memory-seed SKILL.md skillA
memory-seed from baodq97/tencentdb-agent-memory is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add baodq97/tencentdb-agent-memory/memory-seed@git:20260731.937a638Pins git:20260731.937a638 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- baodq97/tencentdb-agent-memory
- Path
skills/memory-seed/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260731.937a638, committed Jul 31, 2026
- First version recorded
- May 26, 2026
- Size
- 2,718 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
Extract L1 memory atoms from Claude Code conversation history. Run manually via /memory-seed.
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
# Memory Seeding
Read conversation transcripts from `~/.claude/projects/` and extract structured L1 memory atoms. You perform all extraction — no external LLM needed.
## Workflow
### 1. Find pending sessions
```bash
tmem sessions
```
If no pending sessions, tell the user and stop.
### 2. For each pending session
Read the conversation:
```bash
tmem read-session SESSION_FILE_PATH
```
### 3. Extract memories
Read the extraction guide for detailed rules:
```bash
cat ${CLAUDE_PLUGIN_ROOT}/skills/memory-seed/references/extraction-guide.md
```
Analyze the conversation and produce a JSON array of memories. Each memory needs `content`, `type`, `priority`, `scene_name`, `source_message_ids`, `metadata`.
**Grounding (important):** populate `source_message_ids` with the actual transcript message `uuid`s the memory was drawn from. `tmem write-l1 --session` runs a deterministic grounding check — an atom whose `content` does not overlap its cited source messages is **dropped as confabulation**. Leaving `source_message_ids` empty skips the check (atom kept ungated), so cite real ids to get protection, and never invent facts absent from the source. Note: the check is lexical (shared…
…Read the whole file at its exact version.
How to install
mdr add baodq97/tencentdb-agent-memory/memory-seed@sha256:428d4e225d8c301fThe line at the top of this page pins the label git:20260731.937a638, 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_zbllwwm72uajcr4l)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between May 26, 2026 and Jul 31, 2026, about one every 33 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260731.937a638 latest | 2026-07-31 | 937a638 | 2,718 B | A | view · diff |
| git:20260629.bbe93f8 | 2026-06-29 | bbe93f8 | 3,058 B | A | view · diff |
| git:20260526.b264102 | 2026-05-26 | b264102 | 2,284 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 (2718 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
baodq97/tencentdb-agent-memory · 12 stars · license a license file GitHub does not identify · pushed 2026-09-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zbllwwm72uajcr4l GET https://markdownregistry.com/api/v1/resolve?ref=baodq97/tencentdb-agent-memory/memory-seed GET https://markdownregistry.com/api/v1/blob/428d4e225d8c301f419fdbdbe30cc9e9a9941243297de444d3c3880f28cf0997
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.