agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/write-design/SKILL.md

write-design

Skill0 starsChanged 16 days agoMITView on GitHub

Write a technical design for one initiative — approach, contracts, failure, security, and delivery slices. Use when the user asks for a technical design, tech spec, or how we will build this. Do not write product code. Do not design a one-line bug.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not implement. Do not start coding “just the first slice.”

    line 19
  2. Very specific:

    If product why is unknown, stop and run write-prd.

    line 31
  3. Very specific:

    Read AGENTS.md, applicable requirements/contracts/NFRs, and the named PRD/architecture.

    line 46

≈ “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

Write design

Describe how this initiative will be built in this repository. This is not a PRD, not write-architecture, and not write-dev-tasks.

Do not implement. Do not start coding “just the first slice.”

Is this the right skill?

SignalDo this instead
Why / success still openwrite-prd
New system boundaries / greenfield shapewrite-architecture
One sticky library/store choicerecord-decision
One small already-clear changeshape-work
Break an existing design into ticketswrite-dev-tasks

If product why is unknown, stop and run write-prd. If slice 1 is the whole goal, offer shape-work.

Required inputs

  • PRD and/or architecture if they exist
  • Applicable requirements, contracts, and NFR paths with source revisions. For an initiative with Must requirements, missing requirements or approval evidence → stop and name write-requirements; a small clear slice may use shape-work with an explicit reason.
  • AGENTS.md. Skim entry points and an existing pattern.

Human decisions (do not invent)

  • Product forks, compatibility, environment
  • Breaking contract changes

Procedure

  1. Read AGENTS.md, applicable requirements/contracts/NFRs, and the named PRD/architecture. Check prerequisite approvals or explicit waivers against context/decision-rights.md; do not design from an unapproved or stale baseline.
  2. Find the home: first existing docs/design/, docs/designs/, docs/specs/, or a path AGENTS.md names. Name: docs/design/YYYY-MM-DD-<slug>.md.
  3. Open references/design-template.md. Copy every heading. Write n/a when unused.
  4. Approach names real files, types, or layers — or says none exist. Data/contracts stay expand-then-contract. Config is names only, never secret values. Delivery is ordered slices; do not write full tickets (write-dev-tasks).
  5. Load engineering-bar (../engineering-bar/SKILL.md). Check Minimum path, Failure, Data, Security, UI. Do not paste the bar.
  6. Map every applicable Must id to an approach/design slice, contract, and verification plan. A trace is artifact path + local id, qualified by source revision; do not renumber upstream ids. Uncovered Must items are blocking questions, not silent omissions. Keep design status draft until the authorized human's approval evidence exists.

Output

  • Path: docs/design/YYYY-MM-DD-<slug>.md
  • Template: references/design-template.md

Quality bar

  • An engineer could start slice 1 without guessing the approach
  • Alternatives include a smaller option (reuse / stdlib / native)
  • At least one Delivery slice is smaller than the whole initiative
  • Unused headings are n/a
  • Every applicable Must is covered or explicitly blocked; input revisions and prerequisite approval evidence are named

Done

  1. Path
  2. Chosen approach in a few sentences
  3. Slice 1 and the next skill (write-dev-tasks or shape-work)

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