AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
The English summary is being prepared. Showing the original description.
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.
The English summary is being prepared. Showing the original description.
Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
The English summary is being prepared. Showing the original description.
Process meeting recordings and transcripts into decisions, action items, and team dynamics
The English summary is being prepared. Showing the original description.
Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.
The English summary is being prepared. Showing the original description.
6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.
The English summary is being prepared. Showing the original description.
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
The English summary is being prepared. Showing the original description.
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
The English summary is being prepared. Showing the original description.
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
The English summary is being prepared. Showing the original description.
Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
The English summary is being prepared. Showing the original description.
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
The English summary is being prepared. Showing the original description.
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
The English summary is being prepared. Showing the original description.
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
The English summary is being prepared. Showing the original description.
Capture raw thoughts with automatic domain classification and vault routing
The English summary is being prepared. Showing the original description.
Personalize COG Second Brain workflow through role pack selection and vault initialization
The English summary is being prepared. Showing the original description.
Save URLs with auto-extracted insights, credibility scoring, and vault routing
The English summary is being prepared. Showing the original description.
Cross-domain pattern analysis with personal, professional, and project domain synthesis
The English summary is being prepared. Showing the original description.
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
The English summary is being prepared. Showing the original description.
Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
The English summary is being prepared. Showing the original description.
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
The English summary is being prepared. Showing the original description.
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
The English summary is being prepared. Showing the original description.
Use when adding a new agent harness (CLI-based coding agent) adapter to adapters. Covers capability audit, adapter scaffold, session parsing, auth detection, hooks/plugins wiring, tests, and docs.
The English summary is being prepared. Showing the original description.
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
The English summary is being prepared. Showing the original description.
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)