agentsclimarketplace

Memory diagnose

Skill ladyiceberg/openclaw-memory-quality/skills/memory-diagnose

openclaw-memhealth: Memory health monitor for OpenClaw — diagnose, guard, and remediate your agent's memory.

Install
npx -y skills add ladyiceberg/openclaw-memory-quality --skill memory-diagnose

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

1.6 KB, as published. Nobody here has run it

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.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.