CtrlK
BlogDocsLog inGet started
Tessl Logo

peer-review

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is peer-review in K-Dense-AI/scientific-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 dense, well-sequenced review workflow: every step has an executable local command, explicit validation gates (intake, audits, lint), and one-level-deep bundle references that all exist. The only trimmable material is the dated-ledger caveat and the trailing citation boilerplate.

DimensionReasoningScore

Conciseness

The body is almost entirely prescriptive lists and commands with no explanations of concepts Claude already knows, but the dated source-ledger note ('verified 2026-07-23') and the multi-paragraph arXiv-fetch citation boilerplate at the end are time-sensitive/trimmable material that keeps it at the 'efficient with minor trimmable instances' anchor rather than 'every token earns its place'.

4 / 5

Actionability

Every workflow step ships a copy-paste-ready command with concrete arguments and outputs (e.g., 'python3 scripts/validate_review_intake.py completed-intake.json', 'generate_review_scaffold.py completed-intake.json -o private-review.md') plus the exact template to start from, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The 11-step sequence includes a hard validation gate ('Proceed only when status is READY_FOR_LOCAL_REVIEW' with an explicit list of what the validator blocks), per-step validators and audits, a lint pass, and a 'Before handoff' checklist — explicit checkpoints and error-recovery guidance for a complex process, matching the anchor-5 pattern rather than the minor-validation-gaps anchor.

5 / 5

Progressive Disclosure

The body is an overview with clearly signaled, one-level-deep references (each step names its reference file, plus a 'Local tool index' and a 'References and assets' section), and every referenced path in references/, scripts/, and assets/ exists in the bundle. Only the unused assets/reporting_checklist_template.csv is unreferenced, which is not enough to drop below the clear-navigation anchor.

5 / 5

Total

19

/

20

Passed

Description

92%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: it states concrete capabilities in third person, provides an explicit 'Use for…' trigger clause with domain-specific terms, and defines a distinct niche. The only gap is a handful of natural synonyms a user might use (e.g., 'referee report', 'rebuttal').

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ('Prepare evidence-bounded, constructive peer-review drafts', 'reporting-guideline selection', 'claim–evidence checks', 'revision-response planning') covering the full review lifecycle in third-person voice, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

It explicitly answers both 'what' (prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments) and 'when' via a concrete 'Use for authorized review of…' clause listing specific triggers, exactly matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Good natural-term coverage ('peer-review', 'manuscript', 'preprint', 'protocol', 'statistics', 'reproducibility', 'citation'), but a few natural synonyms users might say ('referee report', 'reviewer comments', 'rebuttal letter') are missing, so it fits the 'good coverage with a few natural terms missing' anchor rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (authorized scientific peer review of manuscripts, protocols, preprints, and proposals) with distinct domain triggers, so overlap with general writing, citation, or document skills is minimal.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
K-Dense-AI/claude-scientific-writer
Reviewed

Table of Contents

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.