agentleFS
patmeh1patmeh1/product-docs-kit/.claude/skills/add-feature/SKILL.md

add-feature

Skill0 starsChanged 2 months agoMITView on GitHub

Propagate a new or changed feature from the PRD through every other product document - user flows, design system, architecture, data model, API contract, security, tests, and traceability. Use when the user wants to add a feature, change existing behaviour, remove a feature, or asks "what would this feature affect". Run this BEFORE writing any code. Also use for phrases like "I want to add", "new requirement", "change request", or "impact analysis".

28 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md, then the full docs/ set.

    line 13
  2. Very specific:

    Read the full procedure in prompts/03-add-feature-change-request.md and follow it exactly.

    line 14
  3. Very specific:

    Update every affected document.

    line 42
  4. Very specific:

    Add a TC- test case for every acceptance criterion.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 26 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

Feature Change Request — one feature, every document

Perform a change impact analysis and propagate a requirement through the whole documentation set, so it can then be implemented against a real specification.

Before you start

  1. Read AGENTS.md, then the full docs/ set.
  2. Read the full procedure in prompts/03-add-feature-change-request.md and follow it exactly.
  3. Identify the requirement ID (FR-___). If the user has not written it into docs/01-prd.md yet, draft the PRD entry first and confirm it with them before going further.

Four phases — stop for the user between each

Phase 1 — Understand and challenge

Restate the feature. Review their acceptance criteria: are they testable, binary, and do they cover error paths and permissions, or only the happy path?

Say plainly if the feature serves no OBJ- in the vision document and recommend rejecting it. Offer a simpler alternative if one exists, even unasked.

Phase 2 — Impact analysis

Produce a table: which documents change, what changes, which new IDs, what risk. Justify every None — that is where things get missed.

Then explicitly assess:

  • Breaking change? API shape, required fields, removed columns, changed behaviour
  • Migration? State the expand → migrate → contract sequence across releases
  • Feature flag? Recommend one if risky or hard to validate on preview
  • Shared component touched? List every SCR- that uses it

Stop. Do not edit anything until the user approves.

Phase 3 — Propagate

Update every affected document. For each one: bump version, set last_updated, and append a Change Log row citing the requirement ID. Never modify an existing change log row.

Add a TC- test case for every acceptance criterion. Add the traceability matrix row. Add the CHANGELOG.md entry under [Unreleased].

Phase 4 — Verify and hand off

Confirm IDs are unique, nothing contradicts an accepted ADR, and terminology matches docs/11-glossary.md. Then produce a ready-to-paste GitHub issue and the branch name feat/FR-___-slug.

Absolute rule

Do not write any application code in this skill. Documentation only. Implementation happens in /implement-feature.

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.