denis@keisei — keiseikit-browse — 144×42
⌘1
KEISEIKIT v0.16.2DAEMON UPSLEEP 03:07
session 4f3amem 47/2002026-05-01 05:21

$ ls /skills/ | wc -l → 67

/skills store

Click-only flows. Every skill below is invokable from Claude Code via /<name>. Browse, copy install command, view source.

$ filter --by=cat=allworkflowauditdesignbuildops
[SKILL] · skillv1.0

/3d-scene

Use when building 3D scenes for web — Three.js, React Three Fiber (R3F), Spline embeds, GLTF/GLB loading, scroll-linked 3D, camera animations. Covers scene setup, model optimization, and performance

[SKILL] · skillv1.0

/a11y-audit

Use when auditing accessibility — WCAG 2.2 AA compliance, contrast checks, keyboard navigation, screen reader support, prefers-reduced-motion. Triggers on "accessibility", "a11y", "wcag", "sc

[SKILL] · skillv1.0

/ai-animation

Use when creating AI-powered animations and videos — nano-banana keyframes → Kling/Luma/Veo video generation via fal.ai → web-ready output. Full pipeline from concept to scroll-driven animation

[SKILL] · skillv1.0

/animate

Gateway router for web animation work. Picks between /scroll-animation, /motion-design, /web-effects, or /ai-animation via one AskUserQuestion call, then hands off. Does NOT implement animation — th

[SKILL] · skillv1.0

/api-design

Hub-and-spoke pipeline that produces a production-grade API design plan for a new or evolving service — style (REST / GraphQL / tRPC / gRPC), resource model, machine-readable contract (OpenAPI 3.1 o

[SKILL] · skillv1.0

/architecture

Multi-agent architectural analysis following the Holographic Development Chain. Use when user asks to design architecture, plan implementation, analyze system structure, or says "архитектур

[SKILL] · skillv1.0

/architecture-rules

Architectural rules engine — pattern validation, duplication detection, stack compatibility, and design pattern enforcement. Auto-triggers during code review, architecture planning, and when creatin

[SKILL] · skillv1.0

/auth-setup

Hub-and-spoke pipeline that produces a production-grade auth/IAM plan for a new or existing app — user flows, identity providers, session strategy, authorization model, and threat mitigations — vi

[SKILL] · skillv1.0

/batch-workflow

Use when running multi-skill pipelines — new-feature, marketing-launch, design-to-code, web-creation, full-audit, rag-setup workflows

[SKILL] · skillv1.0

/ci-scaffold

Hub-and-spoke pipeline that produces a production-grade CI/CD plan and scaffolds the workflow files for a new or existing repo — platform choice (GitHub Actions vs Forgejo Actions), build matrix, OI

[SKILL] · skillv1.0

/competitor-analysis

Deprecated alias for /research with the competitors angle preset. Routes to /research Phase-5 verification wave focused on competitor mapping, architecture analysis, and market positioning.

[SKILL] · skillv1.0

/compose-solution

Meta-orchestrator — converts a free-text task description into the right artefact(s) (agent, skill, hook, rule, or block) by composing existing KeiSeiKit primitives. Pure-click decision chain except

[SKILL] · skillv1.0

/content-pipeline

Use when creating content — research, outline, draft, SEO, format for platform, social promo

[SKILL] · skillv1.0

/debug-deep

Deep debugging using multi-agent analysis and error pattern matching. Use when user reports a bug, error, crash, or unexpected behavior. Triggers on "debug", "fix", "broken", "crash", "error".

[SKILL] · skillv1.0

/design-inspiration

Deprecated alias for /research with the design-refs angle preset. Routes to /research focused on design patterns, visual archetype references, and award-winning site teardowns.

[SKILL] · skillv1.0

/design-system

Use when building a design system — tokens, base components, Tailwind config, dark mode, docs

[SKILL] · skillv1.0

/dev-guard

Continuous parallel quality gate during development — 3 agents check every significant code change for security holes, performance traps, and pattern violations in real-time. Run after writing code,

[SKILL] · skillv1.0

/dev-ship

Pre-merge/pre-deploy parallel gate — 4 agents run final security audit, test validation, dependency check, and baseline comparison BEFORE code reaches main branch. Last line of defense.

[SKILL] · skillv1.0

/dev-start

Parallel-agent project/feature kickoff — 4 agents design contracts, scaffold tests, review security, validate structure BEFORE any code is written. Prevents 80% of audit findings at the root.

[SKILL] · skillv1.0

/docs-scaffold

5-phase documentation scaffolder — auto-detect project type, audit existing docs, generate CLAUDE.md / DECISIONS.md / runbook / README / diagrams / CHANGELOG from KeiSeiKit templates. Each phase is

[SKILL] · skillv1.0

/drive-import

Import one or more Google Drive folders as private repos into the local Forgejo dev-hub. Wraps the kei-drive-import bash wizard. Click-only path-picker, optional --scan auto-discover. Requires rclone

[SKILL] · skillv1.0

/email-sequence

Use when creating email sequences — welcome, onboarding, nurture funnels with HTML templates

[SKILL] · skillv1.0

/escalate-recurrence

Triggered when Claude detects the same mistake ≥2× in one session, or the user says "опять / again / second time / already said". Interactively codifies the pattern into a rule + hook + wiki

[SKILL] · skillv1.0

/figma-to-code

Use when converting Figma designs to code — screenshot, context, tokens, responsive implementation

[SKILL] · skillv1.0

/fix-issue

Use when fixing a GitHub issue — reproduce, trace root cause, fix, add regression test

[SKILL] · skillv1.0

/form-builder

Use when building forms — multi-step wizards, Zod validation, anti-spam (Turnstile), serverless backends, file upload, progressive enhancement. Triggers on "form", "contact form", "wizard", "

[SKILL] · skillv1.0

/frontend-design

Use when designing web UI before coding — anti-AI-slop aesthetic philosophy, typography pairing, color theory, spatial composition, motion guidelines, design archetypes. Triggers on "design", "UI

[SKILL] · skillv1.0

/hooks-control

Runtime enable/disable of KeiSeiKit hooks via env vars (v0.15.1). Click-only wizard that emits shell `export` / `unset` commands for the user to paste. Supports per-hook disable, profile switch (full

[SKILL] · skillv1.0

/landing-page

Use when creating a landing page — orchestrates design, copy, assets, animations, SEO. Supports recipe system for specific page types (apple-product, saas, portfolio, ecommerce). Triggers on "landi

[SKILL] · skillv1.0

/motion-design

Use when implementing motion design — page transitions, element animations, micro-interactions, layout animations. Covers Motion (ex Framer Motion), View Transitions API, auto-animate, SVG animation

[SKILL] · skillv1.0

/nano-banana

Generates AI images using the nano-banana CLI (Gemini 3.1 Flash default, Pro available). Handles multi-resolution (512-4K), aspect ratios, reference images for style transfer, green screen workflow fo

[SKILL] · skillv1.0

/new-agent

Generate a new project-specialist agent manifest via interactive wizard. Asks stack/deploy/domain questions via AskUserQuestion, composes blocks, writes manifest, generates .md.

[SKILL] · skillv1.0

/new-project

4-phase pipeline for bootstrapping a new multi-agent project — intake, fork skeleton (branch + ledger row + sub-agent spawn), parallel execution with progress aggregation, and per-branch merge cerem

[SKILL] · skillv1.0

/observability-setup

Hub-and-spoke pipeline for installing the logs + metrics + traces triad on an existing service. Decomposes into 5 phases — scale/stack intake, code-side instrumentation, scrape+ship wiring, dashboar

[SKILL] · skillv1.0

/onboard

Scan a project (or scope of projects) and propose candidate agents, hooks, and primitives based on detected stack, CI, deploy, tests, and env surface. Three modes — Full auto, Step-by-step, Full man

[SKILL] · skillv1.0

/perf-audit

Use when auditing performance — baseline, profile, identify top 3 bottlenecks, fix, remeasure

[SKILL] · skillv1.0

/pet-init

Create a personal AI pet persona via interactive wizard. No TOML editing required.

[SKILL] · skillv1.0

/playwright-cli

Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping. Token-efficient alternative to MCP. Use when user asks to test UI, automate browser, take screenshots, fill f

[SKILL] · skillv1.0

/pr-review

Use when reviewing a pull request — Constructor Pattern awareness, security, SSOT check

[SKILL] · skillv1.0

/quick-api

Use when scaffolding a new API endpoint — types, test, handler, validation, route, docs

[SKILL] · skillv1.0

/rag-pipeline

Use when building RAG (Retrieval-Augmented Generation) systems — embedding pipeline, vector database, document ingestion, semantic search, hybrid search. Triggers on "RAG", "embeddings", "vecto

[SKILL] · skillv1.0

/refactor

Use when refactoring code while preserving behavior — checkpoint, extract, test, audit

[SKILL] · skillv1.0

/research

Deep research on any topic using parallel agents, web search, and cross-referencing. Use when user asks to research, investigate, or deeply analyze a topic, technology, library, or concept. Triggers o

[SKILL] · skillv1.0

/responsive-audit

Use when auditing responsive design — 6 breakpoints, layout, touch targets, overflow, images

[SKILL] · skillv1.0

/schema-design

Hub-and-spoke pipeline that converts "I need a database for app X" into a designed relational schema, a generated first migration, and optional seed/fixture data — via pure-click decisions across

[SKILL] · skillv1.0

/scroll-animation

Use when building scroll-driven animations — GSAP ScrollTrigger, CSS scroll-timeline, frame sequences, parallax, pin/scrub effects. Covers Apple-style scroll playback, progress-linked animations, an

[SKILL] · skillv1.0

/self-audit

Session retrospective triage (RULE 0.14). Runs `kei-memory analyze + patterns`, classifies findings, presents them via click-only AskUserQuestion, routes each selected item to `/escalate-recurrence` (

[SKILL] · skillv1.0

/seo-audit

Use when auditing SEO — technical + content analysis via WebFetch and code inspection

[SKILL] · skillv1.0

/session-budget

Use when tracking token/cost budget per session — monitors API usage and compute costs

[SKILL] · skillv1.0

/share-page

Use when you need to share an HTML page (visual report, diagram, presentation) via a public URL. Triggers on "share", "поделись ссылкой", "выгрузи", "задеплой".

[SKILL] · skillv1.0

/site-builder

Build a website from block recipes via interactive wizard. Asks stack/type/style/sections via AskUserQuestion, generates one section at a time, enforces WYSIWYD (what you see in the mock is byte-ident

[SKILL] · skillv1.0

/site-create

End-to-end site pipeline — intake → design → sections → WYSIWYD mock-render loop → parallel audits → preview → deploy. Pure-click (≥8 AskUserQuestion blocks). The mock-render verify ga

[SKILL] · skillv1.0

/site-teardown

"Deconstruct any live website into reusable recipe — extract HTML, CSS, JS, design tokens, animations. Use when user says: teardown, deconstruct, clone site, reverse engineer, how is this site buil

[SKILL] · skillv1.0

/sleep-on-it

Defer a hard question, research task, or design comparison to the nightly remote agent (KeiSeiKit v0.12.0 incubation layer). Runs on top of the v0.11 sleep-sync pipeline — user fills one free-text f

[SKILL] · skillv1.0

/sleep-setup

One-time wizard (5) that configures KeiSeiKit sleep layer. Phase 0 picks mode (local-only / remote-only / hybrid); Phase 0b picks local trigger time (6 options incl. Custom HH:MM). Remote/hybrid gener

[SKILL] · skillv1.0

/social-post

Use when creating platform-optimized social posts — Twitter threads, LinkedIn, Instagram, Telegram

[SKILL] · skillv1.0

/spawn-agent

Prepare a composed Agent-tool invocation via kei-spawn. Click-only wizard — pick role, describe task, set scope. Emits ready-to-paste prompt + subagent_type + isolation + DNA.

[SKILL] · skillv1.0

/test-gen

Use when generating tests for untested code — happy path, edge cases, error handling

[SKILL] · skillv1.0

/test-matrix

"Use when a project needs testing BEYOND unit tests — fuzzing, property-based, load, E2E, or mutation. Five-phase hub-and-spoke pipeline composes the right mix per language × critical path × CI t

[SKILL] · skillv1.0

/ui-component

Use when building a UI component — API design, variants, accessibility, animations, tests

[SKILL] · skillv1.0

/video-gen

Use when generating video from frame sequences — FFmpeg extraction, WebP/AVIF conversion, sprite sheets, scroll-synced playback, video encoding/transcoding. Covers the full pipeline from video sourc

[SKILL] · skillv1.0

/visual-explainer

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, proje

[SKILL] · skillv1.0

/vm-provision

End-to-end VPS provisioning — select provider → plan → provision → harden → verify (ssh-check + firewall-diff hard-gate) → handoff. 6 phases, ≥6 AskUserQuestion calls, defensive-only. St

[SKILL] · skillv1.0

/wave-audit

3-wave parallel audit — Wave 1 discovery (4 agents), Wave 2 verification (4 agents), Wave 3 cross-optimization (1 synthesizer). Each wave runs agents in parallel. Combines security review, runtime a

[SKILL] · skillv1.0

/web-assets

Use when optimizing images, fonts, and video for web — AVIF pipeline, responsive srcset, font subsetting, video codec selection, Sharp.js processing. Triggers on "optimize images", "web assets",

[SKILL] · skillv1.0

/web-deploy

Use when deploying websites — Cloudflare Pages, Vercel, edge functions, caching strategy, Core Web Vitals, CI/CD pipeline, DNS setup. Triggers on "deploy", "hosting", "cloudflare pages", "web

[SKILL] · skillv1.0

/web-effects

Use when building visual web effects — WebGL shaders, image distortion, particles, noise/grain, hover effects, displacement maps. Covers curtains.js, OGL, tsParticles, custom WebGL, and CSS-only eff

publish your own skill

Browsing is open. To publish a skill into the store you need a creator account.