agentleFS
jimtinjimtin/production-ai/skills/user-action-coverage-review/SKILL.md

user-action-coverage-review

Skill1 starsChanged 5 months agoMITView on GitHub

Impact-scoped review that maps user actions, critical paths, roles, states, and mutations to Playwright/E2E plus unit/integration evidence. Use after an accepted plan and before implementation for substantial feature, frontend, workflow, route, mutation, auth/role, upload, save/delete, navigation, admin/user portal, or release-readiness work; rerun before final validation if scope changes.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use this skill to prevent missing browser, integration, and unit coverage from being discovered only at the full gate.

    line 10
  2. Distinctive:

    Use after plan acceptance and before implementation for substantial user-facing or workflow work, including:

    line 14
  3. Distinctive:

    Read applicable AGENTS.md, route/workflow manifests, critical-path inventories, Playwright specs, integration tests, unit tests, and …

    line 27
  4. Very specific:

    Prefer existing repo inventory files over inventing a parallel source of truth — $repo-testing-setup commits these at foundation time.

    line 28
  5. Distinctive:

    Update flow inventories and critical-workflow manifests in the same change when the repo has them.

    line 42
  6. Very specific:

    Do not start the canonical full gate until each in-scope row is covered, blocked, or explicitly deferred by the user.

    line 46
  7. Distinctive:

    Use this shape in planning notes, implementation handoff, or final report:

    line 50
  8. Distinctive:

    Do not call the review complete until:

    line 70
  9. Distinctive:

    every in-scope user action is listed

    line 72
  10. Distinctive:

    every critical path maps to browser/E2E plus integration evidence

    line 73

≈ “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

User Action Coverage Review

Purpose

Use this skill to prevent missing browser, integration, and unit coverage from being discovered only at the full gate. This is an impact-scoped coverage review, not a full app audit. Use $full-app-review for whole-app or production-readiness audits.

When To Use

Use after plan acceptance and before implementation for substantial user-facing or workflow work, including:

  • new or changed routes, forms, navigation, mutations, saves, deletes, uploads, imports, exports, toggles, filters, role-gated actions, admin/user portal workflows, and deployed-flow behavior
  • frontend changes covered by $frontend-design-quality
  • release-readiness work where user workflows or critical paths are in scope

The $clarify-before-build exit hands off here: a confirmed Shared Understanding Contract for substantial user-facing work names this skill as the first post-confirmation step, and the action matrix becomes the contract's acceptance-criteria evidence.

Rerun before final validation if implementation scope changes, if a user action is added or removed, or if tests are rewritten.

Workflow

  1. Load repo truth.
    • Read applicable AGENTS.md, route/workflow manifests, critical-path inventories, Playwright specs, integration tests, unit tests, and relevant package scripts.
    • Prefer existing repo inventory files over inventing a parallel source of truth — $repo-testing-setup commits these at foundation time.
  2. Build the action matrix before implementation.
    • Include every affected click, form submit, save, autosave, upload/import/export, delete/archive, navigation, keyboard path, role-gated mutation, empty/error/retry state, and removed action.
    • Include public, authenticated, admin, and superadmin roles when the surface supports them.
  3. Map evidence.
    • Browser/E2E evidence must prove the user can actually perform or cannot perform the action.
    • Integration evidence must cover API routes, persistence boundaries, provider adapters, permissions, workflows, queues/jobs, and cross-module contracts.
    • Unit evidence must cover changed hooks, services, helpers, validation, rendering utilities, state machines, and branch behavior.
  4. Convert gaps into implementation tasks.
    • missing, stale, partial, and negative assertion needed rows are not observations to defer silently; they become work items before final validation.
    • Removed actions need negative browser assertions where the old UI/action would otherwise be reachable.
    • Update flow inventories and critical-workflow manifests in the same change when the repo has them.
  5. Reconcile before the full gate.
    • Rerun the matrix after implementation if scope changed.
    • Do not start the canonical full gate until each in-scope row is covered, blocked, or explicitly deferred by the user.

Required Matrix

Use this shape in planning notes, implementation handoff, or final report:

| User action | Route/surface | Role/persona | Data state | Expected behavior | Playwright/E2E evidence | Unit/integration evidence | Status |
|---|---|---|---|---|---|---|---|
| Save profile | /settings/profile | signed-in user | valid form | persists and shows success | WEB-123 | profile-route.test.ts, useProfileSave.test.ts | covered |

Allowed status values:

  • covered
  • missing
  • stale
  • partial
  • negative assertion needed
  • blocked
  • deferred by user

Acceptance Bar

Do not call the review complete until:

  • every in-scope user action is listed
  • every critical path maps to browser/E2E plus integration evidence
  • changed logic has unit or focused integration coverage identified
  • removed actions have absence coverage or a documented reason
  • stale tests, stale manifests, and stale flow inventories are listed as implementation tasks
  • blockers name the exact missing dependency, fixture, auth, environment, or product decision

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.