agentleFS
Sign inStart free
Yash-SukhdeveYash-Sukhdeve/universal-workflow-system/.claude/skills/phase-distillation/SKILL.md

phase-distillation

Skill0 starsChanged 45 days agoMITView on GitHub

Distill local memories into global lessons at phase completion

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add to .workflow/handoff.md: "Phase $ARGUMENTS distillation: promoted M lessons to global knowledge"

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Phase-End Knowledge Distillation

Distill memories from Phase $ARGUMENTS:

  1. mcp__vector_memory_local__search_memories( query="PHASE $ARGUMENTS", limit=50) NOTE: Using search (not list_recent) to target phase via content prefix.
  2. Group results by category.
  3. For groups with 2+ entries sharing a root cause: Consolidate into ONE general lesson. Apply generalizability gate (3-question evaluation).
  4. CALIBRATION CHECK: Review last 10 global promotions. "Which of these are actually project-specific? Be adversarial." For false promotions: store corrective memory with same category: content="SUPERSEDES: <original content summary>. REASON: project-specific." NOTE: Server has no delete_memory tool. Superseding entries rank higher for targeted queries, displacing false ones.
  5. Store passing patterns to global DB.
  6. Add to .workflow/handoff.md: "Phase $ARGUMENTS distillation: promoted M lessons to global knowledge"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free