← All skill packs

AI Agent & Automation Workflows

Skill pack
24 skills0 selected
keiseilabSkills in this pack

Architectural rules engine — pattern validation, duplication detection, stack compatibility, and design pattern enforcement. Auto-triggers during code review, architecture planning, and when creating new modules. Triggers on "проверь архитектуру", "review architecture", "check patterns", "проверь дублирование", "stack compatibility".

English

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

English

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, OIDC-vs-token secrets posture, release automation, and a security gate — via pure-click decisions across five phases. Emits .github/workflows/.yml or .forgejo/workflows/.yml, a secrets-env scaffold (RULE 0.8), and runs kei-ci-lint before handing off. Never writes secret values.

English

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 the single intake field. Enriches blocks/ over time via Phase 6 block-augmentation — the kit gets smarter with every invocation.

English

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 budgets.

English

Curated collection of top-tier website designs organized by category, style, and pattern. Includes SaaS, marketing, e-commerce, and portfolio sites with analysis of what makes them effective. Use when looking for design inspiration or examples of specific patterns.

English

Pre-merge/pre-deploy parallel gate — 4 backend agents (security, tests, deps, regression) plus optional 5th frontend-final-gate agent (production build, Lighthouse, axe full, visual diff full) run final checks BEFORE code reaches main. Last line of defense.

English

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 a click-driven file in this skill directory.

English

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 OAuth (one-time) + Wave 45 dev-hub Forgejo running.

English

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 entry via option-picker questions. Pure-click flow — no free-text decisions. Writes rule file, generates hook scaffold at user-chosen severity, registers hook in settings.json via update-config. See ~/.claude/rules/recurrence-escalate.md.

English

Use when implementation is complete and needs validation - tests REAL app features with Playwright, checks console errors, validates CRUD operations, generates persistent HTML reports to /test/…

English

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 / advisory-off / minimal / off), or full re-enable. Does NOT execute anything — user controls their shell.

English

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

English

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

English

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, and smooth scroll integration.

English

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

English

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 field plus three clicks, task lands in sync-repo/sleep-queue/ and is processed before REM consolidation. Up to 5 tasks per night, 15 minutes each. Pure-click wizard except the single task-description field.

English

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 generate an SSH deploy key, init the memory-repo, write env refs (RULE 0.8), and emit a /schedule create command. Local-only / hybrid emit a CronCreate snippet. Pure-click except 2 free-text fields (repo URL in Phase 2, Custom time in Phase 0b).

English

Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.

English

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

English

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 target, scaffolds configs + corpus + fixtures, wires CI jobs, and defines the crash/regression triage workflow. Pure-click: every decision except intake is an AskUserQuestion.

English

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. Stops if either verification primitive fails.

English

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 analysis, quality check, and constructor pattern into one unified workflow with evidence grading and Go/No-Go verdict.

English

기능 개발 라이프사이클 자동화. 사양서/마일스톤 생성 → 개발/테스트 사이클 관리 → 완료 리포트 및 아카이브.

Korean

Includes Architecture Rules, Batch Workflow, CI Scaffold, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills24CategorygeneralStars0

What’s included

Architecture Rules

Architectural rules engine — pattern validation, duplication detection, stack compatibility, and design pattern enforcement. Auto-triggers during code review, architecture planning, and when creating new modules. Triggers on "проверь архитектуру", "review architecture", "check patterns", "проверь дублирование", "stack compatibility".

Batch Workflow

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

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, OIDC-vs-token secrets posture, release automation, and a security gate — via pure-click decisions across five phases. Emits .github/workflows/.yml or .forgejo/workflows/.yml, a secrets-env scaffold (RULE 0.8), and runs kei-ci-lint before handing off. Never writes secret values.

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 the single intake field. Enriches blocks/ over time via Phase 6 block-augmentation — the kit gets smarter with every invocation.

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 budgets.

Design Inspiration

Curated collection of top-tier website designs organized by category, style, and pattern. Includes SaaS, marketing, e-commerce, and portfolio sites with analysis of what makes them effective. Use when looking for design inspiration or examples of specific patterns.

Dev Ship

Pre-merge/pre-deploy parallel gate — 4 backend agents (security, tests, deps, regression) plus optional 5th frontend-final-gate agent (production build, Lighthouse, axe full, visual diff full) run final checks BEFORE code reaches main. Last line of defense.

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 a click-driven file in this skill directory.

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 OAuth (one-time) + Wave 45 dev-hub Forgejo running.

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 entry via option-picker questions. Pure-click flow — no free-text decisions. Writes rule file, generates hook scaffold at user-chosen severity, registers hook in settings.json via update-config. See ~/.claude/rules/recurrence-escalate.md.

Feature Validation

Use when implementation is complete and needs validation - tests REAL app features with Playwright, checks console errors, validates CRUD operations, generates persistent HTML reports to /test/ directory

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 / advisory-off / minimal / off), or full re-enable. Does NOT execute anything — user controls their shell.

Pet Init

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

Quick API

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

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, and smooth scroll integration.

Session Budget

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

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 field plus three clicks, task lands in sync-repo/sleep-queue/ and is processed before REM consolidation. Up to 5 tasks per night, 15 minutes each. Pure-click wizard except the single task-description field.

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 generate an SSH deploy key, init the memory-repo, write env refs (RULE 0.8), and emit a /schedule create command. Local-only / hybrid emit a CronCreate snippet. Pure-click except 2 free-text fields (repo URL in Phase 2, Custom time in Phase 0b).

Spawn Agent

Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.

Test Gen

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

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 target, scaffolds configs + corpus + fixtures, wires CI jobs, and defines the crash/regression triage workflow. Pure-click: every decision except intake is an AskUserQuestion.

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. Stops if either verification primitive fails.

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 analysis, quality check, and constructor pattern into one unified workflow with evidence grading and Go/No-Go verdict.

Dev Start

기능 개발 라이프사이클 자동화. 사양서/마일스톤 생성 → 개발/테스트 사이클 관리 → 완료 리포트 및 아카이브.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Architecture Rules skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • Reported license for the skills shown: Apache-2.0. The author’s terms apply.
AI Agent & Automation Workflows | Agent Skills Atlas