agentleFS
warpdotdevwarpdotdev/oz-for-oss/.agents/skills/create-product-spec/SKILL.md

create-product-spec

Skill313 starsChanged 6 months agoMITView on GitHub

Create a product spec from a GitHub issue in this repository by applying the shared `write-product-spec` workflow with Oz-specific issue context and output paths. Use when an issue should be turned into a product spec artifact stored under `specs/GH<issue-number>/product.md` and the agent should prepare file changes only, without creating commits or pull requests itself unless a cloud workflow explicitly asks for it.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 9 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a product spec from a GitHub issue for this repository.

    line 8
  2. Distinctive:

    Use that shared skill as the base behavior and structure unless this wrapper overrides it.

    line 16
  3. Distinctive:

    do not create or edit Linear issues as part of this workflow

    line 24
  4. Distinctive:

    If a triggering comment or other workflow-provided comment context is present, treat it as additional context, not as a silent override of …

    line 30
  5. Very specific:

    Start from the shared write-product-spec guidance and follow its structure and writing standards unless this wrapper says otherwise.

    line 34
  6. Very specific:

    Read the issue details carefully.

    line 35
  7. Very specific:

    Create or update specs/GH<issue-number>/product.md.

    line 37
  8. Distinctive:

    Keep the product spec focused on intended behavior and user-facing requirements.

    line 38
  9. Distinctive:

    If design context such as a Figma link is present in the issue description or comments, include it.

    line 47
  10. Distinctive:

    Do not include implementation details, file-level changes, or technical design.

    line 48
  11. Very specific:

    Do not implement the feature or modify production code as part of this task.

    line 49
  12. Very specific:

    Do not include issue number references (e.g.

    line 50
  13. Distinctive:

    Leave the repository with the new or updated product spec file ready to be committed by the workflow.

    line 57
  14. Very specific:

    When requested by the prompt, leave a ready-to-use pr-metadata.json with branch_name, pr_title, and pr_summary.

    line 58
  15. Distinctive:

    If the issue is underspecified, still produce the best possible product spec and clearly capture assumptions or open questions in the spec …

    line 59

≈ “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

create-product-spec

Create a product spec from a GitHub issue for this repository.

Overview

This skill is a thin Oz wrapper around the shared product-spec workflow:

  • write-product-spec

Use that shared skill as the base behavior and structure unless this wrapper overrides it. Keep the same emphasis on precise user-facing behavior, invariants, edge cases, validation, and open questions.

The Oz-specific differences are:

  • the primary input is a GitHub issue, not a Linear issue
  • the output path is specs/GH<issue-number>/product.md
  • issue_comments.md and triggering-comment context are first-class inputs
  • a workflow may also request a structured PR metadata file in pr-metadata.json
  • do not create or edit Linear issues as part of this workflow

Inputs

Expect issue details in the prompt, including the issue number, title, description, labels, assignees, and optional prior discussion captured in issue_comments.md.

If a triggering comment or other workflow-provided comment context is present, treat it as additional context, not as a silent override of the issue body. Resolved decisions from comments can refine the spec; unresolved disagreements should remain explicit open questions.

Process

  1. Start from the shared write-product-spec guidance and follow its structure and writing standards unless this wrapper says otherwise.
  2. Read the issue details carefully. If issue_comments.md exists, review it for clarifications, prior decisions, and issue-comment nuance that should influence the spec.
  3. Inspect the repository enough to understand the current user workflow and likely scope before writing the spec.
  4. Create or update specs/GH<issue-number>/product.md.
  5. Keep the product spec focused on intended behavior and user-facing requirements. Use the shared skill's sections as the baseline, adapted to this repository and issue format. At minimum, cover:
    • summary
    • problem
    • goals
    • non-goals or scope boundaries
    • concrete user experience and behavior requirements
    • success criteria
    • validation
    • open product questions
  6. If design context such as a Figma link is present in the issue description or comments, include it. If no design context exists, make that absence explicit rather than silently omitting it.
  7. Do not include implementation details, file-level changes, or technical design. Those belong in the tech spec.
  8. Do not implement the feature or modify production code as part of this task. Limit changes to the product spec artifact. Treat temporary context files such as issue_comments.md as scratch input only and do not commit them.
  9. Do not include issue number references (e.g. (#N), Refs #N) in commit messages. The issue is already linked in the PR.
  10. If the prompt asks for it, write pr-metadata.json at the repository root containing a JSON object with the fields branch_name, pr_title, and pr_summary. The pr_summary should summarize the product and technical planning clearly enough that reviewers can use it directly as the PR body. For spec-only PRs, include a non-closing reference to the source issue such as Related issue: #<issue-number> rather than closing keywords like Closes or Fixes.
  11. Default behavior: do not stage files, create commits, push branches, open pull requests, or use the GitHub CLI. If the prompt explicitly instructs you to publish a named branch, you may commit and push exactly the requested spec changes to that branch, but still do not open or update the pull request yourself unless the prompt explicitly asks for it.
  12. In your final response, provide a brief summary of the product spec and call out any assumptions or open questions so the workflow can reuse that summary when creating the PR.

Outputs

  • Leave the repository with the new or updated product spec file ready to be committed by the workflow.
  • When requested by the prompt, leave a ready-to-use pr-metadata.json with branch_name, pr_title, and pr_summary.
  • If the issue is underspecified, still produce the best possible product spec and clearly capture assumptions or open questions in the spec file and final response.

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.