agentleFS
UwayxtUwayxt/agent-skills/.agents/skills/growth-impact-review/SKILL.md

growth-impact-review

Skill4 starsChanged 3 months agoMITView on GitHub

Evaluate systemic impact of new additions. Use when scaling dashboards, adding new modules, or assessing layout stress.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    Run after EVERY module/page addition.

    line 10
  2. Very specific:

    Visual Hierarchy: After 8+ modules, check visual-hierarchy-review.

    line 13
  3. Very specific:

    Tokens: Check design-tokens. Does adding modules require new token variants (e.g., new accent colors for module identity)?

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Growth Impact Review

Growth breaks structures. Anticipate the fracture points before they snap.

When to Run

Run after EVERY module/page addition. Not at milestones. Not at release. Every. Single. Addition.

Pipeline Integration

  • Visual Hierarchy: After 8+ modules, check visual-hierarchy-review. Does the dashboard homepage's visual hierarchy still work — does the most important module still get the most prominent position?
  • Tokens: Check design-tokens. Does adding modules require new token variants (e.g., new accent colors for module identity)? Flag if the token set is being stretched beyond its design.

1. Dashboard Check

  • Do shortcut grids wrap awkwardly?
  • Is the primary module still prominent?
  • Does the visual density overwhelm the user?

2. Navigation Check

  • Does any navGroup exceed the cognitive limit?
  • Are new categories required, or does it fit organically?

3. Routes Check

  • Do new routes conflict with existing path conventions?
  • Are legacy routes preserved or appropriately redirected?

4. Cross-refs Check

  • Are interdependent modules correctly linked?
  • Is data properly shared without redundant fetches?

Scenario

Module #7 added to a dashboard that was designed for 4. Impact report shows: navGroup 'Operasional' now has 6 items (OK, under limit), but shortcut grid now wraps to 3 rows (recommend pagination or grouping).

Anti-Patterns

  • The Frog Boiler: Ignoring minor layout degrading on each addition until the UI is unusable.
  • Token Sprawl: Creating new semantic tokens for one-off module identities.

Completion Criteria

  • All checks completed for Dashboard, Nav, Routes, and Cross-refs.
  • Mitigation strategies proposed for any layout or cognitive breakage.
  • Tokens and visual hierarchy verified.

Output Format

A structured Markdown impact report detailing the checks, flagged issues, and specific mitigation proposals.

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.