contrib-synthesize SKILL.md skillA
contrib-synthesize 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/contrib-synthesize@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/contrib-synthesize/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260731.937a638, committed Jul 31, 2026
- First version recorded
- Jun 18, 2026
- Size
- 3,581 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
Internal phase — synthesize learnable playbooks, cross-engineer common capabilities, and you-vs-role-model comparisons from built personas. Invoked by contrib-profile / `/contrib playbook|compare`.
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
# Contributor Synthesize
Turn multiple contributor personas into (a) the L4 capability model, (b) a
learnable playbook per subject, and (c) exemplar quotes. The deterministic
prevalence math is done by the CLI; you write the interpretation for learners.
**Read `references/synthesis-guide.md` first** — the altitude test for playbook
heuristics, how to mine exemplar quotes, the you-vs-role-model gap table, and the
"preliminary until ≥3 subjects" caveat for L4.
## Workflow
### 1. Compute the deterministic L4 backbone
```bash
tmem contrib capabilities
```
Prints each common capability with prevalence % and exemplar. If it says
"need >=2 subjects", tell the user to ingest + build at least one more subject
and stop.
### 2. Capability model (narrative)
Pull every persona in one call to reason across them:
```bash
tmem contrib personas # all subject personas as JSON
```
For each common capability (from step 1), write 1–2 sentences: what the shared
behaviour is, the prevalence ("N/M subjects"), and who exemplifies it best (the
exemplar subject), citing one piece of their evidence.
### 3. Learnable playbook (per subject)
Read the subject persona:
```bash
…Read the whole file at its exact version.
How to install
mdr add baodq97/tencentdb-agent-memory/contrib-synthesize@sha256:9b26dcfb7e164207The 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_k5xgxqd3f73xumg4)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 18, 2026 and Jul 31, 2026, about one every 43 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260731.937a638 latest | 2026-07-31 | 937a638 | 3,581 B | A | view · diff |
| git:20260618.d13af19 | 2026-06-18 | d13af19 | 4,341 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 (3581 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_k5xgxqd3f73xumg4 GET https://markdownregistry.com/api/v1/resolve?ref=baodq97/tencentdb-agent-memory/contrib-synthesize GET https://markdownregistry.com/api/v1/blob/9b26dcfb7e1642074c695770b4a2463c854a8d634a0ac683b4be4d2f45d4e614
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.