agentleFS
MrCipherSmithMrCipherSmith/goodai-base/skills/trd-creator/SKILL.md

trd-creator

Skill0 starsChanged 5 months agoMITView on GitHub

Use when PRD and FSD exist and need to be expanded into a Technical Requirements Document (TRD) covering architecture, tech stack, data models, API contracts, and non-functional requirements.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always produce these seven sections:

    line 31

≈ “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

TRD-Creator Sub-Agent

1. Purpose

Expands PRD and FSD into a Technical Requirements Document (TRD) that specifies how the system must be built — architecture decisions, data models, API contracts, NFRs, and deployment notes — grounding functional requirements in technical reality.

Operates in two modes:

  • Direct Mode — interacts with the user
  • Orchestrated Mode — invoked by spec-orchestrator with structured JSON input; returns document content

2. TRD Document Structure

Always produce these seven sections:

  1. Architecture — system architecture decisions, component boundaries, and key design patterns
  2. Tech Stack — languages, frameworks, libraries, and services selected and why
  3. Data Models — entity definitions, relationships, key fields, and storage decisions
  4. API Contracts — endpoint signatures, request/response shapes, authentication, error codes
  5. Non-Functional Requirements — performance targets, scalability, reliability, security, observability
  6. Integration Points — external systems, third-party services, and internal service dependencies
  7. Deployment Notes — infrastructure requirements, environment variables, migration steps, rollout strategy

3. Orchestrated Mode

3.1 Input Contract

See input-contract.schema.json. Key fields:

{
  "request": "<original user request — always required>",
  "upstream": {
    "brd": "<brd.md content or null>",
    "prd": "<prd.md content — always present when trd-creator is invoked>",
    "fsd": "<fsd.md content or null>"
  },
  "codebase_path": "<path to project codebase, or null>",
  "current_draft":     "<existing trd.md content — present only in refinement mode>",
  "reviewer_findings": [
    { "id": "P-N", "location": "<section>", "severity": "blocker|major|minor", "description": "<what is wrong>" }
  ],
  "upstream_warnings": ["<DONE_WITH_CONCERNS note from a prior stage>"]
}

prd.md is always present when trd-creator is invoked: a PRD failure causes the pipeline to exit before this stage.

3.2 Generation Mode (no current_draft)

Produce a TRD from scratch. For each optional upstream artifact that is null, note its absence and state what assumptions the TRD makes in its place. If codebase_path is provided, inspect relevant files to ground tech stack and architecture claims in actual code.

3.3 Refinement Mode (reviewer_findings present)

Address every finding in reviewer_findings within current_draft. Do not regenerate from scratch — preserve the structure and revise only what the findings require.

3.4 Output

Return the complete TRD document as a plain markdown string. Prefix your response with:

STATUS: DONE

The orchestrator writes the returned content to trd.md. Do not write files yourself in orchestrated mode.


4. Direct Mode

Interact with the user. Ask for PRD/FSD content if not provided. Save the TRD to docs/trd/ following rules/core/documentation-management.mdc.

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.