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
16,902 results · page 451 of 564
- View details
tailwind-4SkillDev tools
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind - :class/class usage, theme variables, no var() in class.
Ready to connect
- View details
- View details
verify-buildSkillDev tools
SeldonFrame merge gate — run unit tests + tsc + check-use-server + migration-journal + regression-grep and return ONE pass/fail verdict. Invoke before merging any branch; nothing merges without a green verdict.
Ready to connect
- View details
voice-gateSkillDev tools
Line-editor pass on any content draft against a client voice guide. Flags cadence issues, signature-move overuse, voice-guide violations, receipt gaps — things a rule-based gate can't catch. Use after /content-gate and before human review.
Ready to connect
- View details
write-readmeSkillDev tools
Create or rewrite high-quality, executable, evidence-driven bilingual READMEs for GitHub projects; use when the user asks for a README, project description, or to organize the project homepage. Prioritize verifying features, commands, and links against project facts.
Ready to connect
- View details
x-post-engineSkillDev tools
Mine the current work session (or a named event) into 2-3 draft X posts using the 6 founder-content formats, keyword-first. Drafts only — Max makes the angle call and posts. Invoke at the end of a build session or with a topic.
Ready to connect
- View details
zod-4SkillDev tools
Zod 4 schema validation patterns. Trigger: When using Zod for validation - breaking changes from v3.
Ready to connect
- View details
ad-reconSkillDev tools
Active Directory reconnaissance with or without credentials: user/group/computer enumeration, ACL/delegation, ADCS, modern Windows LAPS, BloodHound, Server 2025/dMSA/Ghost SPN candidates, and trust mapping. Recon only — do not exploit Kerberoast-to-DA, DCSync, or change passwords. Operator may selec
Ready to connect
- View details
add-unit-testsSkillDev tools
Write missing unit tests for a makeup-js module based on coverage gaps
Ready to connect
- View details
ask-boringSkillDev tools
Route a request to the right Boring v2 workflow skill without doing the work.
Ready to connect
- View details
bi-dashboard-authoringSkillDev tools
Create or edit BSL BI dashboard JSON specs for the BI Dashboard plugin.
Ready to connect
- View details
boring-feedbackSkillDev tools
Use for /feedback: create one enriched GitHub issue with safe context, lean labels, first plan, and queued or grill-blocked state.
Ready to connect
- View details
boring-loop-grillSkillDev tools
Use for /loop-grill: clarify one Kanzen issue with grill-me and ask-user, then return it to triage or keep it blocked.
Ready to connect
- View details
boring-loop-implementSkillDev tools
Use for /loop-implement: implement one Kanzen issue or approved plan, open/update the PR, run review/fix/re-review, gather proof, and prepare owner or fast-track merge handoff.
Ready to connect
- View details
boring-loop-planSkillDev tools
Use for /loop-plan: turn a Kanzen issue or PR that is too risky, unclear, large, or multi-slice for direct implementation into an issue-linked plan with acceptance, flag path, proof, review budget, and next slice.
Ready to connect
- View details
boring-triageSkillDev tools
Use for /triage in boring-ui: refresh GitHub state, classify issues/PRs, choose the first unmet gate, route grill/plan/implement/proof/merge, and decide fast-track versus owner-review routing.
Ready to connect
- View details
consultingSkillDev tools
Apply consulting methodologies from McKinsey, BCG, Bain, and Accenture for structured problem-solving and strategic analysis. Use whenever the user asks for business advice or analysis — analyzing a business problem, developing or reviewing a strategy or business plan, structuring a presentation or
Ready to connect
- View details
ecom-landing-pagesSkillDev tools
Use when someone wants landing page ideas, concepts, or angles for a store: "give me landing page concepts", "LP ideas", "landing page angles", a campaign or ad landing page, pages for a new audience/segment, a seasonal/event/promo page, or a geo/local page. Also use when a chosen concept gets picke
Ready to connect
- View details
execSkillDev tools
Drive one ready artifact through implementation, proof, review, and owner handoff.
Ready to connect
- View details
freeshard-oidc-identity-campaignSkillDev tools
Executable, decision-gated campaign to productionize the embedded OIDC identity provider inside shard_core (Authlib), replacing the rejected Authelia direction. TRIGGER on: OIDC, OpenID Connect, SSO, single sign-on, identity provider, IdP, Authlib, authorization code, PKCE, id_token, JWKS, discovery
Ready to connect
- View details
freeshard-proof-and-analysis-toolkitSkillDev tools
First-principles analysis recipes for the Freeshard repos — how to PROVE a root cause instead of pattern-matching to the first plausible fix. Use when only a subset of shards/requests fails, when two components disagree about the same bytes, when a formula is duplicated across languages, when adding
Ready to connect
- View details
freeshard-research-methodologySkillDev tools
The discipline that turns a hunch into an accepted result in the Freeshard project — evidence bar, idea lifecycle, documented retirement, where good ideas come from, and which artifact to write when. TRIGGER on "how do I propose X", "should I spike this", "is this hypothesis proven", "why did they r
Ready to connect
- View details
freeshard-testing-and-qaSkillDev tools
How to run, write, and trust tests in the freeshard (shard_core) repo. Use when running pytest, adding or modifying tests, choosing between the api_client/app_client/db fixtures, overriding config in tests, diagnosing a flaky or hanging test, or deciding what evidence a fix needs before a PR. TRIGGE
Ready to connect
- View details
fresh-eyesSkillDev tools
Read-only independent review of a plan, diff, or PR for overlooked mistakes, omissions, risks, broken acceptance, and missing proof.
Ready to connect
- View details
generated-pane-authoringSkillDev tools
Create and edit boring.generated-pane JSON specs from predefined safe component catalogs.
Ready to connect
- View details
owner-gateSkillDev tools
Raise a factory gate as a durable Inbox Human Intention and block on the owner's decision.
Ready to connect
- View details
refactor-moduleSkillDev tools
Systematically refactor a makeup-js module with modern JavaScript patterns
Ready to connect
- View details
renovate-defaultSkillDev tools
Fallback Renovate maintenance playbook, read by the `/fix` skill when no other `renovate-*` playbook matches a red Renovate dependency PR. Carries repository-wide conventions only (no dependency-specific knowledge). Use for mechanical dependency drift: a stale-generated-code `make generate` diff, `g
Ready to connect
- View details
renovate-otel-coreSkillDev tools
Renovate maintenance playbook, read by the `/fix` skill, covering the OTel collector core + contrib + API/SDK lockstep group (Renovate group label `group:otel-core-contrib`). Select when the PR moves `go.opentelemetry.io/collector` / `collector/**`, `github.com/open-telemetry/opentelemetry-collector
Ready to connect
- View details
revamp-demoSkillDev tools
Revamp a makeup-js module demo page with consistent style and structure
Ready to connect
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.
53,788 of the 54,220 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.