paper-plan

Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable and the workflow is clearly sequenced with a genuine review feedback loop. Its weaknesses are conciseness (repeated MAX_PAGES explanations and overlapping template blocks) and progressive disclosure (dangling shared-references links and inline template content that could be externalized).

Suggestions

Consolidate the MAX_PAGES definition to a single place and remove the re-explanations in the review prompt, output skeleton, and Key Rules to tighten conciseness.

Either create the referenced ../../shared-references/*.md files or remove the dangling protocol links so navigation targets are real.

Move the large §0–§5 section-by-section template block into a separate reference file (e.g. SECTION_TEMPLATE.md) and link to it from the main body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no concept-padding, but MAX_PAGES is re-explained several times (Constants, the review prompt, the output skeleton, and Key Rules) and the §0–§5 section template overlaps with the Step 2 paper-type templates, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready scaffolding: Claims-Evidence Matrix and Figure/Citation Plan tables, an exact mcp__gemini-review review_start/review_status call block, concrete natbib commands, a chunked-write Bash fallback, and a full PAPER_PLAN.md output skeleton.	3 / 3
Workflow Clarity	A clear seven-step sequence includes an explicit external feedback loop in Step 6 (poll review_status until done=true, then apply feedback before finalizing) and validation scaffolding (Claims-Evidence alignment, [VERIFY] citation flags).	3 / 3
Progressive Disclosure	Sections are well organized with one-level references, but the referenced shared-references/*.md protocol files do not exist on disk and substantial template content (the §0–§5 block) is inline rather than split into a separate reference file.	2 / 3
	Total	10 / 12 Passed

Description

90%

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: it clearly states a concrete action with named inputs, provides explicit bilingual trigger guidance, and occupies a distinct niche. The only gap is specificity — it names a single primary action rather than enumerating multiple distinct capabilities.

Suggestions

Expand the action list to name additional concrete capabilities (e.g., 'build a Claims-Evidence Matrix, plan figures and citations, and produce a section-by-section outline') to raise specificity from a single action to multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names one concrete action ('Generate a structured paper outline') and its specific inputs ('review conclusions and experiment results'), but enumerates only a single primary action rather than multiple distinct concrete actions.	2 / 3
Completeness	Explicitly answers both 'what' (generate a structured paper outline) and 'when' with an explicit 'Use when user says...' trigger clause.	3 / 3
Trigger Term Quality	Strong coverage of natural terms users would say, spanning bilingual triggers ('写大纲', '论文规划', 'paper outline', 'plan the paper') plus a natural paraphrase for creating a paper plan before writing.	3 / 3
Distinctiveness Conflict Risk	Clear niche (academic paper planning from review/experiment artifacts) with specialized bilingual triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: fe5963c

Reviewed: about 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.