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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 orchestration guide with strong validation and feedback loops, scoring high on workflow clarity and actionability. Its weaknesses are minor verbosity in templated report blocks and the absence of any progressive-disclosure bundle — all detail is inline in one file with dangling external references.

Suggestions

Move the per-phase checkpoint report templates and the full Phase 6 report scaffold into a references/ file (e.g. report-templates.md) and link to it from the phases, reducing inline tokens and improving progressive_disclosure.

Either ship the referenced ../../shared-references/output-versioning.md, output-manifest.md, and output-language.md files in the bundle or replace the dangling links with inline one-line summaries so the references are real and navigable.

Trim the emoji checkpoint blocks to a compact bullet form to tighten conciseness without losing the concrete output contract.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — uses tables, code blocks, and clear sections and assumes Claude's competence (no explanation of LaTeX/PDF basics) — but the repeated emoji checkpoint report templates and the full Phase 6 report scaffold are instances of padding that could be trimmed, fitting anchor 4 rather than the lean anchor 5.	4 / 5
Actionability	Provides concrete invocations for each phase ('/paper-plan "$ARGUMENTS"', '/paper-figure "PAPER_PLAN.md"', 'latexmk -pdf', the Phase 5.9 gate command) and explicit constants, but some phases defer to sub-skill internals described in prose ('Codex plans → Gemini optimizes → Nano Banana Pro renders') rather than copy-paste-ready code, fitting anchor 4.	4 / 5
Workflow Clarity	Six phases are clearly numbered and sequenced, each with 'What this does / Output / Checkpoint', and the pipeline includes explicit validation (compilation must succeed before the loop, the Phase 5.9 fresh-gate that blocks the Final Report on BLOCK) and review→fix→recompile feedback loops across two rounds, matching the anchor 5 example with validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	The file has good section structure and clearly-signaled markdown references to shared output protocols, but it is a ~300-line monolith with no bundle files present (references/, scripts/, assets/ are empty) and the referenced ../../shared-references/*.md files do not exist in this bundle, so content that could live in separate files is inlined and external refs dangle, fitting anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

91%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: it states concrete capabilities, gives bilingual natural trigger phrases, and explicitly covers both what the skill does and when to use it. The only gap is mild overlap with the closely related sub-skills it orchestrates.

Dimension	Reasoning	Score
Specificity	Names the domain ('Full paper writing pipeline') and lists several concrete actions — orchestrating five named sub-skills (paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop) to convert a narrative report into a submission-ready PDF — but the action framing is uniformly 'calls these sub-skills' with minor coverage gaps, fitting anchor 4 rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Orchestrates ... to go from a narrative report to a polished, submission-ready PDF') and 'when' ('Use when user says ...'), with concrete trigger phrases, matching the anchor 5 example that pairs both halves.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage in two languages — '写论文全流程', 'write paper pipeline', '从报告到PDF', 'paper writing' — plus a plain-language trigger clause ('wants the complete paper generation workflow'), matching the comprehensive anchor 5 including synonyms.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche (full end-to-end writing pipeline) with distinct triggers, but orchestrates closely related sub-skills (/paper-plan, /paper-write, etc.) that create minor overlap risk, fitting anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	18 / 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: 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.