CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review-web

Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, token-efficient review skill with excellent progressive disclosure and a clean 5-dimension framework. It loses points on actionability and workflow clarity because its guidance is largely descriptive checklists rather than executable procedures with explicit validation gates.

Suggestions

Add at least one concrete, copy-paste-ready command or code snippet to the workflow (e.g. the exact git/incident commands to run) to lift actionability from descriptive to executable.

Insert explicit validation checkpoints and a fix→retry feedback loop in the debugging workflow (e.g. 'If reproduction fails, re-check logs before concluding environment issue') to meet the rubric's feedback-loop anchor.

Mark the depth-selection step with a concrete decision rule (PR size thresholds or change-type criteria) so 'Pick the depth' is unambiguous rather than judgment-based.

DimensionReasoningScore

Conciseness

Lean bullet-based prose that assumes Claude's competence; it avoids explaining basic concepts (what an N+1 query is, what CSRF is) and every section earns its tokens.

3 / 3

Actionability

Guidance is concrete at the checklist level ('No literal 60000 in code. Use named constants', 'git log --oneline') but mostly descriptive rather than copy-paste executable; few runnable commands or code snippets compared to the rubric's anchor.

2 / 3

Workflow Clarity

Both the review and debugging workflows are numbered and sequenced, but validation checkpoints and explicit fix→retry feedback loops are implicit rather than gated — e.g. the debugging flow only reaches 'Verify in production' at step 8 with no re-validate-on-failure loop.

2 / 3

Progressive Disclosure

SKILL.md is a focused overview with clearly signaled one-level-deep references to review-template.md, nextjs-patterns.md, and wordpress-headless-patterns.md, all of which exist as real bundle files.

3 / 3

Total

10

/

12

Passed

Description

100%

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 is specific, trigger-rich, and clearly delineates both capability and activation conditions, with third-person voice throughout. It is among the strongest examples on this rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns' — rather than vague abstractions.

3 / 3

Completeness

Explicitly answers both what (review/debug web code across several domains) and when, via a 'Use this skill whenever...' clause followed by enumerated trigger phrases.

3 / 3

Trigger Term Quality

Dense natural-language triggers a user would actually say — 'review my code', 'debug', 'build error', 'broken', 'not working', 'PR review', 'audit code' — plus concrete failure signals like '4xx or 5xx errors' and 'deploy failures'.

3 / 3

Distinctiveness Conflict Risk

Scoped to web application code review with distinctive triggers, and the body's 'When NOT to use' section disambiguates adjacent skills, so conflict risk is low.

3 / 3

Total

12

/

12

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
rampstackco/claude-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.