paper-writing

Workflow 3: Full paper writing pipeline that goes 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

81%

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

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 body is a well-structured, highly actionable orchestrator with excellent workflow clarity and validation feedback loops. Its main weakness is conciseness: the assurance logic is duplicated across Phase 0 and Phase 6.0, and some contract/forensics prose is inlined rather than deferred to the shared-references files it already points to.

Suggestions

De-duplicate the assurance-level resolution: define the derivation once (Phase 0) and have Phase 6.0 reference it instead of re-spelling out the full first-match-wins order and re-derive step list.

Move the inline forensics prose (Phase 5.9) and the "Empirical motivation" narrative paragraphs into the referenced shared-references files, keeping only the operational trigger condition and gate exit-code rule inline.

Convert the pseudocode if/else detector blocks in Phases 4.5 and 4.7 into literal bash conditionals (as Phase 5.5 already does) so every code block is copy-paste executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic-concept padding), but it is noticeably long with duplicated material — the assurance-level derivation is spelled out in full in both Phase 0 and Phase 6.0 — plus "Empirical motivation" prose blocks, so it fits the "mostly efficient but could be tightened" anchor rather than the lean anchor 4.	3 / 5
Actionability	Provides many concrete, copy-pasteable bash commands (mkdir/echo into paper/.aris, the rg numeric-claim regex, the find for raw results, bash "$AUDIT_VERIFIER" ...), but Phases 4.5/4.7/5.8 use pseudocode-style if/else detector blocks and the report templates are placeholder-filled, leaving minor gaps versus the fully-executable anchor 5.	4 / 5
Workflow Clarity	Clear Phase 0–6 sequence with explicit inter-phase checkpoints, a literal submission pre-flight checklist, validation gates (proof/claim/citation audits, external verifier), and review→fix→recompile feedback loops, matching the top anchor including the checklist-for-complex-processes criterion.	5 / 5
Progressive Disclosure	Well-sectioned by phase with a clear overview diagram and mostly well-signaled one-level-deep references (e.g. [integration-contract.md](../shared-references/integration-contract.md)), but a few references are plain-text paths (assurance-contract.md, reviewer-independence.md) and substantial contract/forensics detail is inlined that overlaps referenced shared-references files — minor organization gaps fitting anchor 4 rather than the cleanly-split anchor 5.	4 / 5
	Total	16 / 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 strong: it explicitly states both the capability and concrete activation triggers with good bilingual/synonym coverage and a distinct niche. The only weak spot is specificity, where the pipeline is described as one high-level transformation rather than enumerating its constituent actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a single concrete transformation ("goes from a narrative report to a polished, submission-ready PDF") but does not enumerate the several specific pipeline actions (plan, figures, LaTeX, compile, review), matching the "1-2 concrete actions, not comprehensive" anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Explicitly answers both what ("Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF") and when ("Use when user says ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Quotes multiple natural trigger phrases users would say — "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", "complete paper generation workflow" — covering synonyms and bilingual variants comprehensively, fitting the top anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (full paper-writing orchestration pipeline) with distinct trigger phrases and minimal overlap risk with the narrower sub-skills it composes, matching the "clear niche with distinct triggers" anchor.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (732 lines); consider splitting into references/ and linking	Warning
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: 5 suspicious	Warning

	Total	12 / 16 Passed

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