Audit CC project workspace against CAB v1.1.0 standards. Read-only 8-dimension scored assessment with YAML + markdown artifacts; Dimension 8 covers DP8 wrap-and-extend compliance. Triggers: audit workspace, check standards, cab audit, workspace health check, assess CC setup, dp8 compliance check.
Triage UX-log entries marked downstream_target=LL into formal lessons-learned.md entries with verifiable enforcement layer citations per LL-33 protocol. Operates on notes/ux-log-*.csv rows; outputs LL-NN entries + Priority Queue updates + bidirectional cross-references. Triggers: triage lessons, promote UX-log to LL, codify lesson, LL promotion, run lesson triage.
Enforce PLAN → REVIEW → EXECUTE → VERIFY → COMMIT protocol for non-trivial tasks. Prevents one-shotting, premature completion, and scope drift. Triggers: implement feature, fix bug, refactor, multi-step task.
Detect drift between CAB plugin extensions (source of truth) and deployed global ~/.claude/ extensions. Three failure modes detected: content drift, scope-shadowing across local→user→plugin layers (LL-27), AND type-shadowing at the same scope when commands and skills share names (LL-32). Triggers: sync check, plugin drift, shadow scan, type collision, deploy alignment, before pushing CAB changes, after global config edits.
Create or extend Claude Code project structures. Five modes via --mode flag: default (interactive new project), plugin (CAB plugin scaffold + git + optional GitHub remote), integrate (overlay CC architecture onto existing codebase), global (set up ~/.claude/ user config), quick (template-driven fast scaffold, no questionnaire). Triggers: new project, scaffold, init plugin, integrate existing, global config, quick template, start project.
Generate SOW, implementation plans, acceptance criteria, and phased backlogs. Decomposes requirements into actionable deliverables. Triggers: plan project, scope feature, write requirements, create SOW, define acceptance criteria.
Reconstruct session context after mid-dialogue death (compaction crash, force-close, dropped connection, hung process). Bootstraps from notes/ first, identifies the dying-session JSONL transcript, extracts last N turns, synthesizes coverage gap vs current state files, backfills discoveries into LL/state, and resumes at the exact HITL question. Triggers: session crashed, lost context, force-compact recovery, dying session, transcript recovery, recover from compaction.
Scan codebase for technical debt: code duplication, stale TODO/FIXME markers, dead code, consistency drift, and dependency health. Classifies findings as auto-fixable, manual-review, or tracked-known. Triggers: tech debt scan, end-of-session cleanup, code health check, periodic audit, before refactor.