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

88%

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

77%

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 clear, validated workflows and good reference navigation, but it loses points on conciseness (repeated sections) and progressive disclosure (broken templates/ references and inline content that could live in reference files).

Suggestions

Deduplicate the citation-hallucination, proactivity, and page-limit material that recurs across sections; consolidate each into one canonical location and link to it.

Provide the missing templates/ directory and templates/README.md referenced by the LaTeX and resubmission sections, or replace those references with pointers to the real reference files.

Move the full Writing Philosophy, LaTeX template usage, and format-conversion guides into reference files (e.g., references/latex-templates.md) and keep SKILL.md a lean overview that links out.

Dimension	Reasoning	Score
Conciseness	The ~925-line body contains valuable non-obvious craft knowledge, but the citation-hallucination warning, "be proactive / deliver drafts" guidance, and conference page-limit tables are each repeated nearly verbatim in multiple places, which could be tightened.	2 / 3
Actionability	Provides executable bash (cp -r templates, latexmk), runnable Python (Semantic Scholar search, doi_to_bibtex), concrete LaTeX snippets, and specific checklists — all copy-paste ready.	3 / 3
Workflow Clarity	Numbered Workflows 0–4 are clearly sequenced with explicit validation checkpoints ("Verify template compiles as-is", "If ANY step fails → mark placeholder", "Compile after each section") and feedback loops for the fragile citation and LaTeX operations.	3 / 3
Progressive Disclosure	Real one-level-deep references (writing-guide, citation-workflow, checklists, reviewer-guidelines, sources) are well signaled and exist in the bundle, but the body repeatedly points to a templates/ directory and templates/README.md that are missing, and large philosophy/LaTeX-usage/format-conversion sections remain inline rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, uses natural trigger terms, answers both what and when explicitly, and occupies a clear non-conflicting niche; it is written in third person with no over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Write publication-ready ML/AI papers", "drafting papers from research repos", "verifying citations", "preparing camera-ready submissions" — matching the comprehensive multi-action anchor.	3 / 3
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").	3 / 3
Trigger Term Quality	Covers natural user phrasing ("drafting papers from research repos", "verifying citations", "camera-ready submissions", venue names) that a user would actually say, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche — academic paper writing for specific ML conferences with citation verification and LaTeX templates — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 6da7f7c

Reviewed: about 8 hours 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.