Full SRS workflow: Brainstorm → Spec → Plan (per-section files) → User Review → SRS Generation → Validation → Improvement Report → Context Save. Use when user provides a project topic and wants a complete requirements pipeline.
The English summary is being prepared. Showing the original description.
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
The English summary is being prepared. Showing the original description.
BA (Business Analyst) agent. Analyzes requirements and produces 4 artifact files: requirements.md, user-stories.md, acceptance-criteria.md, business-rules.md. Use --srs to load from SRS workflow artifacts (spec.md / brainstorm.md). Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
BE Dev (Backend Developer) agent. Reads BA + TechLead + PM artifacts and generates backend source code files, .env.example, and pr-description.md. No hardcoded credentials. Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
Utility skill. Lists all projects under the projects/ directory and shows which Virtual Team pipeline phases have been completed for each project.
The English summary is being prepared. Showing the original description.
PM (Project Manager / Scrum Master) agent. Reads BA and TechLead artifacts and produces sprint plan, task breakdown, and story point estimates. Creates one TodoWrite entry per sprint task for live pipeline tracking (FR-42). Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
Tester agent. Reads ALL preceding artifacts (BA + TechLead + PM + BE + FE) and produces test plan, test cases (unit/integration/e2e), and bug report template. Declares Gate 2: UAT Readiness. Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
Full-pipeline orchestrator. Runs all 7 agents (BA → TechLead → PM → BE Dev → FE Dev → Tester → QA/QC) in sequence by invoking each per-agent skill via the Skill tool. All writes go through the pre_write_validator.py hook for hard enforcement. Use per-agent commands (/team-ba, /team-techlead, etc.) for manual control.
The English summary is being prepared. Showing the original description.
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"
The English summary is being prepared. Showing the original description.
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
The English summary is being prepared. Showing the original description.
Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z"
The English summary is being prepared. Showing the original description.
Dispatch to the right problem-solving technique based on how you're stuck
The English summary is being prepared. Showing the original description.
Generate ready-to-paste AI image-gen prompts for 2D game art (character/sprite, icon/UI/item, background/tileset) that stay consistent with the project's art style across separate chat sessions in Claude/Gemini/ChatGPT chat UIs. Use when the user wants to render, generate, or create game art/sprites/icons/backgrounds with AI, or mentions an "art style bible" for a game project. Maintains a persistent `art-style-bible.md` so style doesn't drift between requests, and gives a post-generation checklist plus post-processing guidance for common technical misses (transparency, size, aspect ratio).
The English summary is being prepared. Showing the original description.
BA (Business Analyst) agent. Analyzes requirements and produces 4 artifact files: requirements.md, user-stories.md, acceptance-criteria.md, business-rules.md. Use --spec <path> to load requirements from any markdown file. Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
Phase 1 of the SRS workflow. User gives a project topic → AI runs a deep, categorized brainstorm (5 mandatory rounds) to fully understand actors, features, scope boundary, tech constraints, and business rules before writing anything.
The English summary is being prepared. Showing the original description.
Phase 6 of the SRS workflow. Reads approved plan files and generates a complete IEEE 830-compliant SRS — one file per section, no word limit. A full SRS may span 300+ pages across all files.
The English summary is being prepared. Showing the original description.
Phase 8 of the SRS workflow. Generates an improvement report covering deferred features, technical risks, validation warnings, and next-version candidates. No word limit.
The English summary is being prepared. Showing the original description.
Phase 4 of the SRS workflow. Reads spec.md and writes one detailed plan file per SRS section (§1–§3 + Appendices). Each file is a complete blueprint for the corresponding SRS section. No word limit.
The English summary is being prepared. Showing the original description.
Phase 2 of the SRS workflow. Reads projects/{slug}/brainstorm.md and writes a comprehensive spec.md. No word limit.
The English summary is being prepared. Showing the original description.
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
The English summary is being prepared. Showing the original description.
Phase 9 of the SRS workflow. Saves all project context to _context/ files so future Claude sessions can resume without re-reading the full SRS.
The English summary is being prepared. Showing the original description.
Always use this skill before claiming any work is done, fixed, passing, or complete — even if it seems obvious. Also use when receiving code review feedback from any source (human or automated), when finishing a task or major feature, before committing or creating a PR, or when about to express satisfaction with work. Covers three practices: receiving feedback with technical rigor (no performative agreement), triggering code review via /code-review command or cook/fix pipelines, and verification gates (run the command, read the output, then make the claim). Never skip — the cost of false completion claims is higher than the cost of verifying. References: code-review-reception.md, requesting-code-review.md, verification-before-completion.md.
The English summary is being prepared. Showing the original description.
TechLead (Senior Technical Lead) agent. Reads all BA artifacts and produces system architecture, technology stack, ERD, sequence diagrams, and ADRs. Declares Gate 1: Design Freeze. Part of the Virtual Team Skill pipeline.
The English summary is being prepared. Showing the original description.
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)