lint

Lint and format code. Auto-detects ESLint, Biome, Prettier, or language-native formatters and runs them with auto-fix. Reports remaining issues with actionable suggestions.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

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

A tight, highly actionable skill body with concrete per-tool commands and a clear step sequence, weakened only by the absence of a post-fix verification feedback loop for its batch/destructive operations. Progressive disclosure is clean for a self-contained file.

Suggestions

Add an explicit post-fix verification step (e.g. re-run the linter in check mode to confirm zero remaining issues) to satisfy the feedback-loop expectation for batch/destructive operations.

Trim justificatory sentences like 'Linting the wrong directory is a silent failure mode' to keep the already-lean body fully token-efficient.

Consider whether the long per-language detection catalog would benefit from a reference file, though keeping it inline is defensible.

Dimension	Reasoning	Score
Conciseness	Predominantly lean instructional content — compact tool/command tables with no lecturing on what linters are. A few justificatory phrases ('Linting the wrong directory is a silent failure mode') are minor padding but do not pull it to 2 given the high instruction-to-fluff ratio.	3 / 3
Actionability	Provides concrete executable commands per tool (e.g. 'npx @biomejs/biome check .', 'cargo fmt --check', 'ruff check .') plus a literal results template — copy-paste ready. Not below 3 because guidance is specific and complete.	3 / 3
Workflow Clarity	A clear 4-step sequence exists, but auto-fix/batch operations lack an explicit validate→retry feedback loop after applying fixes, which the rubric caps at 2 for batch/destructive work. Not 1 because steps are well sequenced; not 3 because no post-fix verification checkpoint is specified.	2 / 3
Progressive Disclosure	A single self-contained, well-organized file with clearly labeled sections and no nested references (no bundle files exist or are referenced). Not below 3 because organization is clean and content is appropriately inline for its scope.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, well-scoped description that names concrete actions and natural trigger tools, but it omits any explicit 'Use when...' guidance, capping completeness. Adding a trigger clause would round it out.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to lint, format, fix style issues, or clean up code.'

Include common conversational phrasings like 'run the linter' or 'format my code' alongside the tool names.

Reaffirm scope boundaries (e.g. 'Use for code, not prose') to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — auto-detecting ESLint/Biome/Prettier, running with auto-fix, and reporting issues — matching the 'lists multiple specific concrete actions' anchor. Not below 3 because it is not merely naming a domain; not above since 3 is the scale max.	3 / 3
Completeness	Clearly states what the skill does but lacks any explicit 'Use when...' trigger guidance, which the rubric caps at 2. Not 3 because the 'when to use' clause is entirely missing; not 1 because the 'what' is thoroughly covered.	2 / 3
Trigger Term Quality	Uses natural terms users actually say — 'Lint and format code' plus named tools ESLint, Biome, Prettier. It is not 2 because coverage is broad and tool names are genuine user triggers; 3 is the max.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (lint/format with specific tool detection) unlikely to overlap with unrelated skills. Not 2 because the tool-specific framing is distinct rather than generic.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gsd-build/gsd-2
Path: src/resources/skills/lint/SKILL.md
Commit: 33c00aa

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.