memesh-review SKILL.md skillA
memesh-review from pcircle-ai/memesh is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pcircle-ai/memesh/memesh-review@git:20261018.647f1ffPins git:20261018.647f1ff in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pcircle-ai/memesh
- Path
skills/memesh-review/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261018.647f1ff, committed Oct 18, 2026
- First version recorded
- Apr 19, 2026
- Size
- 3,678 bytes
- Repository stars
- 16
- License
- MIT
Review and optimize the MeMesh memory database. Analyzes health score, finds stale or noisy memories, shows work patterns, and suggests human-reviewed cleanup actions. Use when asked to "review memories", "check memory health", "clean up knowledge", or "what's in my memory".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MeMesh Memory Review
Review the memory database and provide actionable cleanup recommendations.
## How to Access
Use CLI (works everywhere) or MCP tools (if available). See the `memesh` skill for auto-detect instructions.
## Process
### Step 1: Gather data
```bash
# Get system health
memesh status
# Get all recent memories (structured output for analysis)
memesh recall --limit 50 --json
# `--tag` filters actual tags; inspect each returned entity's `type` to group decisions, lessons, and session records.
```
Recall is a bounded window, not a whole-database count. For an exact health
score and factor totals, use the local `GET /v1/analytics` API after
`memesh serve`. If it is unavailable, omit the
score and label any counts from recall as sample counts.
If MCP `user_patterns` tool is available, also run it for work pattern analysis:
```json
user_patterns: {}
```
### Step 2: Analyze and report
Use the analytics result for graph-wide totals and health factors; use recalled
memories to illustrate findings. Present only fields you actually obtained:
```markdown
## Memory Health Report
### Overview
- Total entities: N
- Last 30 days active: N (N%)
…Read the whole file at its exact version.
How to install
mdr add pcircle-ai/memesh/memesh-review@sha256:9aed2a0eb6cea491The line at the top of this page pins the label git:20261018.647f1ff, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_vbkxzel3l373tybs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Apr 19, 2026 and Oct 18, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.647f1ff latest | 2026-10-18 | 647f1ff | 3,678 B | A | view · diff |
| git:20261005.4a6ca92 | 2026-10-05 | 4a6ca92 | 3,715 B | A | view · diff |
| git:20260924.6aaf317 | 2026-09-24 | 6aaf317 | 3,659 B | A | view · diff |
| git:20260906.50bf239 | 2026-09-06 | 50bf239 | 3,878 B | A | view · diff |
| git:20260804.d53d970 | 2026-08-04 | d53d970 | 3,750 B | A | view · diff |
| git:20260803.c92e978 | 2026-08-03 | c92e978 | 3,746 B | A | view · diff |
| git:20260508.5210764 | 2026-05-08 | 5210764 | 3,588 B | A | view · diff |
| git:20260419.a891aa2 | 2026-04-19 | a891aa2 | 2,841 B | A | view · diff |
| git:20260419.c024a15 | 2026-04-19 | c024a15 | 2,645 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3678 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
pcircle-ai/memesh · 16 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vbkxzel3l373tybs GET https://markdownregistry.com/api/v1/resolve?ref=pcircle-ai/memesh/memesh-review GET https://markdownregistry.com/api/v1/blob/9aed2a0eb6cea4915e4fe89872043e731480c7508037c6f399d8b6a502478053
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.