agentleFS
Sign inStart free
wakqasahmedwakqasahmed/ai-engineering-workflow-skills/skills/engineering/to-prd/SKILL.md

to-prd

Skill2 starsChanged 2 months agoMITView on GitHub

Synthesize the current conversation and repository context into a concise product and engineering spec, publish it to the project issue tracker, and gate agent readiness before decomposition. Use when high-level work needs product framing, implementation and testing decisions, or success criteria captured without another general interview.

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 9 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

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

  • 0

    Common

    Most of the 126 edited versions we read keep these.

  • 4

    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. Very specific:

    Use after clarify-work has resolved fuzzy terminology or scope, when the conversation still needs a durable product and engineering spec.

    line 8
  2. Distinctive:

    Write a concise spec with these sections: Problem, Goal and solution, Prioritized user stories, Success criteria, Non-goals, Constraints, …

    line 17
  3. Distinctive:

    If no tracker or publishing access can be detected, return the finished spec with that explicit blocker.

    line 22
  4. Distinctive:

    Do not reopen settled decisions or invent requirements unsupported by the conversation and repository.

    line 37
  5. Very specific:

    Do not duplicate clarify-work's terminology interview or decompose-to-issues' task breakdown.

    line 38
  6. Distinctive:

    Keep the published spec short enough for an implementation agent to use as its source of truth.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 126 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

To PRD

Use after clarify-work has resolved fuzzy terminology or scope, when the conversation still needs a durable product and engineering spec. Skip this for narrow, issue-shaped work.

Workflow

  1. Synthesize the current conversation; do not repeat a general requirements interview.
  2. Inspect relevant code, the domain glossary, and applicable ADRs before drafting when they are available. Preserve established vocabulary and decisions.
  3. Reuse the highest existing test seam that proves external behavior. Use nearby test prior art to identify the expected layer and observable assertions.
  4. Ask at most one focused confirmation only when the highest existing test seam is genuinely unresolved after inspecting the conversation, repository, and project decisions. Wait for that answer before drafting or publishing. Otherwise continue directly to the spec. Do not use this confirmation for product, implementation or architecture, publication or access, or other blockers; record those in the spec instead.
  5. Write a concise spec with these sections: Problem, Goal and solution, Prioritized user stories, Success criteria, Non-goals, Constraints, Open product decisions, Implementation decisions, and Testing decisions.
  6. Detect the project issue tracker from repository configuration, remotes, or available integrations. Publish the spec to the detected project issue tracker.
  7. Apply ready-for-agent only after every blocker is resolved and publication succeeds. Product, test-seam, implementation or architecture, publication or access, and other blockers all prevent readiness. When access allows, publish a blocked spec without the label and identify every blocker and owner.
  8. Hand the published spec to decompose-to-issues; do not turn the PRD into an issue breakdown.

If no tracker or publishing access can be detected, return the finished spec with that explicit blocker. Do not invent a destination, claim publication or readiness, or hand off to decomposition.

Spec guidance

  • Frame the problem from the affected user's or operator's perspective.
  • State the goal and solution as observable outcomes, not a task list.
  • Include prioritized user stories only when they clarify distinct actors, outcomes, or ordering; keep them few and outcome-focused.
  • Make success criteria verifiable and include constraints that materially shape delivery.
  • Distinguish unresolved product decisions from settled implementation decisions.
  • In Testing decisions, name the chosen existing seam, test layer, relevant prior-art pattern, important external behaviors, and any necessary manual validation.

Guardrails

  • Exclude volatile file paths and code snippets. Include a prototype artifact only when it records a decision more clearly than prose; trim it to the decision-rich state machine, schema, type shape, or interaction.
  • Do not reopen settled decisions or invent requirements unsupported by the conversation and repository.
  • Do not duplicate clarify-work's terminology interview or decompose-to-issues' task breakdown.
  • Keep the published spec short enough for an implementation agent to use as its source of truth.

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