agentleFS
Sign inStart free
Thomaszhou22Thomaszhou22/memory-checkup/SKILL.md

memory-checkup

Skill2 starsChanged 2 months agoMITView on GitHub

Audit and repair an AI agent's memory corpus for consistency. Use when memory contains stale numbers or superseded facts, when different memory files contradict each other (e.g. old download/star counts), when a metric changed and documents must be synced, when daily memory flushes have gaps or stopped, when memory references files that no longer exist, when the user says "check my memory", "memory audit", "体检记忆", or when answering from memory feels risky because facts may have drifted.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. marcogalluccio/company-brain-os★ 7same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Before answering questions that depend on facts recorded over many days (awards, counts, project statuses).

    line 13
  2. Distinctive:

    After a metric changes and the user asks to sync all documents (e.g.

    line 14
  3. Distinctive:

    Update stale mentions, or annotate them as superseded if history should be preserved ("旧口径 4,600+ 已作废").

    line 44
  4. Distinctive:

    Remove or repair dangling references.

    line 45
  5. Distinctive:

    Do NOT delete orphan daily files.

    line 46
  6. Distinctive:

    After edits, re-run the audit to confirm zero issues.

    line 47

≈ “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 Checkup

Audit an agent's memory corpus (MEMORY.md, USER.md, and files under memory/) and surface consistency problems before they reach the user: stale superseded numbers, contradictions, dangling file references, abandoned daily entries, and orphan files.

When to run

  1. The user asks to check/audit/clean memory ("体检", "check my memory").
  2. Before answering questions that depend on facts recorded over many days (awards, counts, project statuses).
  3. After a metric changes and the user asks to sync all documents (e.g. download counts in application essays).
  4. Periodically, alongside daily memory flushes.

Procedure

Step 1: Locate the corpus

The corpus root is the agent workspace: it must contain MEMORY.md and/or a memory/ directory. Ask or infer from context; in OpenClaw this is the workspace directory.

Step 2: Run the audit script

python3 scripts/memory_checkup.py --memory-dir <workspace-root> [--json]

The script scans and reports:

CheckMeaning
Stale numbersSame metric (downloads/stars/users) with an old value in some files and a newer value in newer files
Dangling referencesFile paths mentioned in memory that no longer exist
Stale entriesDaily-flush files whose date has a gap to the newest entry
Orphansmemory/ files never referenced from anywhere else

Step 3: Verify before editing

For every stale-number finding, confirm the current value with the user or with live evidence (run the real check: hit the API, count the files). Never assume the newest mention is correct just because it is newest.

Step 4: Fix

  • Update stale mentions, or annotate them as superseded if history should be preserved ("旧口径 4,600+ 已作废").
  • Remove or repair dangling references.
  • Do NOT delete orphan daily files; list them to the user and let them decide.
  • After edits, re-run the audit to confirm zero issues.

Step 5: Report

Summarize in the user's language: how many files scanned, issues by type, what was fixed, what needs a user decision.

Notes

  • The script is read-only. All fixes are made by the agent, file by file, after verification.
  • Number extraction currently covers downloads/stars/users patterns (English and Chinese); extend DEFAULT_PATTERNS for other metrics.
  • JSON output is machine-readable for piping into other tools.

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