agentleFS
Sign inStart free
ladyicebergladyiceberg/openclaw-memory-quality/skills/memory-diagnose/SKILL.md

memory-diagnose

Skill1 starsChanged 7 months agoMITView on GitHub

Deep diagnosis of OpenClaw retrieval quality — identifies false positives, zombie entries, and gives configuration recommendations to fix weak embedding or FTS-only retrieval. Use this skill whenever the user asks about retrieval quality, wonders why memory seems off, wants to understand false positives or zombie entries, asks about embedding or memory configuration, or uses phrases like "memory diagnosis", "bad memories", "why is memory bad", "memory config", "记忆诊断", "检索质量", "假阳性", "记忆配置". Prefer this skill over generic troubleshooting when OpenClaw memory quality is the topic.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Run both retrieval diagnosis and config check, then give a combined verdict.

    line 8
  2. Very specific:

    Call memory_retrieval_diagnose_oc (pass top_n if user specified, default 20)

    line 12
  3. Distinctive:

    Start with a one-sentence diagnosis, then present findings:

    line 18
  4. Distinctive:

    No API key required. Read-only — never modifies any files.

    line 32

≈ “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

Memory Diagnose

Run both retrieval diagnosis and config check, then give a combined verdict.

Steps

  1. Call memory_retrieval_diagnose_oc (pass top_n if user specified, default 20)
  2. Call memory_config_doctor_oc
  3. Combine both reports into a single diagnostic verdict

Output structure

Start with a one-sentence diagnosis, then present findings:

Retrieval quality is degraded. ~18% of entries are high-frequency low-quality false positives, likely FTS literal matches. Recommend: clean up low-quality entries first, then check embedding config.

Then show the two raw reports.

Suggesting next steps

  • High false-positive rate → suggest /memory-cleanup
  • Config problems found (minScore too low, no embedding provider) → highlight the specific config recommendations from the report
  • Ambiguous entries in the "fuzzy zone" → mention that memory_longterm_audit_oc(use_llm=True) can do semantic review

Notes

No API key required. Read-only — never modifies any files.

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