institutional-memory-distill
SolidDistill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decision_ledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide revise/proceed/escalate -- that's ult-context-generate/SKILL.md Step 7.7's job.
Install
Quality Score: 82/100
Skill Content
Details
- Author
- linkpranay-ai
- Repository
- linkpranay-ai/context-engineering-protocol
- Created
- 2 months ago
- Last Updated
- today
- Language
- Python
- License
- Apache-2.0
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
distill-memory
Scan a project's `.claude/decisions/**/*.md` and the last month of `MODULE:`-tagged commits, then propose 0–3 candidate Claude Code memory entries for the user to review one-by-one — the Layer 2 → Layer 3 step in the knowledge loop. Use this skill whenever the user says "/distill-memory", "distill memory", "roll up decisions into memory", or asks to extract cross-module patterns into memory. This skill should NOT auto-trigger — only invoke it when the user explicitly requests it.
distill-skill
Use when the user wants to crystallize project memory into auto-loading repo skills, run a learn-on-the-job distill pass, turn repeated session patterns into SKILL.md files, or pair with skill-audit to keep those skills from rotting.
memory-distill
Post-mortem-style review of recent feedback memories. Pick 3-5, walk through them one at a time asking "did I get this right? what's the next layer?", then surface latent principles that several memories point at but none articulate. Use when memories feel stale, when the same correction keeps recurring, or periodically to consolidate. Works from concrete recent evidence — not vibes. Invoke as "/memory-distill".