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

memory-retrospective

Skill0 starsChanged 45 days agoMITView on GitHub

Review and curate global memory database at project completion

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Document results in project completion notes.

    line 33

≈ “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

Project Retrospective

  1. mcp__vector_memory_global__get_memory_stats() Note total count for limit parameter.
  2. mcp__vector_memory_global__list_recent_memories( limit=<total_from_stats>) NOTE: Set limit to total count from stats to get ALL memories.
  3. For each memory, identify project origin by inspecting content for tool/pattern names from the current project's domain. (Temporal proximity and domain overlap, not file paths.)

  4. For each memory from this project's timeframe: a. Still accurate? → Keep b. Needs refinement? → Store improved version (old ranks lower) c. Project-specific? → Store corrective superseding memory: content="SUPERSEDES: <summary>. REASON: project-specific." d. Related to another? → Store merged consolidated version

    NOTE: No delete_memory tool. "Removal" = superseding entry. clear_old_memories cannot wipe a DB: the server rejects days_old < 1 and max_to_keep < 100. For severe contamination, delete the DB file (<project_root>/memory/vector_memory.db) and re-store the valid memories from the review notes (see the vector-memory skill).

  5. Document results in project completion notes.

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