agentleFS
ww-w-aiww-w-ai/bkit-gemini/skills/skill-status/SKILL.md

skill-status

Skill66 starsChanged 7 months agoApache-2.0View on GitHub

Show loaded skills inventory with status, classification, and coverage information. Lists all skills from the skills/ directory with their activation state.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    If skill file exists, parse YAML frontmatter for metadata

    line 57
  2. Distinctive:

    Check for potential issues:

    line 137
  3. Very specific:

    Use /skill-status before /skill-create to check for conflicts

    line 144
  4. Very specific:

    Use --verbose to debug skill activation issues

    line 145

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 Status

Show all loaded skills with classification, status, and coverage analysis

Commands

CommandDescriptionExample
/skill-statusShow skill inventory summary/skill-status
/skill-status --verboseShow detailed per-skill info/skill-status --verbose

How to Execute

1. Scan Skills Directory

  1. List all directories under skills/
  2. For each directory, check if SKILL.md or skill.md exists
  3. If skill file exists, parse YAML frontmatter for metadata

2. Categorize Skills

Group skills by source:

  • bkit Core: Skills shipped with bkit extension
  • Project-Local: Skills added by the project team

Group skills by classification:

  • W (Workflow): Multi-step process skills
  • C (Command): Single-action skills
  • G (Guide): Educational/reference skills

3. Determine Status

For each skill:

  • Active: Has SKILL.md with valid frontmatter
  • Empty: Directory exists but no SKILL.md (stub)
  • Error: SKILL.md exists but has invalid frontmatter

4. Coverage Analysis

Calculate coverage metrics:

  • Total skill directories vs active skills
  • PDCA phase coverage (plan, design, do, check, act)
  • Agent integration coverage (which skills reference agents)

Output Format

Summary View (Default)

## bkit Skill Inventory

### Summary
- Total: 35 skills | Active: 33 | Empty: 0 | Error: 2

### By Classification
- Workflow (W): 12 skills
- Command (C): 18 skills
- Guide (G): 5 skills

### Skills

| # | Name | Class | Phase | Status |
|---|------|-------|-------|--------|
| 1 | pdca | W | all | Active |
| 2 | code-review | C | do | Active |
| 3 | deploy | W | do | Active |
| 4 | audit | C | check | Active |
| ... | | | | |

### PDCA Coverage
- Plan: 4 skills
- Design: 3 skills
- Do: 8 skills
- Check: 6 skills
- Act: 3 skills

Verbose View (--verbose)

Adds for each skill:

  • Description (first line)
  • Trigger keywords
  • Allowed tools list
  • Agent integrations
  • Import dependencies
### pdca (Workflow)
- **Phase**: all
- **Triggers**: pdca, plan, design, analyze...
- **Tools**: read_file, write_file, glob, grep_search, tracker_*
- **Agents**: gap-detector, pdca-iterator, report-generator
- **Imports**: 4 templates

Conflict Detection

Check for potential issues:

  1. Duplicate triggers: Two skills with the same trigger keyword
  2. Missing agents: Skill references an agent that does not exist
  3. Circular imports: Skill A imports B which imports A

Integration

  • Use /skill-status before /skill-create to check for conflicts
  • Use --verbose to debug skill activation issues
  • Results help identify coverage gaps in the PDCA workflow

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.