agentleFS
Sign inStart free
theinternetitheinterneti/TTA.dev/.claude/skills/sdd-workflow/SKILL.md

sdd-workflow

Skill0 starsChanged 7 months agoMITView on GitHub

Use this skill when the user asks to build a new feature or write implementation code. Enforces the Spec-Driven Development (SDD) 4-phase workflow before any code is written.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    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. Distinctive:

    Red: Write failing test encoding acceptance criteria

    line 32
  2. Distinctive:

    Run quality gate before marking task complete

    line 35
  3. Very specific:

    If the user asks for code without a spec, initiate /specify first and explain the SDD process.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 4 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 Workflow (TTA.dev)

No implementation code may be written before completing the SDD phases.

The 4 Phases

Execute these phases sequentially. No phase may be skipped.

  1. /specify — Functional Specification (The "What")
    • User journeys, edge cases, success criteria, out-of-scope
    • Output: Markdown document for user review and approval
  2. /plan — Technical Plan (The "How")
    • Which packages are affected (tta-dev-primitives, tta-observability-integration, etc.)
    • New modules, classes, functions to create
    • How the feature composes with existing primitives (>>, |)
    • External dependencies with justification
    • Observability strategy (traces, metrics, logs)
  3. /tasks — Task Breakdown
    • Isolated, testable work units
    • Each task includes acceptance test description
    • Numbered by dependency (topological sort)
    • Format: Markdown checklist
  4. /implement — Test-Driven Implementation
    • Red: Write failing test encoding acceptance criteria
    • Green: Minimal implementation to pass the test
    • Refactor: Clean up while tests stay green
    • Run quality gate before marking task complete

Exceptions

  • /spike: User explicitly requests prototype code. Spike code must never be merged without going through the full SDD workflow afterward.

Enforcement

  • If the user asks for code without a spec, initiate /specify first and explain the SDD process.
  • Reference this constitution by section (e.g., "Per §2 Phase 1, I need to generate a spec first.").

Deep Reference

For the complete SDD Constitution with all tables and detailed guidance, see docs/agent-guides/sdd-constitution.md.

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