CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

76

Quality

94%

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

The canonical home for this skill is code-review in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-structured, actionable process skill with a clear sequenced workflow and an explicit early validation checkpoint. It is mostly lean; the main opportunity is the long inline smell catalog, which is justified but could be split into a reference file.

Suggestions

Consider moving the 12-item smell baseline into a separate reference file (e.g. references/smell-baseline.md) and pasting/loading it for the sub-agent, which would tighten SKILL.md and improve progressive_disclosure.

The 'Why two axes' section is useful rationale but could be condensed to one or two lines since the description and step 5 already convey the separation.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — no padding about git, diffs, or what code smells are conceptually. The 12-item smell catalog is necessarily detailed because it must be pasted verbatim into a sub-agent, though that inline block and the 'Why two axes' rationale could be trimmed slightly.

4 / 5

Actionability

Provides concrete executable commands (`git diff <fixed-point>...HEAD`, `git log <fixed-point>..HEAD --oneline`, `git rev-parse <fixed-point>`) and copy-pasteable sub-agent prompt briefs with explicit word limits and per-finding instructions.

5 / 5

Workflow Clarity

A clear 5-step sequence (pin fixed point → identify spec → identify standards → spawn sub-agents → aggregate) with an explicit validation checkpoint in step 1 ('confirm the fixed point resolves... A bad ref or empty diff should fail here, not inside two parallel sub-agents') and a defined fallback when the spec is missing.

5 / 5

Progressive Disclosure

Well-organized into headed sections with a clearly signaled one-level reference (docs/agents/issue-tracker.md) and no nested references. The inline 12-smell baseline is a long block that could arguably live in a separate file, though inlining is justified since it must be pasted to the sub-agent.

4 / 5

Total

18

/

20

Passed

Description

100%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.

A strong, third-person description that states concrete capabilities, gives explicit 'Use when' trigger guidance with natural phrasing, and carves out a distinct two-axis niche. It is concise yet complete.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Review the changes since a fixed point', a Standards axis (follow documented coding standards), a Spec axis (match the originating issue/spec), 'Runs both reviews in parallel sub-agents', 'reports them side by side' — covering the task comprehensively.

5 / 5

Completeness

Explicitly answers both what (two-axis review via parallel sub-agents reported side by side) and when (an explicit 'Use when...' clause with concrete trigger scenarios).

5 / 5

Trigger Term Quality

'Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X"' covers natural trigger phrases a user would actually say, including the quoted idiomatic 'review since X'.

5 / 5

Distinctiveness Conflict Risk

The two-axis Standards+Spec framing is a clear niche with distinct triggers ('review since X', PR/branch/WIP review) and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
The-Vibe-Company/companion
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.