research-review

Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

Quality

76%

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/research-review/SKILL.md

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.

A well-structured, highly actionable orchestration skill with a clear multi-round workflow and properly signaled external references. Its main weakness is verbosity from repeated model-pinning rules and a large inline prompt/scope-limits block that could be factored into a reference file.

Suggestions

Move the large inline Codex review prompt (especially the SCOPE LIMITS doctrine) into a referenced file under shared-references/ and link to it, reducing SKILL.md body length and deduplicating it from the Prompt Templates section.

State the model-pin and reasoning-effort rule once in Constants and reference it from the Reviewer Calling Convention and Key Rules instead of repeating the full pin in three places.

Tighten Step 3 by collapsing the prose around follow-up patterns into the existing bulleted list, removing restated guidance already covered in Key Rules.

Dimension	Reasoning	Score
Conciseness	Mostly operational content (tool configs, prompts, tracing) but includes padded sections: the large inline scope-limits doctrine inside the Codex prompt, model-pin rules repeated across Constants/Calling Convention/Key Rules, and Prompt Templates that restate the Step 2 prompt — matching 'Mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Provides concrete MCP tool names with exact config JSON and model pins, specific follow-up phrase patterns, and named deliverables, but the templates retain placeholders like '<absolute path to ...>' and '[saved threadId]', leaving minor gaps characteristic of score 4 rather than fully copy-paste-ready score 5.	4 / 5
Workflow Clarity	A clear five-step sequence (Gather → Initial Review → Iterative Dialogue → Convergence → Document) with convergence/stop criteria and a rounds 2-N feedback loop, but the 'checkpoints' are soft convergence criteria rather than explicit validation gates, so it lands at score 4 instead of 5.	4 / 5
Progressive Disclosure	Good section structure with one-level-deep references signaled via markdown links to shared-references/*.md (external-cadence, reviewer-routing, output-composition, review-tracing, integration-contract); however the large inline Codex prompt block could itself be lifted into a referenced file, a minor organization gap keeping it at 4.	4 / 5
	Total	15 / 20 Passed

Description

86%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 strong description that explicitly states both what the skill does and when to use it, with excellent natural trigger phrases. The only weakness is that it describes essentially one action rather than a fuller set of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('deep critical review of research') and a concrete action ('from an external reviewer backend (Codex or manual)'), but essentially describes one action rather than a comprehensive list, matching the score-3 anchor 'Names domain and 1-2 concrete actions, but not comprehensive'.	3 / 5
Completeness	Clearly answers 'what' ('Get a deep critical review of research from an external reviewer backend (Codex or manual)') and 'when' with explicit 'Use when...' trigger clauses, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Directly quotes natural user phrases ('review my research', 'help me review', 'get external review') plus synonyms ('critical feedback on research ideas, papers, or experimental results'), giving comprehensive coverage of natural terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The 'external reviewer backend' / research-review niche is mostly distinct, but generic triggers like 'help me review' carry minor overlap risk with general review or code-review skills, so it sits at score 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/research-review/SKILL.md
Commit: 2132036

Reviewed: less than a minute 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.