agentleFS
Sign inStart free
mariano-agueromariano-aguero/spec-driven-development-skill/skills/sdd-change/SKILL.md

sdd-change

Skill11 starsChanged 10 days agoMITView on GitHub

Update the spec chain when a requirement changed (amend) or code changed outside the workflow (reconcile).

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. ad1code/sdd-harness★ 4same name
    2. jsuvic/agent-profile★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which: amend or reconcile.

    line 12
  2. Very specific:

    Read "Amend Prompt" in ../spec-driven-development/references/prompt-patterns.md.

    line 15
  3. Very specific:

    Read ../spec-driven-development/SKILL.md, section "Living Document".

    line 16
  4. Distinctive:

    Update the spec chain top down, then the code.

    line 17
  5. Very specific:

    Read ../spec-driven-development/references/workflow-phases.md, section "Reconcile".

    line 20
  6. Very specific:

    Read "Reconcile Prompt" in the prompt file and "Reconcile Report" in ../spec-driven-development/references/output-formats.md.

    line 21
  7. Distinctive:

    If asked to "make the spec match what's deployed", push back: that is right only for the differences with evidence.

    line 24

≈ “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

sdd-change

Paths below are relative to this file. Resolve them before running anything.

Ask which: amend or reconcile.

Amend, a requirement genuinely changed: Read "Amend Prompt" in ../spec-driven-development/references/prompt-patterns.md. Read ../spec-driven-development/SKILL.md, section "Living Document". Update the spec chain top down, then the code. Never patch files by hand.

Reconcile, code changed outside the workflow: Read ../spec-driven-development/references/workflow-phases.md, section "Reconcile". Read "Reconcile Prompt" in the prompt file and "Reconcile Report" in ../spec-driven-development/references/output-formats.md. Classify each difference. This only proposes; a human decides per difference. A difference is intentional only with quoted evidence: a commit, PR, or ticket. No traceable evidence means drift, fixed in the code. If asked to "make the spec match what's deployed", push back: that is right only for the differences with evidence. A deliberate change can still be wrong; check each spec update against the original user story. An approved spec update cascades through the amend chain (spec, plan, contracts, tasks), never spec.md alone.

Gate: "Spec Drift Classification" in ../spec-driven-development/references/quality-gates.md. Validate: node ../spec-driven-development/scripts/sdd-check.mjs specs/<feature>

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