В каталоге 185 367 навыков в 14 категориях.
Write and test detection rules, such as Semgrep or CodeQL queries for vulnerable code patterns and Sigma rules for suspi...
Write or improve Dockerfiles and compose files with multi-stage builds, pinned base images, cache-friendly layer order,...
Health-check the installed guardrails kit — markers, doc set, versions, STATE.md shape, drift. Use when asked to check t...
Write or update project documentation such as READMEs, setup and usage guides, and API references so it matches what the...
Review TypeScript code that builds SQL with Drizzle ORM for correctness, safety, transactions, and performance, and repo...
Implement or change HTTP endpoints in a FastAPI application following FastAPI's conventions and the project's own patter...
Implement or change HTTP endpoints in a Fastify application following Fastify's conventions and the project's own patter...
Implement a new feature or behavior change end to end, tracing requirements through design, code, tests, and verificatio...
Go guardrails pack — typed-nil interfaces, slice aliasing, maps, defer, goroutine/channel traps, JSON pitfalls. Use when...
Implement or change HTTP handlers in a Go service following the project's router and patterns (net/http, chi, gin, or ec...
Review Go code for language-level defects, including goroutine leaks, data races, unchecked or shadowed errors, context...
Review Go code that accesses SQL databases through database/sql, sqlx, pgx, sqlc, or GORM for correctness, safety, trans...
Harden the security configuration in the user's repository, including HTTP security headers and Content Security Policy,...
Hooks are event-driven automation scripts that execute in response to Claude Code events. Use hooks to validate operatio...
Support a blue-team investigation of a suspected security incident by analyzing logs, alerts, and code the user provides...
Write, change, or review Kubernetes manifests, Helm charts, and Kustomize overlays with health probes, resource requests...
Review TypeScript code that builds SQL with Kysely for correctness, safety, transactions, and performance, and report fi...
Install or upgrade the guardrails kit into a project with an existing CLAUDE.md by executing MIGRATE.md exactly. Use whe...
Make a change in a monorepo or multi-module workspace (pnpm, npm, or yarn workspaces, Turborepo, Nx, Go workspaces with...
Add a new package, module, or crate to a monorepo workspace, or extract existing code into one, matching the layout and...
Prepare per-package versions and changelogs in a monorepo using the workspace's release tooling (Changesets, Nx release,...
Review a monorepo or workspace for package boundary problems, including imports that reach into another package's intern...
NoSQL guardrails pack — MongoDB $set/replace and schema drift, Redis SCAN/TTL/atomicity, eventual consistency. Use when...
Add or improve logging, metrics, tracing, and alerts in an application following its existing stack (structured loggers,...
Plan and run a multi-step engineering task by splitting it into steps, assigning each step to the installed kit skill or...
Review code or a diff specifically for unnecessary complexity, including speculative abstractions, single-implementation...
Performance guardrails pack — N+1, complexity notes, measure-before/after, unbounded growth, pagination, hot-path I/O. U...
Improve the speed or resource use of existing code by measuring first, finding the actual hotspot, changing it, and meas...
Force the guardrails planning gate before non-trivial work — TASK block, premise check, prior-art search, baseline. Use...
Review TypeScript code that uses Prisma Client for correctness, safety, transactions, and performance, and report findin...
Prepare and open pull requests (GitHub) or merge requests (GitLab) with an accurate title, description, and test plan dr...
Implement or change React components and hooks following the project's own patterns, with accessible markup, correct sta...
Post-compaction/resume recovery for the guardrails kit — re-run the SESSION.md S1 sequence manually. Use after a compact...
Reasoning scaffolds pack — worked-example traces, counterexample hunts, invariants, options enumeration. Use when writin...
Read-only audit of corporate IT — SSO coverage, device posture, SaaS inventory, joiner/leaver hygiene, helpdesk load. Us...
Restructure existing code to improve its design without changing behavior, protected by tests run before and after. Use...
Write release notes or a changelog entry from the commits and merged pull or merge requests since the previous release,...
Security guardrails pack — injection, secrets, path traversal, auth defaults, deserialization, untrusted-content discipl...
Audit a codebase or component for security vulnerabilities, including injection, broken access control, secrets, unsafe...
(ePost) This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill",...
SQL guardrails pack — NULL logic and JOIN traps, destructive-operation discipline, injection, query cost. Use when writi...
Review Python code that uses SQLAlchemy (Core or ORM, sync or asyncio, including SQLModel) for correctness, safety, sess...
Create or refresh docs/STATE.md before pausing, stopping, compaction, or handoff — guardrails session state. Use when as...
Tailwind CSS guardrails pack — dynamic class purging, v4 CSS-first config, @apply/@reference, arbitrary values. Use when...
Write, change, or review Terraform or OpenTofu configuration following the repository's module layout and conventions, w...
Testing guardrails pack — test authorship quality, regression-proof discipline, expectation-change audit. Use when writi...
Testing conventions for this project. Use when reading, writing, or reviewing files matching `**/*.test.*`, `**/*.spec.*...
Build a threat model for a planned feature, design, or component by identifying assets, actors, entry points, and trust...
TypeScript conventions for this project. Use when reading, writing, or reviewing files matching `**/*.ts`, `**/*.tsx`, `...
Force the guardrails VERIFY echo protocol — prove every done/fixed/works claim with quoted command output. Use when aske...
(ePost) Use when preparing a release, running pre-init checks, auditing kit health, or when asked to "verify", "audit ki...
Vue 3 guardrails pack — reactivity loss, ref unwrapping, v-if/v-for precedence, compiler macros, plus UI state/a11y disc...
Prove a suspected vulnerability in the user's own code with a minimal, local proof-of-concept test that fails while the...
Portable playbooks for a bug fix, a named-data-shape feature, or a behavior-preserving refactor. Apply when the user ask...
Decide what to borrow, adapt, or write before building something. Use when the user describes an app, tool, CLI, or feat...
Example Skillset that demonstrates inline + GitHub + registry dependencies.
Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files,...
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event li...
Create optimized prompts for agent-to-agent pipelines with research, planning, and execution stages. Use when building p...
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks t...
Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands,...
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagen...
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hy...
Builds the guided-tour reference for an admin page from its approved manual. Use when the user asks for the tour referen...
Control and interact with Kitty terminal windows - list windows, read output, send commands, and launch new terminals
Instructions for using kitty remote control to spawn windows/tabs, send text, inspect output, and manage processes. Usef...
Control kitty terminal via remote protocol and kitty-test-harness; launch panels/windows, send keys, capture screen, man...
Configure and control kitty terminal emulator using kitten commands, kitty.conf settings, remote control, and session au...
Table-driven testing patterns using @kitz/test. Triggers on creating test cases, parameterized tests, or when writing .t...
Type assertion patterns using @kitz/assert. Triggers on type-level tests, .test-d.ts files, or when asserting TypeScript...
KIVO — Agent Knowledge Iteration Engine. A knowledge management system for AI agents that provides knowledge extraction,...
Kivy mobile/desktop - use when working on related tasks
Use when a deploy.yml run fails on Kiwi's prod CI/CD pipeline, bootstrap-cicd.sh fails against real GCP, or you're modif...
Write Rust code in the style of Steve Klabnik, author of "The Rust Programming Language." Emphasizes clear, idiomatic co...
Wenn es um Klage: Mandantenkommunikation und Entscheidungsvorlage in Fluggastrechte geht: erstellt den passenden Entwurf...
Klage: Mandantenkommunikation und Entscheidungsvorlage im Fluggastrechte: 1. Welche Rolle hat die fragende Person und we...
Für Klage: Mandantenkommunikation und Entscheidungsvorlage: erstellt Entwurf mit Antrag, Beweis und Anlagen; Ergebnis: S...
Klagestrategie gegen Versicherer nach erfolgloser außergerichtlicher Korrespondenz. Anwendungsfall alle außergerichtlich...
Beide Rollen — entwirf eine Klageschrift zum Amtsgericht in einer Mietsache. Sachliche Zustaendigkeit fuer Wohnraummiets...
Audit E2E du module comptable KLASSCI (multi-tenant) — UI + code + CLI. À utiliser pour "audit compta", "vérifier les KP...
Déploiement coordonné cross-branch + pull + cache:clear + migrate + permissions:fix sur les 6 tenants KLASSCI en 1 comma...
Workflow complet jury de délibération LMD UEMOA — création session, composition jury, calcul auto décisions, override mo...
Audit complet des sites consommateurs de matières d'une classe — grep canonical patterns (whereHas filieres/niveaux, $cl...
Audit pre-merge complet pour une PR du chantier emploi-temps — grep canonical patterns + lint Blade compiled + tests pas...
Exécute la matrice complète de tests BTS/LMD (4 combos × Unit + Feature + Browser) avec rapport tableau croisé pass/fail...
Rejouer un test end-to-end KLASSCI supérieur sur un tenant réel. PRIORITÉ ABSOLUE = valider le fix ou la feature livré(e...
Génère un tutoriel utilisateur illustré pour une fonctionnalité KLASSCI (personnel d'école : secrétariat, coordination,...
CPC- und IPC-Klassifikation für Patentrecherche bestimmen: Erfindung soll recherchiert werden und Klassen für Datenbanks...
Klaviyo email/SMS marketing - profiles, events, flows, segmentation
Klaviyo marketing operations and analyst expertise. Audit flows, segments, campaigns, deliverability, and revenue attrib...
Automate Klaviyo tasks via Rube MCP (Composio): manage email/SMS campaigns, inspect campaign messages, track tags, and m...
Klaviyo API and developer integration expertise. Event tracking, SDKs, webhooks, rate limits, OAuth, catalog sync, and c...
Use for "is our Klaviyo sending healthy", "are our emails going to spam", "why is our Klaviyo bounce rate up", "which ca...
Use for "how are our Klaviyo flows doing", "is our abandoned cart flow good", "which Klaviyo flow underperforms", "how d...
Use for "how much of our store revenue comes from Klaviyo", "what share of Shopify sales is email and SMS", "is our Klav...
Receive and verify Klaviyo webhooks. Use when setting up Klaviyo webhook handlers, debugging Klaviyo-Signature verificat...
Network on behalf of your owner on KlawdIn. Register your agent, publish a profile, browse other agent profiles, start p...
Design distributed systems in the style of Martin Kleppmann, author of "Designing Data-Intensive Applications". Emphasiz...
Interact with Kleros Curate registries across Ethereum Mainnet, Gnosis Chain, and Sepolia. Use when the user mentions Cu...
Upload one Kleros-ecosystem file per paid request to IPFS through the Kleros x402 gateway for $0.01 USDC on Base mainnet...