CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review-excellence

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Quality

77%

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 ./skills/code-review-excellence/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 impressively concise and well-sectioned, with a useful output format spec. However, its only progressive-disclosure reference points to a nonexistent file, and the core review guidance stays generic, which limits actionability and workflow clarity.

Suggestions

Create `resources/implementation-playbook.md` (or remove both references to it) so the deferred checklists actually resolve — currently the promised detail is unreachable.

Add concrete review guidance inline: definitions of each severity tier (blocking/important/minor) and an example of well-phrased actionable feedback with rationale.

Make the workflow explicit and self-verifying, e.g., a numbered sequence ending with 're-confirm each finding against the actual diff before reporting' as a validation checkpoint.

DimensionReasoningScore

Conciseness

The body is a lean set of directive bullets (~35 lines) with zero padding and no explanation of concepts Claude already knows; every token earns its place. It matches the 'lean and efficient' anchor exactly.

5 / 5

Actionability

Some concrete guidance exists (e.g., "Issues grouped by severity (blocking, important, minor)"), but the review instructions themselves are generic directives and the detailed checklists are deferred to a file that does not exist, leaving key details missing. This fits 'some concrete guidance but incomplete' rather than the mostly-executable anchor.

3 / 5

Workflow Clarity

A rough sequence is implied (read context first, then review, then give feedback in the specified format), but steps are not explicitly sequenced and there are no verification checkpoints such as re-confirming findings against the code before reporting. This matches 'steps listed but validation gaps' better than the clear-sequence-with-checkpoints anchor.

3 / 5

Progressive Disclosure

The sole external reference, `resources/implementation-playbook.md`, is invoked twice ("If detailed checklists are required, open resources/implementation-playbook.md") but does not exist in the bundle — no references/, scripts/, assets/, or resources/ directory is present. The deferred content is unreachable, so the disclosure structure is broken rather than merely under-organized; it does not merit a 3 since the one reference that exists in text fails to resolve.

2 / 5

Total

13

/

20

Passed

Description

83%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 description that clearly states capabilities and explicit usage triggers in natural language. Trigger coverage is good but could add common synonyms like "PR" and "diff".

DimensionReasoningScore

Specificity

The description lists several specific actions ("provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale") with only minor gaps. It falls short of a 5 because the actions are softer and more abstract than comprehensively concrete ones, and well above a 3 since more than two concrete actions are named.

4 / 5

Completeness

It explicitly answers both what ("provide constructive feedback, catch bugs early, and foster knowledge sharing") and when ("Use when reviewing pull requests, establishing review standards, or mentoring developers") with concrete trigger phrases, matching the top anchor. The when-clause is explicit and specific, so it does not fit the score-4 anchor where 'when' could be more explicit.

5 / 5

Trigger Term Quality

Natural terms users would actually say are present: "code review", "reviewing pull requests", "review standards", "mentoring developers". A few common variations are missing (e.g., "PR", "diff", "review feedback"), keeping it below comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The mentoring and review-standards angles give it a mostly distinct niche within code review, but "code review" broadly overlaps with closely related skills (security review, general code review workflows), so minor overlap risk remains.

4 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rmyndharis/antigravity-skills

Path

skills/code-review-excellence/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.