agentleFS
TrarothTraroth/claude-dev-framework/skills/design-review/SKILL.md

design-review

Skill1 starsChanged 7 months agoMITView on GitHub

Perform a design review for a new class or data structure in the project. Use this skill before implementing any non-trivial class or when the user explicitly asks for a design validation. The goal is to validate the core structure, invariants, complexity, and alternatives before any code is written.

155 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use project-stage-detect, team-audio and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 16 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +4 more from CoralGame
  • +3 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Before implementing a new class or data structure

    line 14
  2. Distinctive:

    When the user proposes a new design

    line 15
  3. Distinctive:

    When the user says "review the design", "is this a good structure", or "what do you think of this architecture"

    line 16
  4. Distinctive:

    If no issues are found in a category, skip it entirely.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 129 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

Design Review

When to run

  • Before implementing a new class or data structure
  • When the user proposes a new design
  • When the user says "review the design", "is this a good structure", or "what do you think of this architecture"

Review checklist

Report only findings or recommendations.

1. Core data structure

  • The underlying data structure is appropriate for the required operations
  • The structure has clearly defined invariants
  • The invariants can be preserved by all mutation operations
  • The structure does not introduce unnecessary complexity

2. Interface and contracts

  • The class implements the correct interface
  • The correct abstract base class is used when applicable
  • The public API is minimal and coherent
  • Method semantics match the expectations of the implemented interface

3. Complexity guarantees

  • Expected complexity for key operations is clearly defined
  • The chosen structure supports these complexity guarantees
  • No operation requires full traversal where O(1) or O(log n) is expected

4. Invariants

  • Structural invariants are clearly defined
  • Invariants can be documented using formal contracts
  • All mutation methods can preserve these invariants

5. Thread safety

  • Thread-safety requirements are clear
  • If applicable, a synchronized variant is considered
  • The locking strategy is realistic and safe

6. Alternatives

For each relevant alternative:

  • Alternative design identified
  • Advantages and disadvantages compared
  • Reason for rejection documented

Output format

Report findings grouped by category. For each finding, state:

  • The concern
  • The recommendation
  • The severity (blocking / suggestion)

If no issues are found in a category, skip it entirely.

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.