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

skill-create

Skill66 starsChanged 7 months agoApache-2.0View on GitHub

Create new project-local skills with proper directory structure and SKILL.md template. Generates a ready-to-use skill that Gemini CLI can activate immediately.

15 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

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Must be lowercase with hyphens only ([a-z0-9-]+)

    line 54
  2. Very specific:

    Must not conflict with existing skills in skills/ directory

    line 55
  3. Distinctive:

    Must be 2-30 characters long

    line 56
  4. Very specific:

    Write skills/{name}/SKILL.md with the following template:

    line 64
  5. Distinctive:

    After creating the template, ask the user:

    line 120
  6. Very specific:

    Use descriptive, action-oriented names: api-monitor, db-migrate, log-analyzer

    line 144
  7. Very specific:

    Avoid generic names: helper, util, misc

    line 145
  8. Distinctive:

    Use hyphens to separate words, not underscores or camelCase

    line 146
  9. Very specific:

    No duplicate names: - check skills/ directory first

    line 165

“Common” is measured: kept by at least 6 in 10 of the 14 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 Create

Generate new project-local skills with proper structure

Commands

CommandDescriptionExample
/skill-create [name]Create a new skill/skill-create api-monitor

How to Execute

1. Validate Name

  • Must be lowercase with hyphens only ([a-z0-9-]+)
  • Must not conflict with existing skills in skills/ directory
  • Must be 2-30 characters long

2. Create Directory

Create skills/{name}/ directory.

3. Generate SKILL.md

Write skills/{name}/SKILL.md with the following template:

---
name: {name}
classification: C
description: |
  {User-provided description or placeholder}

  Triggers: {name}, {related keywords}

user-invocable: true
argument-hint: "[args]"

allowed-tools:
  - read_file
  - write_file
  - glob
  - grep_search

imports: []
agents: {}
context: session
memory: project
pdca-phase: do
---

# {Name} Skill

> {One-line description}

## Commands

| Command | Description | Example |
|---------|-------------|---------|
| `/{name}` | {Main action} | `/{name} [args]` |

## How to Execute

1. {Step 1}
2. {Step 2}
3. {Step 3}

## Output Format

{Define expected output}

4. Verify Creation

  • Confirm the directory exists
  • Confirm SKILL.md has valid YAML frontmatter
  • Show the user the created file path

5. Interactive Refinement

After creating the template, ask the user:

  1. What should this skill do specifically?
  2. What MCP tools should it use?
  3. What triggers should activate it (in multiple languages)?

Then update the SKILL.md with their answers.

Skill Classification

CodeTypeDescription
WWorkflowMulti-step process (PDCA, deploy, QA)
CCommandSingle action (audit, status, create)
GGuideEducational/reference content

File Structure

skills/{name}/
  SKILL.md        # Required - skill definition and instructions

Naming Conventions

  • Use descriptive, action-oriented names: api-monitor, db-migrate, log-analyzer
  • Avoid generic names: helper, util, misc
  • Use hyphens to separate words, not underscores or camelCase

Output Format

## Skill Created: {name}

- **Path**: skills/{name}/SKILL.md
- **Classification**: C (Command)
- **Status**: Ready to use

Next steps:
1. Review and customize `skills/{name}/SKILL.md`
2. Add specific triggers for your use case
3. Test with `/{name}` command

Validation Rules

  1. No duplicate names - check skills/ directory first
  2. Valid characters - lowercase alphanumeric and hyphens only
  3. Valid YAML - frontmatter must parse correctly
  4. Required fields - name, classification, description, user-invocable

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.