ml-paper-writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

Quality

86%

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

Quality

Content

81%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 highly actionable with executable code and well-sequenced, validation-backed workflows, and it uses progressive disclosure effectively for its reference docs. Its main weakness is conciseness: redundant warnings, re-explained well-known principles, and inline time-sensitive conference details pad the token budget.

Suggestions

Collapse the repeated citation-hallucination warnings into a single authoritative section and have other sections link to it, cutting redundancy.

Move the time-sensitive conference version/year details (page limits, style files per year) into references/checklists.md and keep only a stable summary in SKILL.md, so stale specifics don't burden the context window.

Trim or offload the Gopen & Swan / Lipton / Steinhardt principle explanations to references/writing-guide.md, keeping only the actionable rules inline.

Resolve the dangling templates/ references: either add the templates directory to the bundle or remove/qualify the links so navigation doesn't dead-end.

Dimension	Reasoning	Score
Conciseness	The ~930-line body restates writing principles Claude already knows (Gopen & Swan, Lipton, Steinhardt) and repeats the citation-hallucination warning across multiple sections, plus hardcodes time-sensitive conference versions (NeurIPS 2025, ICML 2026, etc.) inline; useful and mostly efficient but with several trims available.	3 / 5
Actionability	Provides copy-paste-ready bash, python, and LaTeX snippets (e.g. a working doi_to_bibtex function, latexmk commands, template cp workflow) covering the common cases with executable specifics.	5 / 5
Workflow Clarity	Numbered workflows with checklists and explicit validation/feedback loops: the citation workflow mandates verify-then-fetch with a placeholder fallback, and the template workflow requires compiling the unmodified template before any edits.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to five real reference files (writing-guide.md, citation-workflow.md, checklists.md, reviewer-guidelines.md, sources.md), but the body repeatedly links to a templates/ directory and templates/README.md that do not exist in the bundle.	4 / 5
	Total	17 / 20 Passed

Description

92%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 concrete, trigger-rich, and explicitly pairs a clear 'what' with an explicit 'Use when...' clause, hitting the top anchors for specificity, completeness, and distinctiveness. Only minor synonym/extension coverage keeps trigger term quality at 4.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("drafting papers from research repos, structuring arguments, verifying citations, preparing camera-ready submissions") plus bundled tooling ("LaTeX templates, reviewer guidelines, and citation verification workflows"), giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both what ("Write publication-ready ML/AI papers...") and when ("Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ("ML/AI papers", named conferences, "camera-ready submissions", "citations", "LaTeX templates") that users would actually say, but a few common synonyms/extensions are absent, keeping it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (top AI conference paper writing) with named venues and specific triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (938 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ml-paper-writing/SKILL.md
Commit: 4b35756

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.