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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/paper-plan/SKILL.md

Quality

Content

63%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 body is a well-sequenced, actionable paper-planning workflow with concrete templates and a review feedback loop. Its main weaknesses are repeated page-budget guidance across sections and inlined venue/template detail that would benefit from being split into referenced files.

Suggestions

Consolidate the MAX_PAGES / page-counting rules into one place (e.g., the Constants section) and reference it from Step 6 and Key Rules instead of restating it.

Move venue-specific norms (page limits, citation packages per venue) into a referenced venue-checklist file and link to it, reducing inlined detail in the body.

Replace the pseudocode-style spawn_agent block in Step 6 with an explicit, executable invocation (or a clearly justified placeholder) so the cross-review step is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and well-structured, but page-budget/counting rules and MAX_PAGES guidance are restated across Constants, Step 6, and Key Rules, and some venue-detail repeats, so it could be tightened.	3 / 5
Actionability	Provides concrete fillable templates (Claims-Evidence Matrix, section-by-section fields, Figure Plan table) and a specific cross-review block with named model/effort, but the spawn_agent block is pseudocode-style and templates are scaffolding rather than fully executable code.	4 / 5
Workflow Clarity	Seven clearly sequenced steps with sub-steps and an explicit feedback loop ("Apply feedback before finalizing") in Step 6, plus claim-validation logic in Step 1; minor gaps in explicit verification checkpoints elsewhere.	4 / 5
Progressive Disclosure	Headers give structure and shared-references are signaled, but substantial content that could live in separate files (venue page tables, full section templates, citation rules) is inlined, and the referenced shared-references are external rather than bundled.	3 / 5
	Total	14 / 20 Passed

Description

90%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 concise, uses third-person voice, and pairs a clear statement of purpose with explicit bilingual trigger phrases. Its only weakness is that it states a single overarching action rather than enumerating the several concrete sub-actions the skill performs.

Dimension	Reasoning	Score
Specificity	"Generate a structured paper outline from review conclusions and experiment results" names the domain and one concrete action with its inputs, but does not list multiple specific actions (e.g., build claims-evidence matrix, plan figures, scaffold citations).	3 / 5
Completeness	Explicitly answers both what ("Generate a structured paper outline...") and when ("Use when user says...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural bilingual synonyms users would actually say — "写大纲", "paper outline", "plan the paper", "论文规划" — giving comprehensive coverage of trigger phrases.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (paper planning from review conclusions) with distinct, specific triggers, giving minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/skills-codex/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.