ac-code-validator

Validate code quality and standards. Use when running linting, checking types, validating code style, or performing static analysis.

Quality

73%

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 ./skills/ac-code-validator/SKILL.md

Quality

Content

61%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 well-structured API-overview body whose code examples are accurate and executable against the bundled script. Its weaknesses are redundancy (duplicated intro/Purpose and tool mapping), an unstated validate-fix-revalidate workflow around the batch auto_fix operation, and a Configuration example that omits the config file location.

Suggestions

Delete the redundant "Purpose" section (it restates the opening line) and keep the language-tool mapping in one place — either the code-block comments or the Language Support table, not both.

State the workflow loop explicitly: run validate(), inspect result.checks and summary.auto_fixable, run auto_fix(), then re-validate before proceeding — auto_fix is a batch operation that currently has no re-validation checkpoint.

Document where the Configuration JSON lives (the script reads .claude/validator-config.json) so the configuration example is directly actionable.

Dimension	Reasoning	Score
Conciseness	The "Purpose" section restates the intro within six lines ("Validate code against quality standards..." vs "Performs static analysis, linting, type checking, and style validation to ensure code meets quality standards"), and the tool mapping appears twice (comments in the code blocks and again in the Language Support table). Not 2: there is no padding explaining concepts Claude already knows; not 4: the redundant Purpose section and duplicated tool mapping go beyond minor trimming.	3 / 5
Actionability	The Quick Start and every method call (validate, run_lint, run_type_check, check_formatting, run_security_scan, auto_fix) are real and executable, verified against scripts/code_validator.py. Not 5: the Configuration section shows a JSON config without stating where it lives (the script reads .claude/validator-config.json), and project_dir is an undefined placeholder, so examples are not fully self-sufficient.	4 / 5
Workflow Clarity	The intended loop (validate -> inspect result.checks/summary.auto_fixable -> auto_fix -> re-validate) is only implicit in the section ordering, never stated as a sequence with checkpoints. auto_fix is a batch file-modifying operation with no re-validation guidance, which caps workflow clarity at 3; not 2: the material is well organized and the usage sequence is readily derivable.	3 / 5
Progressive Disclosure	The single bundle reference (scripts/code_validator.py) is real, clearly signaled ("See scripts/code_validator.py for full implementation"), and one level deep, with implementation detail correctly deferred to it. Not 5: the API Reference pointer is terse and the 30-line Validation Result JSON is deep detail inlined rather than split; not 3: structure is good and references are neither buried nor nested.	4 / 5
	Total	14 / 20 Passed

Description

71%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 solid description with an explicit and concrete "Use when..." trigger clause covering linting, type checking, style validation, and static analysis. Its main weaknesses are a generic what-clause and overlap risk with code-review-type skills from the broad "code quality and standards" framing.

Suggestions

Replace the generic what-clause "Validate code quality and standards" with the skill's concrete capabilities, e.g. "Run linting, type checking, formatting checks, and security scans, with auto-fix for fixable issues."

Add missing natural trigger terms such as "formatting", "code style check", and tool names users actually mention (eslint, ruff, mypy, prettier).

Sharpen distinctiveness by framing the niche as pre-integration static analysis (e.g. "before committing or integrating code") to reduce overlap with code-review skills.

Dimension	Reasoning	Score
Specificity	"running linting, checking types, validating code style, or performing static analysis" lists several concrete actions, matching the anchor for minor coverage gaps. Not 5: the what-clause "Validate code quality and standards" is generic and omits capabilities like formatting, security scanning, and auto-fix; not 3: more than 1-2 concrete actions are explicitly named.	4 / 5
Completeness	Both parts are present: what ("Validate code quality and standards") and an explicit when with four concrete trigger phrases. Not 5: the anchor-5 example pairs concrete triggers with a what-clause enumerating multiple specific actions, whereas here the what is a single generic phrase; not 3: the when-clause is explicit and concrete, not missing or merely implied.	4 / 5
Trigger Term Quality	Terms like "linting", "checking types", "code style", and "static analysis" are natural phrases users would say. Not 5: misses common variations such as "formatting" and tool names users actually mention (eslint, ruff, mypy, prettier); not 3: the keywords present are natural and cover the main entry points rather than being generic.	4 / 5
Distinctiveness Conflict Risk	"Validate code quality and standards" is broad and would overlap with code-review, lint-configuration, or quality-gate skills, fitting "somewhat specific but could still overlap with similar skills". Not 4: the generic quality/standards framing creates more than minor overlap risk; not 2: the tool-oriented triggers (linting, type checking, static analysis) do narrow the niche.	3 / 5
	Total	15 / 20 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: fernandezbaptiste/Skrillz
Path: skills/ac-code-validator/SKILL.md
Commit: 93ed392

Reviewed: 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.