autoresearch

Stateful validator-gated research loop with native-hook persistence

Quality

75%

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/oh-my-codex/skills/autoresearch/SKILL.md

Quality

Content

100%

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

The content is strong across the board: lean and jargon-aware, concrete and actionable, with a clearly sequenced workflow backed by explicit validation gating and a feedback loop. It is well-organized as a self-contained overview with no need for bundle files.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining basic concepts; only minor deprecation redundancy between the intro and the migration note keeps it from being perfectly tight.	3 / 3
Actionability	Concrete state-file paths, exact validation-mode names, JSON artifact templates, and specific skill invocations give copy-paste-ready guidance for the contract.	3 / 3
Workflow Clarity	A numbered recommended flow is paired with explicit artifact-gated completion and an auto-nudge feedback loop that continues until validation passes, including error-recovery continuation.	3 / 3
Progressive Disclosure	No external references are needed and the document is organized into clear, well-signaled sections (boundary, use/don't-use, contract, flow, migration), which scores 3 for a self-contained skill.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 uniformly middling: it conveys a niche concept with some concrete mechanics but relies on jargon, omits any use-when trigger guidance, and lacks distinct verb-actions. It would benefit from a natural-language trigger clause.

Suggestions

Add an explicit 'Use when...' trigger clause naming phrases users would naturally say, e.g. 'Use when you need a research loop that keeps running until a validator approves the output.'

Replace or supplement jargon ('validator-gated', 'native-hook persistence') with natural trigger terms such as 'keep researching until the result passes validation'.

Lead with concrete action verbs (e.g. 'Runs', 'Persists', 'Validates') in third person to sharpen specificity and distinguishability from general research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('research loop') and concrete mechanics ('validator-gated', 'native-hook persistence') but lists no concrete verb-actions like extract/fill/merge, and leans on buzzwordy adjectives.	2 / 3
Completeness	It states what the skill is but provides no 'when' guidance; with no 'Use when...' clause, completeness is capped at 2 per the judging guideline.	2 / 3
Trigger Term Quality	'research loop' is a somewhat natural keyword, but 'validator-gated' and 'native-hook persistence' are technical jargon a user would not naturally say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	'validator-gated research loop' is a fairly specific niche, but the generic 'research' term could still overlap with other research skills.	2 / 3
	Total	8 / 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: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/autoresearch/SKILL.md
Commit: 435d4a9

Reviewed: 2 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.