CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

architecture-review

Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/architecture-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

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

This is a well-structured orchestrator skill: the SKILL.md body routes nine clearly sequenced phases to real one-level-deep reference files, and it pairs them with an explicit error-recovery validation gate and concrete collaborative protocols. The only notable inefficiency is the verbatim repetition of the compaction/re-read instruction across every phase section, and the body itself contains no sample outputs.

DimensionReasoningScore

Conciseness

The body explains nothing Claude already knows and its protocol rules are tight, but "Read it again if the conversation was compacted or resumed during this phase" and "this phase's steps are in that file, not here" are repeated verbatim across all nine phase sections. That repetition could be stated once, so not every token earns its place.

4 / 5

Actionability

Guidance is concrete throughout: exact per-phase reference paths, precise argument-mode semantics, a scripted ambiguity question ("Is [X] a technical requirement or a design preference?"), explicit AskUserQuestion option structure, a named output file, and a defined retry scope. No sample matrix or report fragment appears inline, leaving a minor gap to the fully-executable 5 anchor.

4 / 5

Workflow Clarity

Nine phases are clearly sequenced with unambiguous per-phase directives, and the Error Recovery Protocol provides explicit validation ("a named artifact that is not on disk is a failed phase, however fluent the response reads"), feedback loops (retry scope = fewer GDDs / single-system), and draft-before-approval checkpoints — matching the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

The body is a pure routing document: all nine phase files plus lens-engine.md exist in references/, are clearly signaled with explicit read-now directives, and are one level deep (internal cross-references are sibling pointers, not redirect chains). This matches the clear-overview anchor exactly.

5 / 5

Total

18

/

20

Passed

Description

66%Weight 40%Scale 1-5

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, third-person, and distinct within its game-architecture niche, listing several concrete capabilities plus an explicit verdict vocabulary. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and weakens discoverability. Adding trigger guidance and the phrase "architecture review" would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to review game architecture, check ADR coverage, or map GDD requirements to decisions" — its absence caps completeness at 3.

Include the natural phrase "architecture review" and synonyms like "requirements coverage" or "decision conflicts" to broaden trigger-term coverage.

Mention the review report artifact (e.g. docs/architecture/architecture-review-*.md) or the mode variants (coverage, consistency, rtm) to round out capability coverage.

DimensionReasoningScore

Specificity

"Traceability matrix mapping GDD requirements to ADRs" and "Finds gaps, cross-ADR conflicts, engine compatibility" name several concrete actions plus an explicit verdict scale (PASS/CONCERNS/NOT ASSESSED/FAIL). Minor gaps remain — architecture-doc coverage and the coverage/consistency/rtm/single-gdd modes are unmentioned — so it falls short of the comprehensive 5 anchor.

4 / 5

Completeness

The "what" is clearly and concretely stated, but the description contains no "Use when..." clause or any equivalent trigger guidance. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

In-domain keywords like "traceability matrix", "GDD requirements", "ADRs", and "engine compatibility" match what a user in this domain would naturally say. The phrase "architecture review" itself and common variations such as "requirements coverage" or "decision conflicts" are missing, keeping it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The GDD + ADR + engine-compatibility combination pins the skill to game-development architecture review, a clear niche. "Traceability matrix" and "gaps" are mildly generic and could overlap with a general ADR-management or review skill, so minimal-conflict 5 is not fully earned.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

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

Reviewed

Table of Contents

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.