CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

local-code-reviewer

Run and analyze the repository's automated code review checks (Prettier, TypeScript type-check, Vitest, and Regex Audits) using `pnpm run code-review`.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A tight, well-structured, single-command skill: the exact command is given, output analysis is broken down per check, and a fix-rerun loop closes the workflow. The only trimmable fat is mild duplication between the intro and the When to Use section and slight over-explanation of what each tool checks.

DimensionReasoningScore

Conciseness

The body is lean (~24 lines) with a copy-paste command and tight step list, but contains minor over-explanation: "Check if any changed files failed formatting" / "Check for compilation or static type errors" restate what Prettier and tsc already mean to Claude, and the opening paragraph duplicates the "When to Use" bullets. Not a 5 because those small redundancies could be trimmed; well above a 3 since nothing is padded or tutorial-like.

4 / 5

Actionability

The guidance is fully executable: the exact command `pnpm run code-review` in a bash block, per-check analysis directions (formatting failures, type errors, test results, regex violations like console.logs and hardcoded secrets), and a fix-and-rerun loop. For a single-command skill this is copy-paste ready and covers the common case completely.

5 / 5

Workflow Clarity

This is a simple, single-purpose skill where the action is unambiguous: run → analyze per-check output → fix and re-run until all checks pass → report. The feedback loop ("re-run the code review until all checks pass successfully") is an explicit validation checkpoint, and the operation is neither destructive nor batch, so no cap applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundle exists, and none is warranted). Per the rubric's simple-skill guideline, well-organized sections (When to Use, Steps) with a clear overview earn a 5 here.

5 / 5

Total

19

/

20

Passed

Description

66%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 specific, third-person description with a concrete command and named tools, but it omits any explicit "when to use" trigger guidance, which caps its completeness. Adding a use-when clause and a few natural synonyms (lint, formatting, tests) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to run code review checks, lint, typecheck, or run tests before committing."

Include natural synonym terms users would say — "lint", "formatting check", "run the tests", "quality gates" — alongside the tool names to broaden trigger coverage.

State what happens with the results (e.g., "reports failures and fixes them") to round out the capability coverage.

DimensionReasoningScore

Specificity

The description lists several concrete items — "Run and analyze the repository's automated code review checks (Prettier, TypeScript type-check, Vitest, and Regex Audits) using `pnpm run code-review`" — naming four specific checks and the exact command. It stops short of anchor 5 because the actions themselves are only "run" and "analyze" without enumerating what is done with the results, leaving minor coverage gaps.

4 / 5

Completeness

The "what" is clear (run and analyze four named code review checks via a specific command), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. It is not a 4 because the "when" is entirely absent rather than present-but-imprecise.

3 / 5

Trigger Term Quality

Natural terms like "code review", "Prettier", "TypeScript", "Vitest", and "pnpm" are terms users would plausibly say when needing this skill. A few common variations are missing (e.g., "lint", "formatting", "run tests", "quality checks"), which keeps it below anchor 5's comprehensive synonym coverage but above anchor 3's merely-some-relevant-keywords level.

4 / 5

Distinctiveness Conflict Risk

The description is tied to this repository's specific toolchain (Prettier, TypeScript, Vitest, pnpm, regex audits), giving it a mostly distinct niche with only minor overlap risk against generic code-review or testing skills. It is not a 5 because "automated code review checks" is still a broadly contested trigger phrase shared with general review workflows.

4 / 5

Total

15

/

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

BigSimmo/Communication

Path

.agents/skills/local-code-reviewer/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.