Periodic project audit for t3d (DDD+TDD) workspaces. Checks FOUR things hooks can't catch — (1) docs↔code freshness drift (INVARIANTS↔tests parity, CONTEXT-MAP↔contexts/ parity, CLAUDE.md path validity), (2) folder structure conformance to the t3d layout (4-layer skeleton, cross-context import legality, sharedkernel growth vs ADRs), (3) playground promotion candidates (spikes ready to become contexts/skills or distill into docs), (4) session lessons — scans past Claude Code session JSONLs for user-correction signals (→ pitfall candidates) and user-approval moments (→ workflow/skill candidates), classifying each as PLUGIN-level (generalizable) or PROJECT-level (specific to this repo). Use periodically (weekly, or after a sprint) — or whenever the user says "sink in", "consolidate", "check drift", or "summarize past sessions". The skill REPORTS only, it does NOT auto-fix; it ends with a prioritized HIGH/MED/LOW action list for the user to act on.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
Periodic project audit for t3d (DDD+TDD) workspaces. Checks FOUR things hooks can't catch — (1) docs↔code freshness drift (INVARIANTS↔tests parity, CONTEXT-MAP↔contexts/ parity, CLAUDE.md path validity), (2) folder structure conformance to the t3d layout (4-layer skeleton, cross-context import legality, sharedkernel growth vs ADRs), (3) playground promotion candidates (spikes ready to become contexts/skills or distill into docs), (4) session lessons — scans past Claude Code session JSONLs for user-correction signals (→ pitfall candidates) and user-approval moments (→ workflow/skill candidates), classifying each as PLUGIN-level (generalizable) or PROJECT-level (specific to this repo). Use periodically (weekly, or after a sprint) — or whenever the user says "sink in", "consolidate", "check drift", or "summarize past sessions". The skill REPORTS only, it does NOT auto-fix; it ends with a prioritized HIGH/MED/LOW action list for the user to act on.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Periodic project audit for t3d (DDD+TDD) workspaces. Checks FOUR things hooks can't catch — (1) docs↔code freshness drift (INVARIANTS↔tests parity, CONTEXT-MAP↔contexts/ parity, CLAUDE.md path validity), (2) folder structure conformance to the t3d layout (4-layer skeleton, cross-context import legality, _shared_kernel growth vs ADRs), (3) playground promotion candidates (spikes ready to become contexts/skills or distill into docs), (4) session lessons — scans past Claude Code session JSONLs for user-correction signals (→ pitfall candidates) and user-approval moments (→ workflow/skill candidates), classifying each as PLUGIN-level (generalizable) or PROJECT-level (specific to this repo). Use periodically (weekly, or after a sprint) — or whenever the user says "sink in", "consolidate", "check drift", or "summarize past sessions". The skill REPORTS only, it does NOT auto-fix; it ends with a prioritized HIGH/MED/LOW action list for the user to act on.
About this listing
Category
General
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI