agentleFS
gradigitgradigit/claude-skills/.claude/skills/updating-skills/SKILL.md

updating-skills

Skill0 starsChanged 9 months agoMITView on GitHub

Systematic workflow for modifying existing Agent Skills. Ensures spec compliance, version bumps, changelog updates, and audit pass after every change. Activates when user asks to "update skill", "modify skill", "evolve skill", "bump version", or mentions changing an existing skill. Do NOT use when creating, auditing, or testing skills.

  • Commits and pushes

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 17 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    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:

    When iterating on a skill across multiple conversations, the creating-skills spec and auditing-skills checklist can fall out of context.

    line 28
  2. Distinctive:

    Use TaskCreate to track progress:

    line 32
  3. Distinctive:

    Before any changes, read all skill files:

    line 49
  4. Distinctive:

    Never propose changes to files you haven't read.

    line 63
  5. Distinctive:

    When in doubt, use minor.

    line 75
  6. Distinctive:

    Run evaluations before changes (baseline) and after (regression check).

    line 88
  7. Distinctive:

    When updating, check all files for consistency:

    line 102
  8. Distinctive:

    Follow Keep a Changelog format:

    line 115
  9. Distinctive:

    Run the auditing-skills checklist.

    line 141
  10. Distinctive:

    Only for skills published to GitHub:

    line 193
  11. Very specific:

    Read all files: SKILL.md, CHANGELOG.md, EVALUATIONS.md, examples.md, heuristics.md, README.md, LICENSE

    line 212
  12. Distinctive:

    Run current evaluations (baseline — all pass)

    line 213
  13. Distinctive:

    Update EVALUATIONS.md (add Python triggering + functional scenario)

    line 217
  14. Distinctive:

    Update frontmatter version to "4.4.0"

    line 218
  15. Distinctive:

    Add CHANGELOG.md entry for 4.4.0

    line 219
  16. Distinctive:

    Update this skill when:

    line 237
  17. Distinctive:

    On missed consistency issue: Add to cross-file checklist

    line 238
  18. Distinctive:

    On new pitfall: Add to common pitfalls table

    line 239

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Updating Skills

Systematic workflow for modifying existing Agent Skills while maintaining spec compliance.

Why This Exists

When iterating on a skill across multiple conversations, the creating-skills spec and auditing-skills checklist can fall out of context. This skill ensures every update follows the same disciplined process.

Workflow

Use TaskCreate to track progress:

  • 1. Read current state (all skill files)
  • 2. Run current evaluations (baseline)
  • 3. Understand requested changes
  • 4. Classify version bump (major/minor/patch)
  • 5. Make changes following spec
  • 6. Update EVALUATIONS.md (if behavior changed)
  • 7. Bump version in frontmatter
  • 8. Update CHANGELOG.md
  • 9. Audit against checklist
  • 10. Fix any audit issues
  • 11. Present summary to user
  • 12. Push if published (user confirms)

Reading Current State

Before any changes, read all skill files:

skill-name/
├── SKILL.md        # Always read first
├── CHANGELOG.md    # Check current version
├── EVALUATIONS.md  # Check existing test scenarios
├── examples.md     # If exists
├── heuristics.md   # If exists
├── reference.md    # If exists
├── README.md       # If exists (published skills)
└── LICENSE          # If exists

Never propose changes to files you haven't read.

Classifying Version Bump

Follow semver:

Change TypeBumpExample
Breaking change (workflow restructure, removed feature)Major X.0.04.0.0 → 5.0.0
New feature, new section, new capabilityMinor x.Y.04.2.0 → 4.3.0
Bug fix, typo, version ref fix, wording tweakPatch x.y.Z4.3.0 → 4.3.1

When in doubt, use minor.

Evaluation-First Updates

Decide whether EVALUATIONS.md needs changes:

Change TypeUpdate EVALUATIONS.md?Example
New feature / capabilityYes — add scenarioAdded Python support → add Python triggering + functional test
Changed behaviorYes — update existing scenarioModified output format → update expected output
Bug fixMaybe — add edge case if gap exposedFix crash on empty input → add empty-input scenario
Wording / typo onlyNoFixed typo in description

Run evaluations before changes (baseline) and after (regression check). Use testing-skills for execution.

Making Changes

Follow creating-skills spec:

  • Third person in description — "Processes files" not "I process files"
  • Body under 500 lines — use progressive disclosure if larger
  • Concrete examples — real input/output, not abstract
  • One-level references — SKILL.md → ref.md, never ref.md → detail.md
  • No over-engineering — only change what was requested

Cross-File Consistency

When updating, check all files for consistency:

CheckWhere
Version stringFrontmatter, CHANGELOG.md, examples.md, README.md
Workflow step countSKILL.md workflow section, any "X steps" references
Feature referencesIf adding/removing a feature, update all mentions
Repo/URL referencesIf changing URLs, check every file

This is the most common source of audit failures.

Updating CHANGELOG.md

Follow Keep a Changelog format:

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

### Added
- New features

### Changed
- Modified behavior

### Fixed
- Bug fixes

### Removed
- Removed features

Rules:

  • Newest version at top
  • Date in ISO format
  • Group changes by type
  • Be specific — "Added deep dependency investigation" not "Updated skill"

Auditing

Run the auditing-skills checklist. Key checks:

Frontmatter

  • name: lowercase, hyphens, matches directory
  • description: third person, what + when, max 1024 chars
  • license: present
  • metadata.version: matches CHANGELOG.md latest entry

Content

  • Body under 500 lines
  • Workflow checklist present
  • Concrete example present
  • Self-evolution section present
  • References one level deep

Evaluations

  • EVALUATIONS.md present and up to date
  • New/changed behavior has matching scenario
  • should-NOT-trigger scenarios still valid

Cross-File (updating-specific)

  • Version consistent across all files
  • Step counts match across all references
  • No stale references to removed features
  • No hardcoded values that should be generic
  • CHANGELOG.md entry matches actual changes

Quality

  • No over-explaining
  • No Windows paths
  • No first/second person in description
  • Consistent terminology

Report format:

## Audit Result

**Grade**: A / B / C
**Version**: X.Y.Z

| Status | Count |
|--------|-------|
| Critical | 0 |
| Warnings | 0 |
| Suggestions | 0 |

{Details if any issues found}

Pushing (If Published)

Only for skills published to GitHub:

cd <skill-directory>
git add -A
git commit -m "v{X.Y.Z}: {one-line summary}"
git push

Local-only skills skip this step.

Example

Input:

Update the screening-github-cloud skill to add Python support

Process:

  1. Read all files: SKILL.md, CHANGELOG.md, EVALUATIONS.md, examples.md, heuristics.md, README.md, LICENSE
  2. Run current evaluations (baseline — all pass)
  3. Changes needed: Add Python screening patterns
  4. Version bump: minor (new capability) → 4.4.0
  5. Make changes in SKILL.md, heuristics.md, examples.md
  6. Update EVALUATIONS.md (add Python triggering + functional scenario)
  7. Update frontmatter version to "4.4.0"
  8. Add CHANGELOG.md entry for 4.4.0
  9. Audit all files for consistency
  10. Fix any stale version refs (examples.md commonly has old versions)
  11. Present diff summary
  12. Push to GitHub

Common Pitfalls

PitfallPrevention
Stale version in examples.mdSearch all files for old version string
Step count mismatchGrep for "X steps" across all files
Hardcoded values surviving a "make generic" changeSearch for the old hardcoded string
Forgetting CHANGELOG.mdAlways update before audit
Amending when should be new versionEach user-requested change set = new version

Self-Evolution

Update this skill when:

  1. On missed consistency issue: Add to cross-file checklist
  2. On new pitfall: Add to common pitfalls table
  3. On workflow improvement: Refine steps based on real usage

Current version: 2.0.0. See CHANGELOG.md for history.

References

  • Creating skills spec (v4.0.0): creating-skills
  • Auditing checklist (v2.0.0): auditing-skills
  • Testing evaluations: testing-skills

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.