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

sdd-specify

Skill11 starsChanged 9 days agoMITView on GitHub

Write or refine spec.md, covering assumptions, acceptance criteria, clarify, and the cold read.

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. monaccode/astromesh-sdd★ 0same name
    2. pchemguy/Skill-SDD-Manager★ 0same 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, 1 is distinctive, and 6 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.

  • 6

    Very specific

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

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

    Read ../spec-driven-development/SKILL.md, section "Phase 1".

    line 12
  2. Very specific:

    Read ../spec-driven-development/references/workflow-phases.md, section "Phase 1" and, for a change to existing behavior, "Delta Specs".

    line 13
  3. Very specific:

    Use "Assumptions Surface Prompt" and "Initial Specification Prompt" in ../spec-driven-development/references/prompt-patterns.md.

    line 14
  4. Very specific:

    If spec.md has open questions, run "Clarify Phase Prompt" and "Post-Clarify Spec Update Prompt" from the same file.

    line 15
  5. Very specific:

    Use the template under "spec.md Template" in ../spec-driven-development/references/artifact-templates.md.

    line 16
  6. Very specific:

    Write the draft spec.md in this turn.

    line 19
  7. Distinctive:

    If the request touches auth, permissions or billing, write explicit ACs for each role's allowed and denied actions and for every error case.

    line 20

≈ “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-specify

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

Read ../spec-driven-development/SKILL.md, section "Phase 1". Read ../spec-driven-development/references/workflow-phases.md, section "Phase 1" and, for a change to existing behavior, "Delta Specs". Use "Assumptions Surface Prompt" and "Initial Specification Prompt" in ../spec-driven-development/references/prompt-patterns.md. If spec.md has open questions, run "Clarify Phase Prompt" and "Post-Clarify Spec Update Prompt" from the same file. Use the template under "spec.md Template" in ../spec-driven-development/references/artifact-templates.md.

Produce: specs/<feature>/spec.md, MoSCoW-prioritized ACs, each [MUST] with a proof line. Write the draft spec.md in this turn. Do not wait for answers first: each assumption you cannot confirm from the repo goes into the spec as a [NEEDS CLARIFICATION] marker, and the reply counts them. If the request touches auth, permissions or billing, write explicit ACs for each role's allowed and denied actions and for every error case. Open [NEEDS CLARIFICATION] items block Gate 1: name each one and how its answer changes the design, and offer to clarify. If the user insists, proceed: replace each marker with an explicit Assumption: line in the spec and report it. Never choose silently, never refuse indefinitely. Cold read (levels M and L): run "Cold Read Prompt" in a fresh agent or session given only spec.md, constitution.md and the Baseline: files of a delta spec, then compare its restatement with the user's intent. List every AC phrase with more than one reading (for example "records belonging to M": created by M, or assigned to M); each is a failing Gate 1 check fixed in the spec. No fresh context available means the cold read is inconclusive. Do not mark the spec Approved; the human does. Gate: "Gate 1" in ../spec-driven-development/references/quality-gates.md, including the cold read by a reader with no context. Validate: node ../spec-driven-development/scripts/sdd-check.mjs specs/<feature> Next: /sdd-plan once a human approves. Reply: Gate 1: pass|fail|inconclusive, one line per failing check, ACs: N MUST, N SHOULD, N COULD, Open questions: N, the spec path, and one next action. No preamble, under ~25 lines, never the spec pasted.

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