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

sdd-validate

Skill11 starsChanged 9 days agoMITView on GitHub

Check code against the spec chain, generate checklists, or analyze a spec for contradictions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ad1code/sdd-harness★ 4same 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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which: validate the implementation, generate a checklist, or analyze the spec.

    line 12
  2. Very specific:

    Read ../spec-driven-development/references/workflow-phases.md, section "Phase 5".

    line 15
  3. Very specific:

    Use "Drift Detection Prompt", "Post-Implementation Validation Prompt" and "Linear Walkthrough Prompt" in …

    line 16
  4. Very specific:

    Run node ../spec-driven-development/scripts/sdd-check.mjs specs/<feature> first.

    line 26

≈ “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-validate

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

Ask which: validate the implementation, generate a checklist, or analyze the spec.

Validate: Read ../spec-driven-development/references/workflow-phases.md, section "Phase 5". Use "Drift Detection Prompt", "Post-Implementation Validation Prompt" and "Linear Walkthrough Prompt" in ../spec-driven-development/references/prompt-patterns.md. Gate: "Gate 5" and "Gate C" in ../spec-driven-development/references/quality-gates.md. Produce: validation.md, a drift report, walkthrough.md, formats in ../spec-driven-development/references/output-formats.md. Adversary (levels M and L): use "Adversary Prompt". Run it in an agent that did not write the code, in its own worktree or scratch copy, on a different model family when available. It tries to break each [MUST] and [UNCHANGED] AC against the real code. Findings from the authoring session do not count as this check. A plausible bypass found by reading is worth reproducing: state the command and the output that would confirm it. A finding is confirmed only with a command, its output, and the output the spec requires. Everything else goes to a Dropped list with a reason each; naming and style findings are dropped as out of scope. Gate 5 stays fail or inconclusive until every finding is rerun or dropped.

Checklist: read "Generated Checklists" in ../spec-driven-development/references/quality-gates.md and "Checklist Generation Prompt" in the prompt file. Analyze: read "Analyze Prompt" in the prompt file and "Analyze Report" in ../spec-driven-development/references/output-formats.md.

Run node ../spec-driven-development/scripts/sdd-check.mjs specs/<feature> first. Fix its findings before judging anything it cannot check.

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