agentleFS
paoloirrerapaoloirrera/ccgraph/.claude/skills/design-doc/SKILL.md

design-doc

Skill1 starsChanged 3 months agoMIT-0View on GitHub

Generate a high-level design doc + task map from an approved story.md

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use testing, release-notes and 1 more.

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.
  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    release-notes

    Author and update release notes for Azure App Configuration libraries and providers. USE FOR: write release notes, add release note entry, update release notes, draft release notes, new version release notes, format release notes. DO NOT USE FOR: generating changelogs from git history, writing internal engineering notes.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

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 22 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:

    Verify versions/features against real sources.

    line 23
  2. Very specific:

    ADRs: If a decision is cross-cutting and hard to reverse (e.g.

    line 31
  3. Distinctive:

    Every task maps to a DoD checkbox.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 22 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

/design-doc — architecture + task map

Step 3 of the AI-DLC pipeline. Turns an approved story.md into design-doc.md: the single source of structure (architecture, decisions, dependencies, and a task map). Per-task detail — the API surface each unit exposes — lives in the task files produced by /tasks. Neither the design doc nor the task files hold full implementations; those are written in the building phase, after inception.

Input

The story slug, e.g. /design-doc weather-tool. Reads .local/user-stories/<slug>/story.md.

Steps

  1. Read the story. If it still has unresolved ⏳ open: items, STOP and recommend /story-refine <slug> first — a design on shifting requirements is wasted work.
  2. Read the template in references/design-template.md (bundled). Match its section order.
  3. Draft the design doc. For each section:
    • Goal & non-goals — lift from the story's Scope; make non-goals explicit.
    • Architecture — the layering/module split and why. An ASCII diagram + a package/file layout tree when it's a Python package or React/TS app. Keep each layer independently testable.
    • Key dependencies — a table of load-bearing choices with a one-line justification each. Verify versions/features against real sources; note the date verified. Do not assert versions from memory.
    • Task map — a numbered table (T1…Tn) with Task / Depends-on / File columns, plus a recommended order. Each task must end green (Python: ruff/black/pytest; TS: tsc/eslint/tests) and map to a DoD checkbox in the story. This table is the contract /tasks expands.
    • Cross-cutting contract — any invariant every task must preserve (e.g. the AgentCore Runtime contract: ARM64, FastAPI on 0.0.0.0:8080, /ws + /invocations + /ping, stateless container).
    • Decisions & open questions — list decided items with rationale; flag remaining ones.
  4. ADRs. If a decision is cross-cutting and hard to reverse (e.g. CDK vs. Terraform, AgentCore Runtime vs. Gateway, stateless default), propose recording it under docs/adr/NNNN-title.md and reference it from the doc. Ask before creating ADR files — confirm the user wants them and the numbering.
  5. Show the draft and confirm the architecture + task map before writing. This is the key gate: the task map drives everything downstream.
  6. On confirmation, write .local/user-stories/<slug>/design-doc.md and suggest /tasks <slug>.

Principles

  • Structure here, API surface in tasks, implementation in the building phase. If you're writing more than an illustrative snippet, stop — the interface belongs in a task file, the bodies belong to the build.
  • Every task maps to a DoD checkbox; every DoD checkbox is covered by at least one task. Call out any gap rather than papering over it.
  • Reference the story with a relative link; reference ADRs with relative links to docs/adr/.

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.