, variance reduction, or deciding how to get trustworthy A/B test signal with fewer users.
Ready to connect★ 1k
- View details
experiment-type-selectionSkillDev tools
Choose the right product experiment type: superiority, non-inferiority, equivalence, A/B/n, or holdback-backed validation. Use when deciding what kind of A/B test to run, when the question is not simply "is variant better," when validating no degradation, proving similarity, comparing multiple varia
Ready to connect★ 1k
- View details
experiment-verification-monitoringSkillMonitoring & ops
Verify and monitor running experiments for operational quality. Use when designing prelaunch QA, spot-check tooling, experiment canaries, A/A tests, leakage checks, interference monitoring, active experiment dashboards, alerts, or an experimentation quality roadmap.
Ready to connect★ 1k
- View details
experimentation-culture-rolloutSkillDev tools
Roll out an experimentation-friendly culture across product, engineering, data, and leadership teams. Use when introducing A/B testing to an organization, overcoming resistance to experiments, shifting teams away from launch-by-opinion, increasing experiment demand, defining rollout tactics, or crea
Ready to connect★ 1k
- View details
experimentation-strategy-roadmapSkillDev tools
Prioritize an experimentation platform roadmap across rate, quality, cost, usability, process, infrastructure, and advanced methods. Use when deciding which experimentation capability to build next, whether to platformize interleaving or adaptive testing, how to align experimentation with company go
Ready to connect★ 1k
- View details
experimentation-throughput-strategySkillProductivity
Plan experiment throughput strategies for mature A/B testing programs. Use when testing capacity is constrained, teams are waiting for experiment slots, roadmap coordination is slowing learning, or a team must choose isolated, overlapping, parallel, or capacity-aware experiment scheduling without sa
Ready to connect★ 1k
- View details
explain-decisionSkillDev tools
Fetch the full reasoning behind an AxonFlow policy decision — matched policies, risk level, override availability, recent hit count
Ready to connect★ 1k
- View details
explain-diffSkillDev tools
Explain a code change, its reasons, effects, trade-offs, and verification limits.
Ready to connect★ 1k
- View details
exposure-effectSkillDev tools
Apply the Exposure Effect (mere-exposure effect) — the well-documented finding that repeated exposure to something tends to increase liking for it. Use when launching new features, planning redesigns, building brand familiarity, or evaluating user resistance to change. Familiarity reads as comfort a
Ready to connect★ 1k
- View details
exposure-onboardingSkillDev tools
Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms. Use when designing onboarding flows, planning feature introductions, building user habits, or evaluating why users
Ready to connect★ 1k
- View details
exposure-redesign-riskSkillMedia
Manage the risks of redesigns when users have built up exposure-based preference for the existing design. Use when planning a major redesign, evaluating user backlash to changes, deciding between incremental and radical change, or recovering from a redesign that generated complaints. Users like what
Ready to connect★ 1k
- View details
fastmcp-djangoSkillCloud & infra
Use when adding, changing, deploying, testing, or debugging FastMCP MCP servers in existing Django apps, including ASGI mounting, stdio or sidecar servers, Django ORM access from MCP tools, auth and permissions, Streamable HTTP deployment, and MCP client tests.
Ready to connect★ 1k
- View details
- View details
- View details
feedback-loopSkillFiles & storage
Use this skill whenever a user takes an action and the system must communicate that the action was received, is in progress, succeeded, or failed. Trigger when designing button states, form submission, file uploads, payment flows, real-time UI updates, loading states, error states, success confirmat
Ready to connect★ 1k
- View details
feedback-loop-positive-vs-negativeSkillDev tools
Use this skill when designing system architecture or product mechanics that involve feedback loops at a higher level than UI state — recommendation engines, gamification, growth mechanics, engagement systems, or any system where one user action affects subsequent actions in compounding or stabilizin
Ready to connect★ 1k
- View details
feedback-loop-states-and-latencySkillFiles & storage
Use this skill when designing the visible states an interactive element passes through (idle / pending / success / error) and matching feedback timing to the user''s perceptual thresholds. Trigger when designing button states, form-submit flows, file-upload progress, loading screens, or any interact
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.