researchwrite

Proposal-first scientific writing pipeline, installed under the compatibility trigger researchwrite and the repository package name nature-proposal-writer. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing. Three modes (compose/revise/hybrid) with a four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.

Quality

81%

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

Quality

Content

78%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-organized, lean instruction skill with strong progressive disclosure and a clear QA pipeline workflow. The body functions as an effective overview; the remaining headroom is in inlining a touch more executable per-mode guidance and explicit validation checkpoints.

Suggestions

Inline a one-line summary of the compose/revise 9-step flow (or a per-mode checklist) so the body is actionable without opening a reference for common cases.

Add an explicit validation/verification checkpoint callout in the run-deliverables section (e.g., 'run validation-checklist before export') to strengthen the feedback loop already implied by Gate 3/4.

Tighten the QA pipeline diagram by collapsing the ASCII tree into a compact ordered list, saving tokens without losing sequence clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's intelligence (terse principle bullets, dispatch table, gate list); the reference index is navigation rather than padding, with only minor tightening opportunities.	4 / 5
Actionability	Concrete guidance throughout — specific file names (00_scope.md, 01_research_canon.md, ...), mode dispatch, gate thresholds (7.0/5.0), and pipeline order; the detailed 9-step flows are deferred to references, which is appropriate for an instruction-only skill but leaves the body one level above executable steps.	4 / 5
Workflow Clarity	Clear Gate 2→1→3→4 sequence with explicit ordering rationale ('Gate 2 在 Gate 1 之前'), scoring thresholds, and a bounded 3-round rollback feedback loop; the per-mode 9-step workflows and stopping rules live in referenced files rather than inline.	4 / 5
Progressive Disclosure	Exemplary overview-plus-reference structure: a 20-row reference index keyed to load conditions, all referenced files verified present, one level deep and clearly signaled, with project-structure and worked-example pointers for discovery.	5 / 5
	Total	17 / 20 Passed

Description

83%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, specific description that clearly states what the skill does and when to use it, with concrete trigger guidance and a distinctive niche. Slight room to broaden natural trigger synonyms and tighten the action verbs.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('composing, revising, or auditing') plus structural features ('Three modes (compose/revise/hybrid) with a four-layer QA pipeline', 'Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs'), but the verbs are fairly generic writing operations rather than fully distinctive capabilities.	4 / 5
Completeness	Explicitly answers both what ('Proposal-first scientific writing pipeline ... Three modes ... four-layer QA pipeline ... Enforces ...') and when ('Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('research proposals', 'opening reports', 'research plans', 'evidence-grounded scientific writing'), but omits common synonyms (manuscript, grant) and the bilingual terms a researcher might actually utter.	4 / 5
Distinctiveness Conflict Risk	The 'proposal-first scientific writing' niche with compatibility triggers (researchwrite / nature-proposal-writer) and QA-pipeline framing is clearly distinct, with only minor overlap risk against general scientific-writing or docx skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-proposal-writer/SKILL.md
Commit: 3817cd1

Reviewed: about 8 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.