ds-review

Use when a draft, paper, or paper-like report is substantial enough for an independent skeptical audit before finalization, rebuttal, or revision routing.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ds-review/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear sequenced workflow and real, well-signaled template references, but it is over-long for an instruction skill with significant repetition and large inline sections that belong in separate reference files.

Suggestions

Deduplicate the review_followup_policy handling: define the audit_only/user_gated/auto_execute modes once and reference them, instead of restating routing logic in 'Non-negotiable rules', step 6, and step 7.

Move the paper_experiment_matrix row schema and manuscript-revision delivery contract into a reference file (e.g. references/matrix-schema.md) and link to it, reducing the inline wall of text.

Consolidate 'Companion skill routing' and 'Artifact routing guidance' with the step-6 routing table to remove overlapping route descriptions.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and free of beginner-concept explanation, but at ~412 lines it repeats the same follow-up policy and routing logic across 'Non-negotiable rules', the workflow, and 'Companion skill routing', and could be tightened substantially.	2 / 3
Actionability	It gives concrete file targets (paper/review/review.md), named templates in references/, and specific tool calls with arguments (artifact.create_analysis_campaign(...), memory.search(...)), making the guidance executable rather than abstract.	3 / 3
Workflow Clarity	An explicit numbered 1-8 workflow sequences the audit with clear gating/stop conditions (review_followup_policy modes, 'only treat the review line as truly closed after...') and route-decision branches serving as checkpoints.	3 / 3
Progressive Disclosure	Templates in references/ are real and clearly signaled one level deep, but the bulk of the matrix schema, delivery contracts, and routing tables live inline in a long monolithic body rather than being split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 well-formed with an explicit 'Use when' trigger covering both what and when, but it is jargon-leaning and only moderately specific about concrete audit actions.

Suggestions

Add 2-3 concrete audit verbs (e.g. 'identify core claims, audit novelty and evidence sufficiency, produce a revision plan') to raise specificity.

Swap jargon ('revision routing') for natural user phrasing ('revision advice before submission', 'harsh review') to improve trigger-term quality.

Add a brief disambiguating clause (e.g. 'audits a finished draft rather than drafting or rebutting reviewer comments') to reduce overlap with write/rebuttal skills.

Dimension	Reasoning	Score
Specificity	It names the domain ("independent skeptical audit") and several output contexts ("finalization, rebuttal, or revision routing") but does not enumerate multiple concrete audit actions like 'identify claims, audit novelty, write review note, produce revision plan'.	2 / 3
Completeness	It explicitly states what the skill does ("independent skeptical audit") and when to use it ("Use when a draft, paper, or paper-like report is substantial enough... before finalization, rebuttal, or revision routing"), satisfying both halves.	3 / 3
Trigger Term Quality	It includes relevant natural terms ("draft, paper, or paper-like report", "audit") but leans on jargon ("rebuttal", "revision routing") and misses common user phrasings like 'harsh review' or 'paper audit'.	2 / 3
Distinctiveness Conflict Risk	The audit framing carves a niche, but 'review' overlaps semantically with sibling write/rebuttal skills and the description does not explicitly disambiguate from them, only the body does.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-review/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 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.