CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review-excellence

Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement.

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/code-review-excellence/SKILL.md

The canonical home for this skill is code-review-excellence in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 lean, well-structured, and easy to navigate with clear use/don't-use triggers and a defined output format. Its main weakness is actionability: the detailed review methodology is deferred to an external playbook that is not present in the bundle.

Suggestions

Inline a short severity rubric (blocking/important/minor criteria) so the skill is self-contained even without the playbook.

Fix the broken reference: create `resources/implementation-playbook.md` or remove the pointer to avoid dead navigation.

Add one concrete example of well-formed review feedback so the output format is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean, well-sectioned, and assumes Claude's competence without explaining basic concepts; the only redundancy is the opening tagline duplicating the frontmatter description, fitting the score-4 anchor 'Efficient; minor instances...that could be trimmed'.

4 / 5

Actionability

There is a usable procedure (read context, review across four named dimensions, give severity-grouped feedback, defer to playbook) plus a defined output format, but the how-to for assessing each dimension and severity criteria is absent and deferred to a playbook that does not exist, matching the score-3 anchor of concrete but incomplete guidance missing key details.

3 / 5

Workflow Clarity

The Instructions form a clear logical sequence (read signals → review → feedback → clarify → escalate to playbook) with a simple-skill structure; review is not a destructive/batch op so the validation cap does not apply, fitting the score-4 anchor 'Clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

Sections are well-organized with a dedicated Resources section signaling a one-level-deep reference, but that referenced file `resources/implementation-playbook.md` does not exist in the bundle, a navigation gap that keeps it from 5 per the score-4 anchor 'Good structure; references mostly clear; minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

45%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 clearly identifies the code-review domain but is written in aspirational, outcome-oriented language rather than concrete actions, and it omits any explicit 'Use when...' trigger guidance. Trigger terms are present but thin and lack common synonyms.

Suggestions

Lead with concrete actions, e.g. 'Review pull requests, assess correctness/security/performance, and post severity-grouped feedback.'

Append an explicit trigger clause: 'Use when reviewing pull requests, code changes, or diffs, or when the user asks for a code review.'

Add natural synonyms users say — 'pull requests', 'PRs', 'review my code', 'diff' — alongside 'code reviews'.

DimensionReasoningScore

Specificity

The description names the domain ('code reviews') but its 'actions' are abstract outcome phrases — 'transform...from gatekeeping to knowledge sharing', 'constructive feedback', 'systematic analysis', 'collaborative improvement' — rather than concrete operations, matching the score-2 anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

It states a 'what' (transform code reviews) but offers no 'when'/Use-when clause, and per the judging guideline a missing 'Use when...' clause caps completeness at 3; the 'what' is also abstract rather than concrete, keeping it from 4.

3 / 5

Trigger Term Quality

'code reviews' is a natural user term but the surrounding language ('gatekeeping', 'knowledge sharing') is not what users say, and common synonyms like 'pull requests', 'PR', or 'review my code' are missing, fitting the score-3 anchor of relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

'code reviews' identifies a niche, but the framing around feedback philosophy and collaboration could overlap with generic mentoring or communication skills, matching the score-3 anchor 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

11

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.