scientific-writing

Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.

Quality

92%

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

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.

A well-engineered, action-oriented skill body with an explicit multi-step workflow, executable bundled scripts, strong validation checkpoints, and clean one-level-deep progressive disclosure. Minor conciseness gains are possible around inline dated policy references.

Dimension	Reasoning	Score
Conciseness	Largely lean and procedural, assuming Claude's competence with no basic-concept padding; a few inline time-sensitive dates (e.g. "2026-07-24", "January 2026") and dense intake/fabrication lists could be trimmed slightly, keeping it just below the top anchor.	4 / 5
Actionability	Provides multiple copy-paste-ready commands with real flags (scaffold, select_reporting_guidelines, check_consistency, validate_manifest, audit_claims, check_references, validate_authorship, lint_manuscript) plus concrete ID and tagging conventions, fully covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced 12-step workflow with explicit validation gates ("Resolve every mismatch manually", re-run affected audits, "Only accountable humans may set submission_ready") and a 7-step revision feedback loop with human approval, matching the top anchor.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with inline "See references/..." pointers and a Bundled files index; references are one level deep, well-signaled, and all referenced files were verified to exist, with content appropriately split into references/assets/scripts.	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, third-person description that explicitly covers both what the skill does and when to use it, with concrete actions and a specialized scientific-writing niche. Keyword coverage is comprehensive but could add a few everyday synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Draft, revise, and audit") plus comprehensive capability areas (evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, local consistency checks), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Clearly answers what (draft/revise/audit with named controls) and explicitly answers when via "Use for ... when scientific accuracy and traceability matter" with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("scientific manuscripts or reports", "manuscript sections, references, declarations, tables, figures, or submission preparation") but a few common synonyms ("paper", "journal article", "peer review") are missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear scientific-manuscript niche with distinct triggers (evidence provenance, reporting-guideline coverage, authorship accountability) and minimal overlap risk with general writing skills.	5 / 5
	Total	19 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/scientific-writing/SKILL.md
Commit: 1e5eeff

Reviewed: ~16 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.