doraval

Use doraval to validate, measure drift, and judge skills and plugins. Use when authoring or reviewing context engineering artifacts for AI coding agents (works for Codex too).

Quality

86%

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

86%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 is short, well-structured, and action-oriented with executable commands and a sequenced test path. Minor marketing fluff and a menu-style command list keep it just short of maximum on conciseness and workflow clarity.

Suggestions

Trim the marketing intro ('Scale your AI context...') and the self-referential demo sentence to tighten token efficiency.

Reframe the command list as an ordered workflow (e.g., validate -> drift -> judge) with an explicit validation feedback loop rather than a flat menu of options.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-focused, but the marketing-style intro ('Scale your AI context... Make your next context work...') and the meta sentence about being a self-referential example are minor padding that could be trimmed.	4 / 5
Actionability	Provides four copy-paste-ready, executable commands (validate, skill validate, skill drift, skill judge) plus a concrete numbered test sequence, covering the common cases.	5 / 5
Workflow Clarity	The Codex test path is a clear numbered sequence and 'Always run doraval validate before sharing or publishing' acts as a checkpoint, but the main command list is a menu of options rather than an ordered workflow with explicit validation feedback loops.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed, organized into clear sections (intro, command list, guardrail, test steps) per the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

87%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 cleanly states what doraval does and when to use it, with concrete actions and a distinct niche. It is slightly shy of maximum specificity and trigger-term breadth.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions ('validate, measure drift, and judge skills and plugins') over a named domain, with only minor coverage gaps; not quite the comprehensive list of a 5.	4 / 5
Completeness	Explicitly answers both 'what' ('validate, measure drift, and judge skills and plugins') and 'when' ('Use when authoring or reviewing context engineering artifacts for AI coding agents (works for Codex too)') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage including 'validate', 'drift', 'judge', 'skills and plugins', 'authoring or reviewing', 'context engineering artifacts', and 'AI coding agents'; a few more natural synonyms would reach 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (context-engineering validation/judgment for AI coding agents) with distinct triggers, minimizing overlap with unrelated skills.	5 / 5
	Total	18 / 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: saif-shines/doraval
Path: test/fixtures/examples/my-codex-plugin/skills/doraval/SKILL.md
Commit: 0fa2092

Reviewed: 1 day 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.