design-review
Skill2 starsChanged 3 months agoApache-2.0View on GitHub
Use when reviewing proposed or implemented architecture, interfaces, major refactors, system structure, product-direction alignment, or consequential design choices.
155 other projects use a version of this.
Adopted by
Most recently taken up by
- KarstenKreh/Standby.Designtheir own version, first seen Nov 8, 2026
- ldaume/agentic-engineering-harnesstheir own version, first seen Nov 8, 2026
- marnickvda/pop-quiztheir own version, first seen Nov 8, 2026
- DrBradStanfield/roadmaptheir own version, first seen Nov 8, 2026
- ainurdev/mystical-assistanttheir own version, first seen Nov 8, 2026
- openclaw/openclaw-enterprisetheir own version, first seen Nov 8, 2026
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.
CoralGameSkillproject-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
CoralGameSkillteam-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
julianoczkowskiSkillbrief-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
lilangMaxSkillasset-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
lilangMaxSkillcreate-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
Other versions155 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 155
- garrytan/gstack★ 141ksame name
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- DenchHQ/DenchClaw★ 1.7ksame name
- DenchHQ/ironclaw★ 1.7ksame name
- me2resh/apexyard★ 542same name
- julianoczkowski/designer-skills★ 536same name
- openclaw/openclaw-enterprise★ 454same name
- AndrewDryga/emisar★ 392same name
- TheDecipherist/claude-code-mastery-project-starter-kit★ 337same name
145 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- adversarial-auditSkill
- architectSkill
- cloud-run-basicsSkill
- debuggingSkill
- executorSkill
- gap-analysisSkill
- github-workflowSkill
- optimizationSkill
- reliabilitySkill
- researchSkill
- reuse-firstSkill
- security-reviewSkill
- simplicitySkill
- verificationSkill
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
- Distinctive: line 12
Start from user intent plus the applicable target product/design authority: canonical specifications, architecture decisions, design …
- Distinctive: line 14
Before consequential implementation, participate in the material-design-readiness gate: identify only material missing decisions whose …
- Distinctive: line 44
Prefer explicit trade-offs over universal rules.
- Distinctive: line 50
Do not implement the reviewed change or rewrite project vision because current code drifted from it.
“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.
Files
Design Review
Judge whether a proposed or implemented consequential design advances the target project's intended system without introducing unjustified complexity or structural drift.
Establish authority and drivers
Start from user intent plus the applicable target product/design authority: canonical specifications, architecture decisions, design documents, roadmap constraints, structure authority, and explicit invariants. Distinguish intended architecture from accidental properties of current implementation.
Before consequential implementation, participate in the material-design-readiness gate: identify only material missing decisions whose absence could alter architecture, interfaces, compatibility, security, ownership, irreversible behavior, or acceptance. Trivial, mechanical, reversible, or well-specified work does not need design-review ceremony merely to satisfy process.
Identify only the quality attributes material to the decision: correctness, maintainability, reliability, security, performance, cost, compatibility, operability, delivery speed, or reversibility.
Review design integrity
Examine relevant areas:
- conceptual integrity and fit with intended architecture;
- component/module/feature ownership, cohesion, coupling, and dependency direction;
- data ownership, source of truth, schemas, and state transitions;
- interface/API contracts and compatibility;
- failure/recovery boundaries;
- migration, rollout, rollback, and reversibility;
- observability and operability requirements;
- security/trust boundaries;
- scalability and resource/cost implications;
- testability and deterministic verification;
- source/generated/test placement and authorized structural boundaries.
For implemented changes, compare the actual diff/structure with the approved design and task. Look for dependency-direction violations, orphan files, generic dumping grounds, unauthorized top-level/shared areas, product/vision drift, or abstractions introduced beyond current evidence.
File naming and physical layout must follow target language/framework/project conventions. The invariant is intentional ownership, not one cross-language directory recipe.
For each concern, state affected authority/quality attribute, evidence, consequence, and a simpler/safer alternative when one exists.
Multiple perspectives
Choose only relevant lenses: product/user, architecture, implementation, operations, security, performance, cost, maintainability, testing, migration/backward compatibility. Do not mechanically run every lens.
Prefer explicit trade-offs over universal rules. Record irreversible decisions more carefully than reversible ones. Do not reward services, layers, factories, registries, extension points, shared modules, or other scale structure without current evidence.
Boundaries
This skill judges quality/integrity of specified or implemented design. Use gap-analysis for missing decisions/states, security-review for malicious/trust-boundary analysis, reliability for production failure/recovery, and simplicity for concentrated accidental-complexity review.
Do not implement the reviewed change or rewrite project vision because current code drifted from it.
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
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.

