agentleFS
Sign inStart free
mauriciovieiramauriciovieira/groundwork/skills/to-prd/SKILL.md

to-prd

Skill0 starsChanged 4 months agoMITView on GitHub

Use when a plan has already been talked through in this conversation and deserves capturing - the user says "write this up", "capture this", "let's document what we agreed", or asks to move forward on a discussed design. Synthesizes the conversation into prd.md with no interview; never invents what wasn't discussed.

132 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-mapping, zoom-out and 10 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.
  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • victorgarciaesgiSkill

    zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

    Also in 60 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 23 projects that use this

  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 23 projects that use this

  • kennethkeimSkill

    ubiquitous-language

    Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

    Also in 23 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 34 projects that use this

  • +4 more from simo97

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 127 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read back through what's been discussed and pull out, only where it was actually stated:

    line 19
  2. Distinctive:

    Do not fabricate content for a section that wasn't discussed.

    line 28
  3. Very specific:

    Write docs/groundwork/features/NNNN-slug/prd.md with sections: Problem, Users, Goals, Non-goals, Acceptance criteria, Out of scope.

    line 32
  4. Very specific:

    If prd.md already exists for this feature, merge rather than overwrite: keep existing content that the conversation didn't touch, update …

    line 34

“Common” is measured: kept by at least 6 in 10 of the 127 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

groundwork:to-prd

Capture, don't interview. The user has already talked through a plan in this conversation; your job is to turn what was actually said into a prd.md, not to ask new questions or invent what wasn't discussed.

0. Preconditions

Read docs/groundwork/config.json. If it doesn't exist, don't stop - bootstrap it per the "Lazy bootstrap" section of the groundwork setup skill: detect tracker and project type, write the config with defaults, state the assumptions in one line, and continue. Running setup explicitly is only for customizing.

Determine the feature slug and number: an argument naming one, an existing feature obviously under discussion, or the next NNNN-slug under docs/groundwork/features/ if this is new. Confirm the slug with the user before writing.

1. Extract from the conversation

Read back through what's been discussed and pull out, only where it was actually stated:

  • Problem and motivation
  • Users / who this is for
  • Goals
  • Non-goals / explicitly out-of-scope items
  • Acceptance criteria, if any were stated
  • Any decisions that read as architectural (flag these for the user - they may belong in an ADR via survey rather than the PRD body)

Do not fabricate content for a section that wasn't discussed. If acceptance criteria were never mentioned, leave that section as an explicit placeholder and tell the user it's missing rather than inventing plausible-sounding criteria.

2. Write prd.md

Write docs/groundwork/features/NNNN-slug/prd.md with sections: Problem, Users, Goals, Non-goals, Acceptance criteria, Out of scope. Use the language the conversation has been in. No em dashes.

If prd.md already exists for this feature, merge rather than overwrite: keep existing content that the conversation didn't touch, update what it did.

3. Report gaps and hand off

Tell the user exactly what got captured and, separately, what's missing or thin. If there are real gaps or unstated assumptions, offer to continue into survey to interrogate them rather than pretending the PRD is complete. If it's solid, offer to-issues. On a yes, load and follow the groundwork skill of that name directly in this session - don't wait to be asked again.

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