Name: lint-and-validate
Rating: 47.2 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

lint-and-validate

MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.

Quality

50%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/lint-and-validate/SKILL.md

The canonical home for this skill is lint-and-validate in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

67%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 actionable, executable per-ecosystem commands and a sequenced quality loop with a feedback checkpoint, and correctly references real bundle scripts. It is weakened by redundant mandate restatements, a non-existent "FINAL AUDIT REPORT" reference, and a vacuous "When to Use" section.

Suggestions

Remove the redundant blockquote/Strict Rule restatements of the frontmatter mandate and replace the vacuous "When to Use" line with concrete trigger conditions.

Either add a real "FINAL AUDIT REPORT" section or remove the reference to it from the Quality Loop.

Link the script names in the Scripts table to the actual files (e.g. `[lint_runner.py](scripts/lint_runner.py)`) so the one-level-deep reference is explicitly navigable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete command lists, but the blockquote restates the frontmatter, the "Strict Rule" and "Fix & Repeat" lines restate the same no-errors mandate, and the "When to Use" section ("applicable to execute the workflow or actions described in the overview") is vague filler.	3 / 5
Actionability	Concrete executable commands are given per ecosystem (`npm run lint`, `npx tsc --noEmit`, `ruff check`, `bandit`, `mypy`) plus a scripts table referencing real files; minor gaps are the placeholder `"path"`/`<project_path>` arguments requiring substitution.	4 / 5
Workflow Clarity	The Quality Loop is a clear sequence with an explicit validation checkpoint (Run Audit, Analyze Report) and a fix-and-repeat feedback loop, plus an Error Handling section; held at 4 because "Analyze Report: Check the FINAL AUDIT REPORT section" references a section that does not exist in the skill.	4 / 5
Progressive Disclosure	Content is well organized into labeled sections with a Scripts table pointing one level deep to real bundle files (lint_runner.py, type_coverage.py) with their commands; not a 5 because there are no in-body links to the referenced files and the overview is thin.	4 / 5
	Total	15 / 20 Passed

Description

33%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 is a forceful mandate rather than a capability statement: it conveys urgency but uses generic language ("appropriate validation tools") with no concrete tools and weak natural trigger terms. It states a when-condition but lacks an explicit "Use when..." clause and risks overlapping many related skills.

Suggestions

Name concrete actions and tools, e.g. "Runs lint, typecheck, and security audits (eslint, tsc, ruff, bandit) and fails the task until the code is clean."

Add an explicit trigger clause: "Use when finishing a code change, before committing, or when the user asks to lint/typecheck/validate code."

Rewrite in third person and drop the ALL-CAPS mandate tone so the description reads as a capability, not an instruction.

Dimension	Reasoning	Score
Specificity	"Run appropriate validation tools" names the domain (validation) but the action is generic with no concrete tools named; the imperative "Do not finish a task" is second-person address, so the base-3 "names domain and a concrete action" is penalized by one.	2 / 5
Completeness	A clear "what" (run validation tools) and a "when" ("after EVERY code change") are present, but the "what" is vague ("appropriate validation tools") and there is no explicit "Use when..." trigger clause, so it caps at 3 rather than 4.	3 / 5
Trigger Term Quality	Only generic phrases ("validation tools", "code change", "error-free") appear; the natural terms users say ("lint", "typecheck", "run tests") are missing, matching the "one or two generic keywords; missing natural phrases" anchor.	2 / 5
Distinctiveness Conflict Risk	"Run appropriate validation tools after EVERY code change" is very broad and would overlap with testing, CI, and general quality-assurance skills, matching the "very broad; high overlap risk" anchor.	2 / 5
	Total	9 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/lint-and-validate/SKILL.md
Commit: 57c135b

Reviewed: 4 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.