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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description with strong trigger terms in both English and Chinese, a clear 'Use when' clause, and a distinct niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions or outputs (e.g., section structure, methodology planning, argument flow). Overall, it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Generates section headings, argument flow, methodology structure, and figure placement plan from review conclusions and experiment results.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (paper outline generation) and mentions inputs (review conclusions and experiment results), but doesn't list multiple concrete actions beyond 'generate a structured paper outline'. It could be more specific about what the outline contains or what steps are involved. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate a structured paper outline from review conclusions and experiment results) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition about creating a paper plan before writing). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '写大纲', 'paper outline', 'plan the paper', '论文规划', and 'paper plan'. These are terms users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The skill has a clear niche — paper outline generation specifically from review conclusions and experiment results — with distinct bilingual trigger terms. It is unlikely to conflict with general writing skills or other academic skills like literature review or paper drafting. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides a clear 7-step workflow for generating paper outlines. Its main strengths are the concrete templates (Claims-Evidence Matrix, section plans, figure plans) and the integrated review feedback loop. Its weaknesses are moderate verbosity—the skill could be tightened by ~20-30% without losing clarity—and the monolithic structure that packs substantial detail into a single file.
Suggestions
Trim repeated explanations of MAX_PAGES counting rules (mentioned in Constants, Step 2 templates, Key Rules, and output template) to a single authoritative definition.
Consider extracting the detailed section-by-section planning templates (Step 3) and paper type structures (Step 2) into a separate reference file to reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines) with some unnecessary verbosity—e.g., the acknowledgements section, repeated explanations of MAX_PAGES counting rules, and some template content that could be more compact. However, most content is substantive and not explaining things Claude already knows. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific markdown templates for Claims-Evidence Matrix, section-by-section planning with exact page budgets, figure plan tables, citation scaffolding, and even the exact MCP tool call format for Gemini review. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit dependencies (extract claims → determine structure → plan sections → plan figures → citations → cross-review → output). Step 6 includes a validation/feedback loop with the reviewer model, and the output step includes a checklist of next steps. The workflow handles error cases (missing input files, large file write failures). | 3 / 3 |
Progressive Disclosure | The skill references several external files (output-versioning.md, output-manifest.md, output-language.md) with clear one-level-deep links, which is good. However, the main SKILL.md itself is quite long and monolithic—the detailed section planning templates, figure plan templates, and citation scaffolding could potentially be split into separate reference files. No bundle files are provided to verify referenced paths exist. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
a425a71
- 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.