architecture-review

Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/architecture-review/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is verbose for a single SKILL.md and keeps reusable output templates inline instead of factoring them into reference files.

Suggestions

Move the long reusable output templates (RTM file format, traceability index format, reflexion log, session-state block) into reference files (e.g. references/output-templates.md) and link to them one level deep from the relevant phases.

Trim repeated report-format blocks and the restated collaborative-protocol rules to reduce the body toward a lean overview plus pointers.

Dimension	Reasoning	Score
Conciseness	The 640-line body is mostly efficient with terse command/table/output templates, but it restates several long output-format blocks (report, RTM, traceability index, reflexion log, session-state) inline and could be tightened overall.	2 / 3
Actionability	Provides fully executable guidance — exact Grep/Glob invocations, exact AskUserQuestion option strings, exact status enums, file paths, and verdict criteria — copy-paste ready throughout.	3 / 3
Workflow Clarity	Phases 1–9 are explicitly sequenced with numbered steps, approval/AskUserQuestion gates before writes, draft-before-approval feedback loops, and explicit 'only proceed when...' validation checkpoints.	3 / 3
Progressive Disclosure	There are no bundle files and the content is a single 640-line monolith; the long reusable output-format templates (RTM, traceability index, reflexion log) are inlined rather than split into clearly-signaled one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-differentiated with strong trigger-term coverage, but lacks an explicit 'Use when...' trigger clause, which is the main thing holding completeness below the top level.

Suggestions

Add an explicit 'Use when...' clause naming the trigger conditions (e.g., 'Use when validating architecture coverage against GDDs, before the pre-production gate, or when ADRs are added or revised').

Keep the /design-review analogy but pair it with a concrete natural-language trigger so users discover it via intent rather than sibling-skill knowledge.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — validates completeness/consistency, builds a traceability matrix, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility, and produces a PASS/CONCERNS/FAIL verdict — matching the level-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers 'what does this do', but 'when should Claude use it' is only implied via the /design-review analog rather than an explicit 'Use when...' clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Covers natural vocabulary users would say — architecture, GDDs, traceability matrix, coverage gaps, cross-ADR conflicts, engine compatibility — plus the '/design-review' analog as a recognizable sibling reference.	3 / 3
Distinctiveness Conflict Risk	The architecture-vs-GDD traceability and ADR-conflict niche is clearly scoped with distinct triggers and an explicit sibling-skill analogy, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (666 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/architecture-review/SKILL.md
Commit: 984023d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.