CtrlK
BlogDocsLog inGet started
Tessl Logo

researchwrite

Proposal-first scientific writing pipeline. Three modes (compose/revise/hybrid) with four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.

63

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-proposal-writer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is lean, well-sequenced with explicit QA gates and retry feedback, and uses excellent one-level-deep progressive disclosure; its main weakness is that the body delegates executable steps to reference files, leaving actionability slightly incomplete.

Suggestions

Include a brief inline 'Quick start' with one concrete worked sequence (e.g., a 3-line compose example) so the body is actionable without opening a reference first.

Add an explicit 'validate after each round' checkpoint line near the mode dispatch or deliverables section to make the feedback loop visible inline rather than only in the QA pipeline diagram.

DimensionReasoningScore

Conciseness

The body is dense and operational—terse principles, tables, and a pipeline diagram assume Claude's competence with no padding explaining what a proposal or QA is; the reference index earns its place as navigation, so it is not at the verbose 2-anchor.

3 / 3

Actionability

Concrete structure exists (named foundation files, mode dispatch table, QA thresholds like 7.0/5.0), but the actual executable step-by-step is deferred to reference files, leaving key operational details out of the body; this matches the incomplete-guidance anchor rather than copy-paste-ready 3.

2 / 3

Workflow Clarity

Multi-step processes are explicitly sequenced—the QA pipeline gate order (Gate 2→1→3→4) with thresholds and a directed-retry feedback loop ('不超过 3 轮') provides clear validation checkpoints and error recovery; not at 2 because checkpoints are explicit, not implicit.

3 / 3

Progressive Disclosure

A clear overview body points to one-level-deep references via a well-organized index table that lists load timing, and every referenced file (compose-mode, revise-mode, hybrid-mode, evaluation-rubric, etc.) exists in references/; navigation is easy and not deeply nested, so it is not at 2.

3 / 3

Total

11

/

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 specific and distinctive with concrete modes and principles, but it omits any explicit 'Use when...' trigger guidance, capping trigger-term quality and completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when drafting or revising scientific proposals, papers, or research reviews, or when running structured QA on scientific writing.'

Surface natural user phrasing ('write a proposal', 'revise my paper', 'review my discussion section') to broaden trigger-term coverage beyond technical jargon.

DimensionReasoningScore

Specificity

Names multiple concrete actions and modes ('compose/revise/hybrid', 'four-layer QA pipeline', 'evidence-before-prose, argument-before-sections, contracts-before-paragraphs'), matching the multiple-specific-actions anchor; it is not at 2 because it goes beyond naming just a domain and some actions.

3 / 3

Completeness

Clearly answers 'what' (modes, QA pipeline, enforced principles) but lacks an explicit 'when/Use when' trigger clause; per guidelines a missing 'Use when...' caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant terms ('scientific writing', 'proposal', 'revision', 'QA') appear but lean technical and lack the natural 'Use when...' phrasing users would say; missing common variations keeps it below 3.

2 / 3

Distinctiveness Conflict Risk

'Proposal-first scientific writing pipeline' with specific modes and a four-layer QA pipeline carves a clear niche unlikely to conflict with general writing skills; not at 2 because the domain framing is distinctive rather than broadly overlapping.

3 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.