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

83%

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

77%Weight 40%Scale 1-3

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

A thorough, highly actionable skill with a clear multi-step workflow and reviewer feedback loop. Its main weaknesses are minor internal repetition and progressive disclosure: the referenced shared-references files are missing from the bundle and content that could be externalized is inline.

Suggestions

Consolidate the MAX_PAGES definition and the "section count is flexible" note so each is stated once (in Constants and Key Rules respectively) to remove repetition.

Either include the referenced shared-references/*.md files in the bundle or inline the essential parts of the Output Versioning, Manifest, and Language protocols so the links resolve.

Consider moving the verbose section-by-section templates and Figure/Citation Plan tables into a reference file the SKILL.md points to, keeping the body as an overview.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense with no conceptual fluff, but restates the MAX_PAGES rule and "section count is flexible" guidance three times each, so it could be tightened. Not a 1 because it never explains concepts Claude already knows; not a 3 because of the repetition.	2 / 3
Actionability	Provides copy-paste-ready markdown templates (Claims-Evidence Matrix, section-by-section outlines, Figure Plan, Citation Plan) and a concrete MCP tool call example, giving fully executable guidance.	3 / 3
Workflow Clarity	A clearly sequenced 7-step workflow with an explicit reviewer feedback loop (poll review_status until done=true, then apply feedback before finalizing), which serves as the validation checkpoint for this non-destructive task.	3 / 3
Progressive Disclosure	Section organization is clear and the three Output Protocol links are signaled one level deep, but those shared-references/*.md files are absent from the bundle and the detailed templates are largely inline rather than split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 that explicitly covers both capability and trigger conditions with natural multilingual keywords. The only gap is specificity, where a single core action is named rather than an enumerated list of concrete actions.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and core action ("Generate a structured paper outline from review conclusions and experiment results"), but lists a single action rather than the multiple specific concrete actions needed for a 3.	2 / 3
Completeness	Clearly answers both "what" (generate a structured paper outline from review conclusions and experiment results) and "when" via an explicit "Use when..." clause with concrete triggers.	3 / 3
Trigger Term Quality	Provides natural, multilingual triggers a user would actually say ("写大纲", "paper outline", "plan the paper", "论文规划"), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (academic paper planning) with distinctive 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
Path: skills/skills-codex-claude-review/paper-plan/SKILL.md
Commit: fe5963c

Reviewed: 17 days 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.