agentleFS
Sign inStart free
Wsh7AshWsh7Ash/skillmcp/skills/reference-canonicalisation/SKILL.md

reference-canonicalisation

Skill0 starsChanged 14 days agoMITView on GitHub

Cite canonical https references so a link keeps working after the pack is published. Use when a skill cites a specification, vendor document or research post

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer the standards body or vendor's own documentation over a blog summary

    line 20
  2. Distinctive:

    Use https and the canonical host, never a mirror or a redirector

    line 21
  3. Distinctive:

    Check the link resolves before committing

    line 23
  4. Distinctive:

    Keep one to three references so the list stays meaningful

    line 25
  5. Distinctive:

    every reference is https and resolves

    line 29
  6. Distinctive:

    no reference points at a search result page

    line 31
  7. Distinctive:

    every reference is canonical, specific and resolving

    line 62

≈ “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

Reference Canonicalisation

Cite canonical https references so a link keeps working after the pack is published

Use when: a skill cites a specification, vendor document or research post

Avoid when: the skill is entirely self-contained and cites nothing external

Procedure

  1. Prefer the standards body or vendor's own documentation over a blog summary
  2. Use https and the canonical host, never a mirror or a redirector
  3. Cite the specific page, not the site root
  4. Check the link resolves before committing
  5. Replace a dead link with the archived canonical page
  6. Keep one to three references so the list stays meaningful

Signals

  • every reference is https and resolves
  • the cited page covers the claim in the skill
  • no reference points at a search result page
  • the reference list is short and specific

Patterns

1. Canonical

https://www.rfc-editor.org/rfc/rfc9112.html

2. Specific page

a named cheat sheet page, not the index

3. Archived fallback

web archive copy when the primary is gone

Pitfalls

  • Citing a blog that summarises the RFC instead of the RFC
  • Using http and relying on a redirect that later changes
  • Linking a site root so the reader cannot find the claim

Done when

  • every reference is canonical, specific and resolving
  • the validator enforces the https form

References

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