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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

75%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.

The content is a well-structured, highly actionable multi-step workflow with concrete templates, an executable style-ref integration, and a reviewer feedback loop. Its main weakness is conciseness — the body is long with some redundant or over-explanatory prose that could be trimmed or moved to the shared references.

Suggestions

Trim restated guidance (narrative-principle prose, the MAX_PAGES explanation that appears in both Constants and Key Rules) to reduce token load.

Consider moving the full GAP_REPORT.md template and detailed section-by-section fill-in templates into a reference file, keeping only the skeleton in SKILL.md.

Add an explicit verification checkpoint between Steps 3-5 (e.g., confirm the section count and page budget sum to MAX_PAGES before review) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete templates and venue-specific rules that earn their place, but several prose sections (e.g., the narrative-principle restatement, repeated MAX_PAGES explanations) restate things Claude already knows or that are said elsewhere and could be tightened.	3 / 5
Actionability	Provides copy-paste-ready guidance throughout: an executable bash block for style-ref resolution with exit-code handling, fill-in markdown templates for every section, a figure-plan table, a citation plan, and a complete concrete mcp__codex__codex invocation with prompt.	5 / 5
Workflow Clarity	A clear 7-step sequence is present with a real feedback loop in Step 6 (reviewer feedback applied before finalizing) and input-validation logic in Step 1 (CLAIMS_FROM_RESULTS.md verdict handling), but intermediate steps lack explicit verification checkpoints before proceeding.	4 / 5
Progressive Disclosure	External detail is pushed to clearly signaled one-level-deep references (../shared-references/*.md, tools/extract_paper_style.py) loaded only when needed, with good section structure; however no bundle files ship locally under ./references/ or ./scripts/ and some inlined templates (e.g., the full GAP_REPORT.md format) could be externalized.	4 / 5
	Total	16 / 20 Passed

Description

86%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.

The description is strong: third-person voice, explicit what-and-when structure, and rich bilingual trigger phrases. Its only weakness is that it names a single concrete action rather than enumerating multiple specific capabilities.

Suggestions

Expand the 'what' clause to list a few concrete sub-actions (e.g., build a Claims-Evidence Matrix, plan figures, scaffold citations) to raise specificity.

Tighten the generic phrase "wants to create a paper plan before writing" toward a more distinctive trigger to reduce overlap with general writing skills.

Dimension	Reasoning	Score
Specificity	The phrase "Generate a structured paper outline from review conclusions and experiment results" names the domain and one concrete action with its input sources, but lists only a single action rather than multiple specific capabilities.	3 / 5
Completeness	Explicitly answers both what ("Generate a structured paper outline from review conclusions and experiment results") and when ("Use when user says...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would actually say — "写大纲", "paper outline", "plan the paper", "论文规划" — covering bilingual synonyms and the descriptive intent, giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The paper-outline-from-review-conclusions niche with bilingual specific triggers is mostly distinct, though broad phrases like "plan the paper" carry minor overlap risk with general paper-writing skills.	4 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/paper-plan/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.