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: Dev tools
18,403 results · page 444 of 614
- View details
lamprey-change-controlSkillDev tools
Explains your agent how changes in the Lamprey Harness repo must be classified, approved, committed, and shipped.
Ready to connect★ 64
- View details
lamprey-loop-reliability-campaignSkillDev tools
Guides your agent step by step through testing and fixing reliability problems in Lamprey's loop autonomy modes.
Ready to connect★ 64
- View details
lamprey-research-methodologySkillDev tools
Lets your agent follow Lamprey's research method, turning a hunch into an accepted, evidence-backed result.
Ready to connect★ 64
- View details
lamprey-ship-and-releaseSkillDev tools
Walks your agent through your project's release process, from tagging to publishing and fixing failed steps.
Ready to connect★ 64
- View details
pdsSkillDev tools
Operate the AT Protocol Personal Data Server in the joelclaw k8s cluster. Use when checking PDS health, reading or writing dev.joelclaw.* records, restoring the service after a rebuild, or debugging session auth / repo DID drift.
Ready to connect★ 64
- View details
planning-campaignsSkillDev tools
Lets your agent turn brand info, ads, and competitor research into concrete ad concepts worth testing next.
Ready to connect★ 62
- View details
project-triageSkillDev tools
Lets your agent inspect a Frappe project's type, apps, versions, and tooling before changes.
Ready to connect★ 64
- View details
refactor-masterSkillDev tools
Lets your agent refactor code safely without changing how it behaves.
Ready to connect★ 63
- View details
review_rubricSkillDev tools
Lets your agent run a fixed checklist to review drafts before they are sent or posted.
Ready to connect★ 64
- View details
rust-sopSkillDev tools
Standard operating procedures for writing Rust in joelclaw. Covers idiomatic patterns, async/tokio, error handling, project structure, testing, and clawnode-specific conventions. Use when writing Rust code, reviewing Rust PRs, scaffolding Rust projects, debugging ownership/lifetime errors, or workin
Ready to connect★ 64
- View details
sales_strategySkillDev tools
Lets your agent propose sales motions, tier structure, channel mix, and risks from a campaign brief.
Ready to connect★ 64
- View details
signal_researchSkillDev tools
Lets your agent find dated, sourced buying signals for target accounts before outreach.
Ready to connect★ 64
- View details
suppression_and_consentSkillDev tools
Lets your agent check do-not-call, opt-out, and consent rules before sending any outreach message.
Ready to connect★ 64
- View details
tdd-test-engineerSkillDev tools
Lets your agent write tests before code, debug flaky tests, and turn bugs into reproducible test cases.
Ready to connect★ 63
- View details
three-bodySkillDev tools
Operate Joel's ASUSTOR NAS host `three-body` safely. Use when Joel mentions three-body, ASUSTOR, NAS instability, SMB/NFS mounts, mounted drives disappearing, `/share`, `/volume1`, `/volume2`, `TMBackup-Joel`, `joelclaw`, `data`, Flagg NAS mounts, or asks to SSH into the NAS.
Ready to connect★ 64
- View details
ui-animationSkillDev tools
Lets your agent add UI motion like springs, gestures, and scroll effects using the animation claude skill.
Ready to connect★ 64
- View details
web-formsSkillDev tools
Lets your agent build public web forms for collecting customer submissions and feedback without admin access.
Ready to connect★ 64
- View details
writing-ad-copySkillDev tools
Lets your agent write ad copy — headlines, text and calls to action — sized for each ad platform.
Ready to connect★ 62
- View details
add-packageSkillDev tools
Lets your agent add a new shared package to a monorepo workspace.
Ready to connect★ 63
- View details
Administrative Value JudgmentSkillDev tools
Assists legal professionals in mainland China's administrative agencies to, based on a passage of administrative case facts, conduct value judgments and balancing of interests according to the fundamental principles of administrative law, and form a preliminary discretionary conclusion.
Ready to connect★ 63
- View details
analyst-researchSkillDev tools
End-to-end research workflow skill for investment analysts and policy researchers. Three scope modes the user picks at trigger time — light (4-5 page decision memo, ~15 min, 0 charts), medium (12-15 page topic brief, ~1 h, 6-10 charts), heavy (flagship report 30-40 pages / 15k+ words, ~2-3 h, 25-35+
Ready to connect★ 63
- View details
analyze-arbitration-agreement-markup-analysisSkillDev tools
Evaluates a counterparty redline of an arbitration agreement provision-by-provision and for interaction effects, playbook compliance, and enforcement consequences.
Ready to connect★ 63
- View details
analyze-arbitration-award-for-new-york-convention-enforcement-defensesSkillDev tools
Ensures analysis of an arbitral award for enforcement resistance covers the relevant Convention defenses, verifies the award's arithmetic independently, and addresses the applicable enforcement procedure in the forum.
Ready to connect★ 63
- View details
analyze-counterparty-markup-of-arbitration-agreementSkillDev tools
Ensures a counterparty arbitration agreement redline is analyzed for interaction effects between changes, gap-filling rules under the relevant governing law, non-signatory enforceability, and multi-agreement consolidation risks.
Ready to connect★ 63
- View details
analyze-counterparty-markup-of-procedural-orderSkillDev tools
Ensures a counterparty's procedural order markup is analyzed against the case management conference record, tactical motivations are surfaced, and aggregate procedural consequences are assessed.
Ready to connect★ 63
- View details
analyze-counterparty-markup-of-protective-orderSkillDev tools
Closes gaps in identifying compound interaction risks across protective order provisions, citing the relevant court’s prior rulings on contested issues, and making concrete recommendations with legal grounding.
Ready to connect★ 63
- View details
api-endpointSkillDev tools
Lets your agent add typed API endpoints or WebSocket routes with docs, validation, and client wiring.
Ready to connect★ 63
- View details
api-webhooksSkillDev tools
Configure inbound API webhooks end to end. Use when the user needs a webhook/callback URL, provides webhook auth or sample payloads, defines provider events, or routes webhook.received deliveries into cataloged automation events.
Ready to connect★ 63
- View details
audit-branchSkillDev tools
Pre-PR audit of the current branch — dead code, duplicate symbols, contract drift, leftover artifacts, import gaps.
Ready to connect★ 63
- View details
auto-paper-collecterSkillDev tools
Personal research-paper radar. Fetches the latest papers and code repos for the user's keyword subscriptions across arXiv, Crossref (IEEE/ACM), Semantic Scholar, GitHub, HuggingFace, Papers with Code and RSS; deduplicates against history; then YOU (the assistant) expand the queries, filter for compu
Ready to connect★ 63
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
59,937 of the 59,937 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.