AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
中文简介正在准备中。当前显示原文说明。
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
中文简介正在准备中。当前显示原文说明。
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.
中文简介正在准备中。当前显示原文说明。
Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
中文简介正在准备中。当前显示原文说明。
Process meeting recordings and transcripts into decisions, action items, and team dynamics
中文简介正在准备中。当前显示原文说明。
Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.
中文简介正在准备中。当前显示原文说明。
6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.
中文简介正在准备中。当前显示原文说明。
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
中文简介正在准备中。当前显示原文说明。
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
中文简介正在准备中。当前显示原文说明。
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
中文简介正在准备中。当前显示原文说明。
Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
中文简介正在准备中。当前显示原文说明。
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
中文简介正在准备中。当前显示原文说明。
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
中文简介正在准备中。当前显示原文说明。
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
中文简介正在准备中。当前显示原文说明。
Capture raw thoughts with automatic domain classification and vault routing
中文简介正在准备中。当前显示原文说明。
Personalize COG Second Brain workflow through role pack selection and vault initialization
中文简介正在准备中。当前显示原文说明。
Save URLs with auto-extracted insights, credibility scoring, and vault routing
中文简介正在准备中。当前显示原文说明。
Cross-domain pattern analysis with personal, professional, and project domain synthesis
中文简介正在准备中。当前显示原文说明。
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
中文简介正在准备中。当前显示原文说明。
Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
中文简介正在准备中。当前显示原文说明。
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
中文简介正在准备中。当前显示原文说明。
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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)
中文简介正在准备中。当前显示原文说明。
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
中文简介正在准备中。当前显示原文说明。