agentleFS
xialangji-debugxialangji-debug/codex-skills-agentmd-obsidian/skills/skill-usage-tracker/SKILL.md

skill-usage-tracker

Skill3 starsChanged 2 months agoMITView on GitHub

Audit local Skill registrations and routing, or report explicitly requested usage, trends, and feedback. Use for skill 整理, 触发不到, 索引同步, 失效/重复技能, frontmatter problems, or skill usage statistics. Registry maintenance does not require session-log scanning or telemetry setup.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run before changing registrations or routing:

    line 18
  2. Very specific:

    Keep active personal Skills flat under .codex/skills and inactive ones under .codex/skills.disabled.

    line 37
  3. Distinctive:

    After edits, run the registry audit again.

    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

Skill Usage Tracker

Choose One Operation

RequestOperation
Registration, routing, duplicates, disabled Skills, frontmatterRead-only registry audit below
Usage counts, trends, recent activity, or feedbackRead usage and telemetry
Enable local telemetry collectionRead the same reference and use only the requested setup

Registry Audit

Run before changing registrations or routing:

python "$env:USERPROFILE\.codex\skills\skill-usage-tracker\scripts\skill_usage_tracker.py" registry-audit --strict --json

This reads registrations and indexes without applying suggestions. Review missing/stale routes, duplicate or invalid directories, frontmatter errors, and active skills omitted from the index. Distinguish active personal, system, disabled, and plugin-cache entries. A cache match is only a candidate until the current available-skills list exposes its prefixed name.

The report separates registered personal/system Skills, disabled folders, plugin cache candidates, and session-visible names. Without --available-names-file, session exposure is unknown. The legacy active and plugins_or_available fields remain compatibility totals, not session-capability counts.

Optional inputs: --active-root, --disabled-root, --index, --available-names-file, --retired-skills, and --archive-index. By default, archive inventory is checked against retired-skills.yaml and skills-index/archive/index.md beside the active root when either exists. The Archived Entries table must match recoverable folders; historical removals belong in a separate section.

Keep active personal Skills flat under .codex/skills and inactive ones under .codex/skills.disabled. Update the owning routing indexes with any authorized rename/move. Do not delete or disable a Skill from low usage alone.

After edits, run the registry audit again. Report actual registration/route problems and changes; do not present plugin-cache totals as active capabilities.

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.