code-review

Architectural code review — coding standards, SOLID, testability, performance concerns.

Quality

75%

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/code-review/SKILL.md

Quality

Content

81%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.

The body is an exemplary operational workflow: fully executable commands, explicit validation gates, verification of subagent findings, and an unambiguous verdict hierarchy. Its weaknesses are token efficiency — three long war-story justifications inflate the budget — and the absence of any summary/overview section at the top of a long single-file skill.

Suggestions

Compress the three extended rationale anecdotes (false clean passes, agent fabrication story, v1.0 null migration) into one-line 'Why:' notes or move them to a reference file — they cost roughly 50 lines of context on every invocation.

Add a 3-5 line overview at the top summarizing the nine phases and the verdict scale, so the skill's shape is visible before reading 280 lines.

State upfront that no bundle files ship with this skill (or add a short pointers section listing the runtime inputs it reads: project.yaml, technical-preferences.md, automation-modes.md) to aid navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational checklists and commands, but it carries several extended rationale blocks — 'the failure mode this prevents is specific and has been observed in practice' (false clean passes anecdote), the 'Why this is mandatory' agent-fabrication story, and the v1.0 migration narrative for null specialists — roughly 50 of ~280 lines of justification that could be compressed to one-line notes. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') better than anchor 4's 'minor instances of over-explanation'.	3 / 5
Actionability	Guidance is fully executable throughout: exact tool invocations ('Grep pattern="^## " path="[adr-file]" output_mode="content" -n', 'git log --oneline -- [file]'), concrete specialist routing by file extension, a copy-paste output template, explicit deviation classifications, and literal AskUserQuestion prompt text with enumerated options. This matches anchor 5 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	Nine phases are clearly sequenced with explicit validation checkpoints: the FOUND/ABSENT input check before any report, bounded ADR reads with fallbacks, verify-before-reporting of specialist findings (VERIFIED vs UNVERIFIED confidence labels), a first-match-wins verdict ordering, and fix-then-rerun next-step options. This matches anchor 5 ('clear sequence with explicit validation steps; feedback loops for error recovery; checklists for complex processes'); the skill is read-only, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and all content is operational guidance that legitimately belongs in SKILL.md, organized under clear '## Phase N' headers for easy navigation. It stops short of anchor 5 because the ~280-line single file has no top-level overview, and the extended failure-mode anecdotes are natural candidates for a separate reference file — 'minor organization gaps' per anchor 4.	4 / 5
	Total	17 / 20 Passed

Description

61%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 concise and names a coherent niche with recognizable keywords, but it omits any 'when to use' trigger guidance, which caps completeness and weakens its ability to fire at the right moment. Adding an explicit trigger clause with natural user phrasings would lift it substantially.

Suggestions

Append a 'Use when...' clause with natural trigger phrases, e.g. 'Use when the user asks to review code, an architecture, or a story implementation, or mentions coding standards, SOLID, or testability.'

Add one or two concrete actions to complement the topic list (e.g. 'spawns engine specialists in parallel, checks ADR compliance, and returns an APPROVED / CHANGES REQUIRED verdict') so the 'what' is more actionable.

Include a common synonym or phrasing users would actually say ('review my code', 'PR review', 'code quality check') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Architectural code review') and enumerates focus areas ('coding standards, SOLID, testability, performance concerns'), but these are review topics rather than concrete actions like 'extracts text, fills forms'. It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' and falls short of level 4, which expects several specific actions with only minor gaps.	3 / 5
Completeness	It clearly answers 'what' (architectural code review covering standards, SOLID, testability, performance) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3. This matches anchor 3 ('has a clear what but when is missing or only weakly implied') and is not level 4, which requires both what and when.	3 / 5
Trigger Term Quality	'code review', 'coding standards', 'SOLID', 'testability', and 'performance' are terms users would naturally say when needing this skill. A few common variations are missing ('review my code', 'PR review', 'code quality', 'architecture review'), matching anchor 4 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of level 5.	4 / 5
Distinctiveness Conflict Risk	The 'Architectural' framing plus SOLID/testability focus carves a recognizable niche that is mostly distinct from adjacent skills, with only minor overlap risk against general code-review or security-review skills. It is not level 5 because the description alone doesn't provide trigger phrases that would reliably disambiguate it from a generic code review request.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/code-review/SKILL.md
Commit: b21fa0f

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.