extract-skill-section skillA
extract-skill-section is agent-read markdown (skill) from hiroro-work/claude-plugins: Extract a named SKILL.md section's body verbatim into a references/<name>.md file, replace the body with a skeleton (section label + delegation pointer, runtime definitions left in place), sync the bundle copy, and verify byte-identity plus cross-reference integrity via the repository's reference test and verify-bundle-sync. One-command automation of the manual section-extraction procedure used to shrink oversized SKILL.md files. Non-interactive — no user prompts. Project-local routine — not for.
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
# Extract Skill Section Extracts one contiguous section body out of an oversized SKILL.md into a `references/<name>.md` file, compresses the section in place to a skeleton (the original section label + a one-line delegation pointer), syncs the bundle copy when the target is a bundle member, and verifies the move mechanically. Two invariants the skill enforces, and one it deliberately does not: - **Verbatim move**: the extracted body lands in the reference file byte-identical (verified by `diff`, no normalization). Heading-level changes or other semantic edits are out of scope — apply them as ordinary edits after this skill returns. - **No definition duplication**: inline retention is achieved by **not extracting** the runtime-referenced definitions in the first place (the `Inline-keep:` pre-flight check), never by re-inserting a copy. - **Boundary correctness is not guaranteed**: the byte-identity check proves the moved content is verbatim, not that the range selection was right. The Pre-flight boundary confirmation is the only guard — review it carefully. …
Read the whole file at its exact version.
How to install
mdr add hiroro-work/claude-plugins/extract-skill-section@git:20260902.b999a01mdr add hiroro-work/claude-plugins/extract-skill-section@sha256:0be29a454259f124Pin 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_xmwqijulepxwqswr)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260902.b999a01 latest | 2026-09-02 | b999a01 | 16,136 B | A | view · diff |
| git:20260818.948b574 | 2026-08-18 | 948b574 | 15,374 B | A | view · diff |
| git:20260719.418337f | 2026-07-19 | 418337f | 17,189 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 (16136 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
hiroro-work/claude-plugins · 48 stars · license none · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xmwqijulepxwqswr GET https://markdownregistry.com/api/v1/resolve?ref=hiroro-work/claude-plugins/extract-skill-section GET https://markdownregistry.com/api/v1/blob/0be29a454259f124f287611aae0af7813cdc11d0a1ad0f296d21e839f807fea5
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.