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.

50

Quality

55%

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-claude/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

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 a tidy, well-structured instruction-only skill with clear 'use when'/'do not use when' framing and a concrete output format, but it leans on abstract guidance and a missing reference file instead of executable detail.

Suggestions

Add concrete inline guidance such as example severity-tagged feedback or a short review checklist, since the deferred playbook does not currently exist.

Add a validation checkpoint to the workflow, e.g. 'Confirm each blocking issue against the relevant tests before reporting it.'

Create `resources/implementation-playbook.md` (or correct the path to match the bundle directory) so the referenced detailed material is reachable.

DimensionReasoningScore

Conciseness

The body is lean bullet-point guidance that assumes Claude's competence; the only trimmable part is the opening sentence that duplicates the frontmatter description.

4 / 5

Actionability

It offers high-level hints ('Review for correctness, security, performance, and maintainability', 'Provide actionable feedback with severity and rationale') and a concrete output format, but no specific checklist, examples, or steps to execute.

3 / 5

Workflow Clarity

A rough sequence is present ('Read context, requirements, and test signals first' then review then feedback), but there are no validation checkpoints or feedback loops before reporting findings.

3 / 5

Progressive Disclosure

Sections are well organized and the detailed-checklist material is split out behind a one-level reference, but the referenced `resources/implementation-playbook.md` does not exist, leaving a broken navigation link.

4 / 5

Total

14

/

20

Passed

Description

48%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 frames code review as a clear, distinct domain but stays at an abstract, mission-statement level, naming the domain without concrete actions and omitting any explicit trigger ('Use when') clause.

Suggestions

Replace abstract verbs with concrete actions, e.g. 'Review pull requests, identify correctness/security/performance issues, and suggest fixes with severity and rationale.'

Add an explicit trigger clause: 'Use when reviewing pull requests or code changes, or when asked for a code review.'

Include natural synonyms users say — 'pull request', 'PR', 'diff review' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

It names the domain ('code reviews') but the stated actions are generic verbs ('constructive feedback, systematic analysis, collaborative improvement') rather than concrete operations like 'review pull requests, identify bugs, suggest fixes'.

2 / 5

Completeness

It gives a clear 'what' (transform code reviews into knowledge sharing) but has no explicit 'when / Use when' trigger clause, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

'code reviews' is a natural keyword a user might say, but common synonyms such as 'pull request', 'PR', and 'diff' are missing.

3 / 5

Distinctiveness Conflict Risk

'Code reviews' is a recognizable niche that is mostly distinct from other skills, with only minor overlap risk against general mentoring or feedback skills.

4 / 5

Total

12

/

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.