agentleFS
Sign inStart free
ntaffziintaffzii/Skill-Agents/skills/deprecated/SKILL.md

deprecated

Skill4 starsChanged 2 months agoMITView on GitHub

Retire, preserve, explain, or replace old skills without silently deleting useful history. Use when the user asks to deprecate a skill, replace a skill, audit stale skills, or understand why a skill should no longer be used.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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:

    Use this skill when a skill is no longer recommended but should remain understandable.

    line 8
  2. Distinctive:

    Do not delete a retired skill until replacements and references are clear.

    line 24
  3. Distinctive:

    Do not leave active workflows pointing at deprecated skills.

    line 25
  4. Distinctive:

    Keep the deprecation reason short and factual.

    line 26
  5. Distinctive:

    If no replacement exists, state that clearly.

    line 33
  6. Very specific:

    Keep its SKILL.md readable.

    line 37
  7. Distinctive:

    Add a deprecation note near the top.

    line 38
  8. Distinctive:

    Remove it from README stable skill lists.

    line 41
  9. Distinctive:

    Remove it from workflow recommendations.

    line 42
  10. Very specific:

    Update data/workflows.json or data/tools.json if needed.

    line 43
  11. Distinctive:

    Run skill and workflow validation.

    line 51

≈ “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

Deprecated Skill Maintenance

Use this skill when a skill is no longer recommended but should remain understandable.

Purpose

skills/deprecated/ keeps retired skills visible until users and workflows have moved away from them. Deprecation should explain what replaced the skill and why.

When To Deprecate

  • Another skill fully replaces it.
  • The workflow is unsafe or misleading.
  • The scope became too broad or unclear.
  • The domain changed and the instructions are stale.
  • It was an experiment that should not be promoted.

Rules

  • Do not delete a retired skill until replacements and references are clear.
  • Do not leave active workflows pointing at deprecated skills.
  • Keep the deprecation reason short and factual.
  • Preserve useful reference material when it can be safely reused.

Workflow

  1. Identify replacement
    • Name the new skill or workflow if one exists.
    • If no replacement exists, state that clearly.
  2. Move carefully
    • Move the old skill folder into skills/deprecated/.
    • Keep its SKILL.md readable.
    • Add a deprecation note near the top.
  3. Update references
    • Remove it from README stable skill lists.
    • Remove it from workflow recommendations.
    • Update data/workflows.json or data/tools.json if needed.
  4. Explain the reason
    • State why the skill was retired.
    • State what to use instead.
    • Preserve any useful reference links.
  5. Validate
    • Run skill and workflow validation.
    • Confirm no active workflow depends on the deprecated skill.

Deprecation Note Template

## Deprecated

Status: Deprecated
Reason: ...
Use instead: `replacement-skill`
Date: YYYY-MM-DD

Output Format

End with:

  • Deprecated skill
  • Replacement
  • References updated
  • Validation result

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