agentleFS
Sign inStart free
YunghoYungho/family-doctor/developer-workflow/SKILL.md

developer-workflow

Skill2 starsChanged 8 months agoMITView on GitHub

Manage skill updates, patches, and versioning for the Family Doctor suite. Use when updating skills, creating new modules, managing changelog, or handling skill version changes. Triggers on \"update skill\", \"add new module\", \"version change\", \"changelog\".

2 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

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Follow semantic versioning: MAJOR.MINOR.PATCH

    line 21
  2. Very specific:

    Read current SKILL.md to understand the existing structure

    line 31
  3. Distinctive:

    Read CHANGELOG.md (if exists)

    line 32
  4. Very specific:

    Update version in SKILL.md frontmatter (version: X.Y.Z)

    line 37
  5. Distinctive:

    Add changelog entry to CHANGELOG.md

    line 38
  6. Distinctive:

    Document what changed and why

    line 39
  7. Distinctive:

    If a change causes problems:

    line 95
  8. Distinctive:

    Do NOT retry the same change without understanding the failure

    line 98
  9. Distinctive:

    Document the failure in CHANGELOG

    line 99
  10. Distinctive:

    No retry on failure: If patch fails, rollback and report

    line 103
  11. Distinctive:

    Audit trail: Every change logged with timestamp

    line 106

≈ “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

Developer Workflow

Manage patches, versioning, and changelog for the Family Doctor skill suite.

When to Use

  • Updating any skill file (SKILL.md)
  • Adding a new skill module
  • Managing version numbers
  • Writing changelog entries
  • Creating patch documentation

Version Numbering

Follow semantic versioning: MAJOR.MINOR.PATCH

  • MAJOR: Breaking changes to routing or output contracts
  • MINOR: New features, new skills, new capabilities
  • PATCH: Bug fixes, documentation updates

How to Execute

Before Any Change

  1. Read current SKILL.md to understand the existing structure
  2. Read CHANGELOG.md (if exists)
  3. Identify the version number to update

After a Change

  1. Update version in SKILL.md frontmatter (version: X.Y.Z)
  2. Add changelog entry to CHANGELOG.md
  3. Document what changed and why

Changelog Entry Format

## [X.Y.Z] - YYYY-MM-DD

### Added
- [Skill]: description of new feature

### Changed
- [Skill]: description of change

### Fixed
- [Skill]: description of fix

### Security
- [Skill]: security-related change

Skill File Structure

Each skill follows this pattern:

skill-name/
├── SKILL.md           # Required: name, description, allowed-tools, instructions
├── references/         # Optional: reference docs
├── scripts/            # Optional: executable scripts
└── evals/             # Optional: test cases

SKILL.md Frontmatter

---
name: skill-name
description: One-line description. Triggers on keywords.
allowed-tools: [tool1, tool2]
---

Testing Checklist

Before committing changes:

  • SKILL.md has valid YAML frontmatter
  • name field matches directory name
  • description includes trigger keywords
  • allowed-tools lists required tools
  • All skill references are correct
  • CHANGELOG updated
  • Version number bumped

Rollback

If a change causes problems:

  1. Revert SKILL.md to previous version
  2. Revert version number
  3. Do NOT retry the same change without understanding the failure
  4. Document the failure in CHANGELOG

Safety Rules

  • No retry on failure: If patch fails, rollback and report
  • Backup before change: Snapshot current state
  • Atomic operations: All-or-nothing patch application
  • Audit trail: Every change logged with timestamp

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