CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review-ai-ai-review

Review pull requests with source inspection, available static analysis and evidence-backed AI assistance; report actionable bugs, security risks and unverified coverage.

Quality

63%

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

Quality

Content

56%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 delivers strong, safety-aware operational guidance with well-sequenced workflows and explicit validation checkpoints, but its token efficiency is undermined by tautological boilerplate sections and re-explanations of well-known concepts. Splitting illustrative code and tool catalogs into reference files would improve both conciseness and progressive disclosure.

Suggestions

Delete or merge the tautological 'Use this skill when'/'Do not use this skill when'/'Instructions' boilerplate, which restates the description without adding guidance.

Remove or compress explanations of concepts Claude already knows (SOLID principles listing, anti-pattern names, scalability red-flag list) down to one-line reminders.

Move the illustrative code blocks (MicroserviceReviewChecklist, PerformanceReviewAgent, detect_n_plus_1_queries) into a one-level-deep reference file and keep only the actionable prompt templates inline.

DimensionReasoningScore

Conciseness

Several sections are pure padding ('Working on ai-powered code review specialist tasks or workflows', generic 'Clarify goals, constraints, and required inputs' bullets), and the body re-explains concepts Claude already knows (SOLID principles, Singleton/God-object anti-patterns, N+1 queries, the OWASP Top 10 enumeration). It is above 1 because much of the operational guidance is dense and skill-specific.

2 / 5

Actionability

The Initial Triage steps, the five-step Local Review Workflow, the worked SQL-injection finding draft, and concrete gotchas ('do not use jq `.[]` on independent JSON objects', placeholder-binding driver caveat) give mostly executable guidance. Pseudocode usage is explicitly justified ('Performance/AST snippets below are pseudocode requiring actual implementations'), keeping it below 5 only for the illustrative-only code blocks.

4 / 5

Workflow Clarity

The triage and local-review sequences are clearly ordered with explicit validation checkpoints ('Recheck the full head before posting', 'verify a hostile input remains a value in a local test', 'Do not run a command... until its required file exists'). It is below 5 because validate-fix-retry feedback loops are only partially explicit rather than spelled out as loops.

4 / 5

Progressive Disclosure

Section headers organize the single ~270-line file and the missing external prerequisite is honestly disclosed, but there is no bundle: illustrative code blocks (Go, JavaScript, TypeScript, Python snippets) and tool catalogs are inlined rather than split into one-level-deep reference files. It is above 2 because structure is present and navigation is possible.

3 / 5

Total

13

/

20

Passed

Description

55%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 states its capabilities concretely and in third person, but it omits any explicit 'Use when...' trigger guidance, which both caps completeness and leaves it undistinguished from generic code-review skills. Adding a trigger clause with natural terms like 'code review', 'PR', or 'diff' would address the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when asked to review a pull request, PR, code review, or diff.'

Include natural synonyms such as 'code review', 'PR', and 'diff' alongside 'pull requests' to improve trigger-term coverage.

Sharpen 'evidence-backed AI assistance' into a concrete action (e.g. 'route findings to an approved AI model for contextual analysis').

DimensionReasoningScore

Specificity

Phrases like 'Review pull requests with source inspection, available static analysis' and 'report actionable bugs, security risks and unverified coverage' list several concrete actions. It falls short of 5 because 'evidence-backed AI assistance' is abstract and the action coverage, while good, is not comprehensive.

4 / 5

Completeness

The 'what' is clear (review PRs via source inspection, static analysis, AI assistance; report bugs, security risks, unverified coverage), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'pull requests', 'bugs', and 'security risks' are terms users would naturally say, but the most common phrasing 'code review' and common synonyms/extensions (PR, diff, merge request) are absent. It is above 2 because the keywords present are natural rather than pure jargon.

3 / 5

Distinctiveness Conflict Risk

'Review pull requests' is somewhat specific to the code-review domain but would overlap with many similar code-review and PR-analysis skills. It is not 4 because no niche trigger distinguishes it from generic review skills.

3 / 5

Total

13

/

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.

Validation — 15 / 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

sickn33/agentic-awesome-skills

Path

skills/code-review-ai-ai-review/SKILL.md

Revision

8aa4123

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill