autoresearch

Stateful validator-gated research loop with native-hook persistence

Quality

69%

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

85%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 content is a tight, well-structured workflow skill with explicit validation gating and a clear feedback loop; it is actionable and well-organized, with only minor conciseness and validator-command detail gaps.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids concept-explanation padding; the only mild over-explanation is the framing intro and migration note, keeping it just below the 'every token earns its place' anchor.	4 / 5
Actionability	It gives concrete paths (.omx/state/.../autoresearch-state.json), explicit state fields, two full JSON artifact examples, and specific skill invocations ($deep-interview --autoresearch); the validator command itself is user-supplied, leaving a minor gap.	4 / 5
Workflow Clarity	The 5-step Recommended flow plus the Core contract's explicit artifact-gated completion rule form a clear sequence with an explicit validation checkpoint and a validate-and-continue feedback loop, matching the top anchor.	5 / 5
Progressive Disclosure	Single-file skill with no bundle files needed; sections are clearly headed and well-organized (Boundary, Use when, Core contract, Completion artifact contract, Recommended flow, Migration note), satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

53%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 conveys a clear, distinctive capability but is architecture-oriented rather than action-oriented and entirely lacks trigger guidance, capping completeness and trigger quality at the midpoint.

Suggestions

Add concrete action verbs and a 'Use when...' clause, e.g. 'Runs a persistent research loop that keeps nudging until a validator artifact passes. Use when the user needs a bounded research deliverable that must pass explicit validation.'

Replace jargon-only phrasing with at least one natural trigger term users would say (e.g. 'keep researching until X is validated').

Lead with what the skill does for the user before the implementation mechanism (stateful/native-hook).

Dimension	Reasoning	Score
Specificity	It names the domain concretely ('research loop') and characterizes the mechanism ('stateful validator-gated', 'native-hook persistence'), but states no user-facing action verbs — describing architecture rather than behavior, so it does not reach the 'several specific actions' anchors.	3 / 5
Completeness	It gives a clear 'what' (stateful validator-gated research loop) but no 'when' or explicit trigger guidance at all; per the rubric a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	'research loop' is a reasonably natural term, but 'validator-gated' and 'native-hook persistence' are technical jargon with no common synonyms or natural phrasings a user would say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'validator-gated' and 'native-hook persistence' qualifiers carve a specific niche with only minor overlap against other research skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 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: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/autoresearch/SKILL.md
Commit: 2da3648

Reviewed: ~18 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.