agentleFS
Sign inStart free
darinhdarinh/copilot-tools/skills/spec-driven/SKILL.md

spec-driven

Skill1 starsChanged 4 months agoMITView on GitHub

The GitHub spec-kit workflow — constitution, specify, clarify, plan, tasks, implement, analyze — and deciding whether a change needs a spec update. Load this skill before running any /speckit-* command or writing to specs/.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use implement.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read .specify/memory/constitution.md and the relevant spec first.

    line 21
  2. Distinctive:

    Every spec claim references real code: file paths, function names, types.

    line 29
  3. Distinctive:

    Update the spec in the same commit as the code, not a follow-up.

    line 31
  4. Distinctive:

    If the requirement genuinely does not exist anywhere, that is a finding: say so, decide, and write the decision into the spec in the same …

    line 42
  5. Distinctive:

    When reviewing completed work:

    line 53
  6. Distinctive:

    Every code change is reflected in the specification artifacts.

    line 55
  7. Distinctive:

    Every spec claim references actual code.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

Spec-driven development

GitHub spec-kit is authoritative. Specifications live in .specify/ and specs/.

Workflow

/speckit-constitution → /speckit-specify → /speckit-clarify → /speckit-plan → /speckit-tasks → /speckit-implement → /speckit-analyze

/speckit-converge re-reads the codebase against the feature's artifacts and appends whatever is still unbuilt to tasks.md. Use it when you inherit a part-finished feature rather than re-deriving its state by reading code.

Discovery

Read .specify/memory/constitution.md and the relevant spec first. Read code when implementing, or when the spec has a known gap. Reading code to answer a question the spec already answers is how specs drift out of use: the spec stops being consulted, then stops being updated, then stops being true, in that order.

Rules

  • Specs describe what is, never what should be. No aspirational claims.
  • Every spec claim references real code: file paths, function names, types.
  • A code change without a corresponding spec update is unfinished.
  • Update the spec in the same commit as the code, not a follow-up.
  • Record the reasons, not just the outcomes. A decision table that says what was chosen and not why is re-litigated by the next agent at full price.

When the spec is silent

A task whose requirement is not in spec.md is not a task without a requirement — it is a task whose requirement lives somewhere you have not looked. Go to the source the plan was derived from before inventing an interpretation. Inventing one is how a plan quietly becomes a different plan.

If the requirement genuinely does not exist anywhere, that is a finding: say so, decide, and write the decision into the spec in the same commit.

Known gaps

State them rather than faking them. A spec that lists what it does not yet cover is usable; one that reads as complete while being partial costs the next reader their confidence in all of it.

Validation

When reviewing completed work:

  • Every code change is reflected in the specification artifacts.
  • Every spec claim references actual code.
  • No aspirational claims.
  • tasks.md checkboxes match what was actually delivered, and the prose beside a ticked task says what it delivered, not what it intended to.

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