ccancellieri

@ccancellieri source repo

4 skills
0 followers
10 hours ago last updated

▌
Ensemble Review · ccancellieri
Use when the user asks for a "comprehensive code review", "multi-model review", "ensemble review", "deep review", or "parallel model review". Dispatches three specialized Claude model tiers (Opus, Sonnet, Haiku) to review code in parallel, each focusing on different aspects. Aggregates findings into a unified severity-ranked report. Invoke when reviewing critical code paths, production deployments, architectural changes, or when the user wants thorough analysis beyond single-model review.

0 installs
▌
Memory Layer Analysis · ccancellieri
Use when reviewing auto-memory or project memory files to decide what to keep, archive, or consolidate. Categorization methodology behind master-state-compaction. Apply when the user asks to "audit memory", "find stale memory entries", "what should I archive", or before any large memory rewrite. Forces explicit per-entry classification (ACTIVE / SUPERSEDED / ARCHIVE / CONSOLIDATE) with stated reason rather than vibes-based pruning.

0 installs
▌
Master State Compaction · ccancellieri
Use when the user asks to "compact memory", "create a master state snapshot", "summarize the project state", "restructure memory", or invokes /hub-compact-master-state, /role-senior-project-architect, or similar. Generates a 4-section snapshot (Architecture / Invariants / Active Working Set / Recent Pivots) for a multi-repo project from auto-memory deltas. Always uses the best configured model (tier_smart) and surfaces inferred assumptions for verification rather than presenting them as facts.

0 installs
▌
Wiki Skill Factory · ccancellieri
Meta-skill for generating project-specialized skills from the memory of work done. Use when you need to understand how memory-to-skill generation works or want to manually trigger it.

0 installs

4 published skills