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

69%

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

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.

The body is a well-structured, actionable review workflow with concrete artifacts, tool calls, and clear references, scoring well on actionability, workflow clarity, and progressive disclosure. Its main weakness is conciseness, driven by repeated routing guidance and numerous cautionary "Do not" rules.

Suggestions

Consolidate the routing rules that recur in Workflow step 6, Companion skill routing, and the auto-followup contract into a single routing table to cut redundancy.

Group the many "Do not..." injunctions into a compact anti-pattern list rather than scattering them across sections.

Move the detailed experiment-matrix row schema into a reference file so SKILL.md stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain guidance without explaining basics Claude already knows, but the ~400-line body repeats routing rules across "Workflow step 6", "Companion skill routing", and the auto-followup contract, and stacks many redundant "Do not..." injunctions that could be consolidated.	3 / 5
Actionability	Provides concrete executable anchors — specific output paths (paper/review/review.md), real template references, and explicit tool calls (artifact.create_analysis_campaign(...), memory.list_recent(scope='quest', limit=5)) — though some sections stay abstract ("audit at least these dimensions").	4 / 5
Workflow Clarity	An explicit 8-step numbered workflow with routing gates and a matrix-stability validation checkpoint ("require that every currently feasible matrix row... is either completed, analyzed, excluded, or blocked"); minor gaps in formal validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled, one-level-deep references to real files in references/ (review-report-template.md, revision-log-template.md, experiment-todo-template.md), though the inlined experiment-matrix row schema and routing tables could be split out to keep the overview lean.	4 / 5
	Total	15 / 20 Passed

Description

71%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 is strong on completeness with an explicit "Use when" trigger and a clear audit action, but is only moderately specific and misses common trigger synonyms like "review" and "manuscript". It is mostly distinct from sibling skills with minor overlap risk.

Suggestions

Add concrete deliverable actions to the description (e.g., "produces a skeptical review note, revision plan, and follow-up experiment TODO list") to lift specificity.

Include the natural trigger words "review" and "manuscript" so users who ask to "review my manuscript" land on this skill.

Sharpen the distinction from `rebuttal` by signaling the audit is independent of existing external reviewer comments.

Dimension	Reasoning	Score
Specificity	Names the domain ("draft, paper, or paper-like report") and one concrete action ("independent skeptical audit") plus routing contexts, but does not enumerate the concrete deliverables a 4-5 would list.	3 / 5
Completeness	Explicitly answers both what ("independent skeptical audit") and when via a concrete "Use when..." clause with trigger contexts ("before finalization, rebuttal, or revision routing").	5 / 5
Trigger Term Quality	Contains natural terms ("draft", "paper", "report", "audit") but omits common variations a user would say such as "review", "manuscript", "submission", or "feedback".	3 / 5
Distinctiveness Conflict Risk	Carves a clear audit niche distinct from drafting and rebuttal, but its proximity to `rebuttal` and `write` (named in the trigger) leaves minor overlap risk with closely related skills.	4 / 5
	Total	15 / 20 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: 4b35756

Reviewed: 5 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.