agentleFS
Sign inStart free
cerebrocybersolutionscerebrocybersolutions/libro/skills/skill-manage/SKILL.md

skill-manage

Skill1 starsChanged 39 days agoApache-2.0View on GitHub

6-action CLI tool for managing your skill library (create/edit/patch/delete/write-file/remove-file). Use when adding a new skill, patching an existing skill body, deleting a retired skill, or attaching reference/template/script/asset files to a skill folder. Enforces validation (lowercase-hyphen names, frontmatter contract, size caps, path-traversal protection).

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. thorwhalen/skill★ 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 repository12 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Default: {brain_root}/skills/ (auto-detected via __file__).

    line 60
  2. Very specific:

    Delete requires explicit intent — --absorbed-into <name> or --pruned.

    line 84

≈ “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

skill-manage

CLI utility for managing skills under your skills directory. Single tool, six actions, stdlib only.

When to use

  • Successful approach repeated 5+ times → save as skill
  • User-corrected workflow that worked → save as skill
  • Non-trivial procedural recipe discovered mid-session → save as skill
  • Stale instructions in existing skill → patch
  • Pattern absorbed from external source → create

Skip for one-off trivial tasks.

Actions

ActionUseRequired args
createNew skill--name --content-file [--category]
editFull SKILL.md rewrite--name --content-file
patchTargeted find-and-replace--name --old --new [--file-path] [--replace-all]
deleteRemove skill--name (--absorbed-into <umbrella> OR --pruned)
write-fileAdd reference / template / script / asset--name --file-path --file-content-file
remove-fileRemove supporting file--name --file-path

Usage

# Create
python3 {brain_root}/skills/skill-manage/scripts/skill_manage.py create \
  --name my-skill --content-file /tmp/skill-md-content.md [--category devops]

# Patch (fuzzy-free; unique match required unless --replace-all)
python3 {brain_root}/skills/skill-manage/scripts/skill_manage.py patch \
  --name my-skill --old "old text" --new "new text"

# Delete with intent declaration (mandatory)
python3 {brain_root}/skills/skill-manage/scripts/skill_manage.py delete \
  --name my-skill --absorbed-into umbrella-skill
# OR
python3 {brain_root}/skills/skill-manage/scripts/skill_manage.py delete \
  --name my-skill --pruned

Output: JSON dict to stdout; exit 0 success / exit 1 error.

Skills root

Default: {brain_root}/skills/ (auto-detected via __file__). Override: SKILLS_DIR=/path/to/skills env var.

Validation

  • Names: lowercase + hyphens/dots/underscores, ≤64 chars
  • Frontmatter: requires name: + description: (description ≤1024 chars)
  • SKILL.md size: ≤100K chars
  • Supporting file: ≤1 MiB
  • Path traversal blocked (.. rejected)
  • Supporting files must live under: references/, templates/, scripts/, Scripts/, assets/

Trigger doctrine (when an agent should call create/patch)

  1. Complex task (5+ tool calls) succeeded → offer create
  2. User-correction worked → patch existing skill with the correction
  3. Error overcome with non-obvious fix → patch skill that owned the workflow
  4. Multi-session pattern emerges → create
  5. External pattern absorbed → create (package the port as its own skill)

Skip when: simple one-offs; pure data manipulation; trivial commands.

Deletion intent declaration

Delete requires explicit intent — --absorbed-into <name> or --pruned. This forces the operator to declare why the skill went away, which is recoverable later from git history. Silent deletes are not supported.

Scope Contract (Least-Privilege)

DimensionScope
Read paths{skills_dir} (default {brain_root}/skills/) and any --content-file / --file-content-file paths
Write paths{skills_dir}/<skill-name>/** (SKILL.md + supporting files under whitelist)
MCP / tool surfaceNone — pure Python, stdlib only
Network egressNone
SurfaceAny (CLI invocation)
CredentialsNone
Escalation triggerValidation failure (exit 1) — operator must fix input and retry

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.

Check your setup, free