skill-training skillA
skill-training is agent-read markdown (skill) from calebnewtonusc/chewbacca: Improve skills from real corrections and develop expertise in new domains. Use for repeated mistakes, learning how to learn, transferring procedures across tools, and verifying that learned behavior persists. Separate source reading from tested competence..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# skill-training For developing expertise in a new domain or improving the learning process itself, read [learning-transfer.md](references/learning-transfer.md). It separates source coverage, procedural change, held-out performance, cross-domain transfer and retention. A skill that is never updated from real runs decays: the world moves and the file does not. The correction the user just made is the training data, and it is gone the moment this session closes. ## When this fires The user edited the output before using it. Or rejected it. Or said "not like that." Or fixed the same thing twice. That is the signal, and it is easy to miss because the work still got done. ## The loop 1. **Name the delta.** What did the output say, what did the user change it to, and what is the difference in one sentence. Not the diff. The rule behind the diff. 2. **Ask which kind it is.** Three answers, and the user picks: - **Persist.** Always do it this way from now on. - **One-off.** This case was special, change nothing. - **Always ask.** Put a question in the skill at this point. Guessing here is how a skill acquires rules nobody wanted. …
Read the whole file at its exact version.
How to install
mdr add calebnewtonusc/chewbacca/skill-training@git:20260923.16d646cmdr add calebnewtonusc/chewbacca/skill-training@sha256:bfb22b8cc4b2d877Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_zjfr22jscymsktie)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.16d646c latest | 2026-09-23 | 16d646c | 4,078 B | A | view · diff |
| git:20260923.fcc7e97 | 2026-09-23 | fcc7e97 | 3,700 B | A | view · diff |
| git:20260921.3f3d9a0 | 2026-09-21 | 3f3d9a0 | 2,751 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 (4078 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
calebnewtonusc/chewbacca · 8 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zjfr22jscymsktie GET https://markdownregistry.com/api/v1/resolve?ref=calebnewtonusc/chewbacca/skill-training GET https://markdownregistry.com/api/v1/blob/bfb22b8cc4b2d877a9e610a7460e53b9636ee558db4314ecfff3bd065ec9ba73
Your agent 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.