lint-and-validate

Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers on keywords: lint, format, check, validate, types, static analysis.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/lint-and-validate/SKILL.md

The canonical home for this skill is jbvc/lint-and-validate

Quality

Content

75%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 compact, well-structured, highly actionable skill body with real script references and a feedback loop. Its weaknesses are minor: a redundant strict-rule restatement, generic path placeholders, and a broken in-document reference to a 'FINAL AUDIT REPORT' section that is never defined.

Suggestions

Remove the broken 'FINAL AUDIT REPORT' reference in The Quality Loop (step 3) or add the section it points to, since no such section exists in the body.

De-duplicate the mandatory/no-commit-without-passing rule: keep either the opening MANDATORY blockquote or the closing Strict Rule, not both.

Make the generic loop's audit command ecosystem-aware (show the Python equivalent alongside 'npm run lint && npx tsc --noEmit') or label it as the Node path.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with tables and short command lists, but the rule is stated redundantly (the opening MANDATORY blockquote, the 'Fix & Repeat NOT allowed' line, and the closing 'Strict Rule' all repeat the same prohibition), which is minor padding that could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready commands for both Node and Python (npm run lint, npx tsc --noEmit, ruff check, bandit, mypy) plus real script invocations, but uses generic 'path'/'project_path' placeholders and references a 'FINAL AUDIT REPORT' section that does not exist, leaving minor gaps.	4 / 5
Workflow Clarity	The 'Quality Loop' gives a clear 4-step sequence with an explicit fix-and-repeat feedback loop, but step 3 points to a nonexistent 'FINAL AUDIT REPORT' section and step 2's audit command is Node-only, so it falls just short of the fully validated level 5.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a Scripts table pointing to real one-level-deep bundle files (lint_runner.py, type_coverage.py), but the dangling 'FINAL AUDIT REPORT' reference is a minor navigation/organization gap that keeps it just below the clean level 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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 strong description that clearly answers what, when, and how it triggers, with good natural keyword coverage. Its main weakness is mild abstraction in the 'what' ('quality control') and a few overly broad trigger terms that create minor overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('quality control, linting, and static analysis') with a couple of concrete action categories, but 'quality control' is abstract and no specific tool-level actions (e.g. run eslint, type-check) are listed, so it stops at '1-2 concrete actions, not comprehensive'.	3 / 5
Completeness	It explicitly states what ('Automatic quality control, linting, and static analysis procedures'), when ('Use after every code modification'), and concrete trigger phrases, matching the anchor that answers both what AND when with concrete triggers.	5 / 5
Trigger Term Quality	The explicit 'Triggers on keywords: lint, format, check, validate, types, static analysis' gives good natural-term coverage users would actually say, but synonyms/variations (e.g. 'type checking', 'type check') are missing, so it is not the comprehensive level 5.	4 / 5
Distinctiveness Conflict Risk	lint/static-analysis/types give it a clear niche, but broad terms like 'check', 'validate', and 'format' create minor overlap risk with closely related code-quality skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/lint-and-validate/SKILL.md
Commit: 211561c

Reviewed: 8 days 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.