agentleFS
kimbjunnkimbjunn/session-pack/unpack/SKILL.md

unpack

Skill1 starsChanged 2 months agoMITView on GitHub

Manual-only entry point for the session-pack skill's unpacking workflow, triggered by the user typing `/unpack`. Not for model auto-invocation — use the session-pack skill for that.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. MichaelSou1/skills★ 1same name
    2. TaiMaBenJi/taima-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read <skill-dir>\SKILL.md in full (if not already in context) and follow its

    line 21
  2. Very specific:

    If the user supplied an argument with /unpack, treat it as the path to the .ccpack bundle.

    line 23
  3. Distinctive:

    Ask the user for a value for every unresolved slot (do not guess), then install:

    line 35
  4. Very specific:

    Only add --strip-unknown if inspect flagged unknown record types, and only add --force (and say so first) to overwrite existing project …

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/unpack

Thin entry point. All logic, the shared script, and the reference material live in the session-pack skill. Do not reimplement anything here.

Locate that skill's directory first — do not assume a fixed path, since session-pack may be installed as a standalone skill (~/.claude/skills/session-pack or <repo>/.claude/skills/session-pack) or as a plugin ($env:USERPROFILE\.claude\plugins\marketplaces\session-pack, with ${CLAUDE_PLUGIN_ROOT} pointing at it). Call this resolved directory <skill-dir> below.

Steps

  1. Read <skill-dir>\SKILL.md in full (if not already in context) and follow its "Unpacking (receiver)" section, steps 1-4, exactly.
  2. If the user supplied an argument with /unpack, treat it as the path to the .ccpack bundle. Otherwise ask for it.
  3. Dry-run first, never unpack blind:
    python <skill-dir>\scripts\ccpack.py inspect <bundle>.ccpack --cwd <target project root>
    Report the CLI version delta, unknown record types, slots needing --bind, the capability diff (MISSING/CHECK), and the file diff (to restore / differ locally / already missing). If inspect prints a lean mode : ABRIDGED line, say so: the transcript resumes normally, but file bodies and long tool results inside it read as [ccpack lean: N chars omitted]. If the user needs the full record, the sender has to re-pack without --lean — it cannot be restored on this side.
  4. Ask the user for a value for every unresolved slot (do not guess), then install:
    python <skill-dir>\scripts\ccpack.py unpack <bundle>.ccpack --cwd <target> [--bind SLOT=VALUE ...] [--strip-unknown] [--force]
    Only add --strip-unknown if inspect flagged unknown record types, and only add --force (and say so first) to overwrite existing project files.
  5. Hand off the resume command the script prints. Do not run claude --resume on the user's behalf — it is interactive and must run in their own terminal.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.