agentleFS
vosslabvosslab/vosslab-skills/skills/documentation/see-also-docs/SKILL.md

see-also-docs

Skill5 starsChanged 21 days agoMITView on GitHub

Create or refresh `docs/RELATED_PROJECTS.md` as a visitor guide to comparable projects and resources, alternatives, prior art, lineage, and closely related companion work.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Create or refresh docs/RELATED_PROJECTS.md as a sourced visitor-discovery guide.

    line 10
  2. Very specific:

    Read references/evidence_and_selection.md before web discovery.

    line 15
  3. Distinctive:

    Use implementation manifests to understand the repository's subject and vocabulary.

    line 19
  4. Very specific:

    Read the repository README, agent guidance, relevant docs, manifests, and existing docs/RELATED_PROJECTS.md.

    line 24
  5. Distinctive:

    Write one sentence describing what visitors use this repository to accomplish.

    line 27
  6. Very specific:

    Run the seed and widening discovery rounds from evidence_and_selection.md using the available search and fetch tools.

    line 28
  7. Very specific:

    Write the owned file only when at least one candidate passes.

    line 33
  8. Distinctive:

    Update the target repository changelog when its rules require that documentation handoff.

    line 37

≈ “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

See also docs

Purpose

Create or refresh docs/RELATED_PROJECTS.md as a sourced visitor-discovery guide. Include only destinations that share a concrete audience, problem, or workflow with the target repository.

Evidence boundary

Read references/evidence_and_selection.md before web discovery. It owns the visitor relevance sentence, inclusion checklist, relationship taxonomy, confidence tiers, and bounded two-round search method.

Use implementation manifests to understand the repository's subject and vocabulary. Establish visitor value separately; a shared implementation language or dependency is not enough.

Workflow

  1. Read the repository README, agent guidance, relevant docs, manifests, and existing docs/RELATED_PROJECTS.md. Identify the primary audience, user goal, formats, standards, comparisons, lineage, companion work, and outbound project links.
  2. Write one sentence describing what visitors use this repository to accomplish.
  3. Run the seed and widening discovery rounds from evidence_and_selection.md using the available search and fetch tools.
  4. For every candidate, capture the official link, visitor-value sentence, relationship type, confidence tier, and strongest authoritative evidence.
  5. Apply the full inclusion checklist. Keep partial research and untraced leads in the run report.
  6. Write the owned file only when at least one candidate passes. Follow references/related_projects_template.md.
  7. Refresh existing entries that remain accurate and remove claims no longer supported by current evidence.
  8. Update the target repository changelog when its rules require that documentation handoff.

Publication threshold

One Confirmed, Likely, or Possible entry qualifies when it has a real link, a specific visitor-value line, authoritative relationship evidence, and every required checklist result. When no candidate passes, preserve the documentation tree and report searches, gaps, and untraced leads outside the published file.

Output contract

Group explicit comparison or lineage evidence under Confirmed related projects. Group useful same-audience or adjacent-workflow candidates under Possible related projects, stating confidence when needed. For each entry include:

  • relationship type;
  • official link;
  • why visitors may care;
  • evidence supporting the relationship;
  • confidence when it is not confirmed.

Close with concise evidence notes describing the authority basis. Follow the target repository's Markdown and ASCII rules. Limit authored product documentation to docs/RELATED_PROJECTS.md plus the required changelog record.

Completion

Return the published path and passing entries with their evidence, or a zero-result receipt naming the searches performed and why candidates failed. Report remaining leads separately so the public file contains only useful, supported destinations.

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.