agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.diff/SKILL.md

speckit.diff

Skill3 starsChanged 45 days agoMITView on GitHub

Artifact Comparator - Compare versions of specs, plans, tasks, or code and trace downstream impact.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Read two revisions/files plus their metadata, related spec/plan/tasks, and repository conventions.

    line 10
  2. Very specific:

    Write .agents/memory/diff-report.md with section-level changes, risk, affected links, and required follow-up.

    line 11
  3. Distinctive:

    Do not edit compared artifacts, hide removals, or infer semantic equivalence without evidence.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Mission

Explain what changed, why it matters, and which artifacts or gates must be revisited.

Inputs and Outputs

  • Read two revisions/files plus their metadata, related spec/plan/tasks, and repository conventions.
  • Write .agents/memory/diff-report.md with section-level changes, risk, affected links, and required follow-up.

Protocol

  1. Identify source revisions, comparison direction, author/date when available, and whether generated/vendor content is excluded.
  2. Compare structure and semantics: added, removed, changed, moved, renamed, and unchanged requirements; preserve exact references and line locations.
  3. Classify impact as None, Editorial, Behavioral, Contract, Data, Security, Operational, or Release; explain confidence and assumptions.
  4. Trace downstream effects: spec → plan → tasks → code → tests → docs/release. Flag stale links, missing migration/rollback/test work, and breaking changes.
  5. Produce a concise table and an ordered follow-up list. Remain read-only unless explicitly used as part of an approved artifact update workflow.

Completion Gate

The report is reproducible, both revisions are identified, every material change has an impact classification, and follow-up gaps are actionable.

Guard Rails

Do not edit compared artifacts, hide removals, or infer semantic equivalence without evidence.

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