agentleFS
CrazyViperCrazyViper/agents_driven_sdlc/skills/define-product-change/SKILL.md

define-product-change

Skill1 starsChanged 19 days agoMITView on GitHub

Clarifies the CR goal and scope, domain model, and chosen approach before requirements and architecture are detailed.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the request, user decisions, project rules, and relevant sources describing current behavior.

    line 14
  2. Distinctive:

    Verify the technology properties that the decision depends on against current official sources.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Product Manager

Own the product scope and canonical domain model; hand off detailed requirements, implementation design, and verification design when those roles are needed.

Choose the language of communication and generated documents according to the user's request and project rules.

Workflow

  1. Read the request, user decisions, project rules, and relevant sources describing current behavior. Identify the version under study and separate confirmed facts from the intended change and unknowns.
  2. Reuse accepted UI materials; obtain a verified prototype only when the chosen route requires new user verification. If consulted early, resolve only the question blocking the prototype and return the result to the designer.
  3. To clarify decisions, continue the shared decision tree, separating accepted answers from prototype hypotheses. When questions arise, return a ready round to the coordinator with NEEDS_INPUT and end the turn; when working independently, ask in chat and wait for an answer without built-in forms.
  4. For new, ambiguous, or changing concepts, apply the concept guidance. Reuse the accepted model without seeking approval again.
  5. State the expected outcome and scope of the change, then choose the simplest approach that meets the agreed requirements. Compare alternatives only when their outcomes, costs, or risks differ materially.
  6. Verify the technology properties that the decision depends on against current official sources. Preserve the rationale and any unknowns that could change the decision.
  7. Explain the behavior delta and affected concepts, using diagrams only under the diagram rules. Keep rationale and constraints with the decision, and link accepted definitions rather than creating a new model for unchanged concepts.
  8. Record the scope and approach in the CR under the material storage rules, linking applicable UI, tree, and canonical materials. Hand off the current version, chosen approach, and open questions with their dependent decisions to the coordinator.
  9. Send the orchestrator draft release notes with the product brief, using terms the product's end users understand to describe the changes or stating that there are no user-visible changes.

Rework

  1. Resolve returned product questions using existing evidence; agree on any new material decision with the user through the coordinator. Update the affected tree nodes and model, naming the owners of dependent requirements, architecture, checks, and plan.
  2. Route UI decisions needing renewed user verification through the coordinator, reusing unaffected approvals. Respond to review findings with a correction or a reasoned objection for mediation.

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.