paper-writing

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says \"写论文全流程\", \"write paper pipeline\", \"从报告到PDF\", \"paper writing\", or wants the complete paper generation workflow.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex-gemini-review/paper-writing/SKILL.md

Quality

Content

73%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-sequenced, highly actionable orchestration skill with strong validation checkpoints and clear delegation to sub-skills and shared references. Its main weakness is conciseness: verbose checkpoint dialog blocks, a full report template, and a timeline table inflate the body without proportional guidance value.

Suggestions

Move the full Phase 6 final-report markdown template and the Typical Timeline table into a referenced file (e.g. references/report-template.md) and keep only a short pointer inline to improve conciseness and progressive disclosure.

Compress the repeated checkpoint dialog blocks into a single reusable checkpoint format description rather than restating the pattern verbatim after each phase.

Tighten the inline 'writing invariant' blockquote by linking to /paper-write's CONFIDENT PROSE / HONEST LIMITS contract instead of restating it in full.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the lengthy checkpoint dialog blocks, the full final-report template, the typical-timeline table, and the inline 'writing invariant' prose add padding that could be trimmed or moved to references.	3 / 5
Actionability	It gives concrete, copy-pasteable invocations for each phase (/paper-plan "$ARGUMENTS", /paper-compile "paper/", etc.), names specific outputs and tools (latexmk, pdftotext, matplotlib/seaborn), and defines constants, though a few phases describe outcomes rather than fully executable steps.	4 / 5
Workflow Clarity	The pipeline is explicitly sequenced Phase 1 through 6 with per-phase inputs/outputs/checkpoints, validation gates (compilation must succeed before the improvement loop), and feedback loops in the review→fix→recompile rounds, including the destructive/batch validation the rubric rewards.	5 / 5
Progressive Disclosure	It is structured as an overview pointing to one-level-deep shared references (output-versioning.md, output-manifest.md, output-language.md) and delegates detailed behavior to sub-skills; no bundle files exist, and some content (the full report template, timeline table) is arguably inlined that could live elsewhere, keeping it just below a 5.	4 / 5
	Total	16 / 20 Passed

Description

85%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 clear, complete, and trigger-rich, effectively answering both what the skill does and when to use it with bilingual phrases. Its only weakness is that specificity stays at the orchestration layer and distinctiveness has minor overlap with the constituent sub-skills it coordinates.

Dimension	Reasoning	Score
Specificity	It names five concrete sub-skills chained into a pipeline (paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop) plus the end-to-end outcome (narrative report → submission-ready PDF), but stays at the orchestration level rather than enumerating the underlying actions of each phase.	4 / 5
Completeness	It explicitly states both the 'what' (full paper writing pipeline across five phases) and the 'when' via a concrete 'Use when user says ...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	It lists several natural triggers a user would actually say ("写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing") including a Chinese variant, but omits file-extension or common synonym triggers like 'LaTeX paper' or 'compile manuscript'.	4 / 5
Distinctiveness Conflict Risk	The end-to-end pipeline niche is fairly distinct and tied to specific sub-skill names, but it overlaps with sibling skills like /paper-write or /auto-paper-improvement-loop that a user might invoke individually.	4 / 5
	Total	17 / 20 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-gemini-review/paper-writing/SKILL.md
Commit: 341f914

Reviewed: 3 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.