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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/writing/ml-paper-writing/SKILL.md

The canonical home for this skill is ml-paper-writing in OpenLAIR/dr-claw

Quality

Content

62%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 skill delivers highly actionable, well-sequenced workflows with strong validation checkpoints, but is markedly verbose and inlines material that overlaps its own reference files. Progressive disclosure is undermined by a missing templates/ directory and substantial inlined reference-grade content.

Suggestions

Tighten the body by moving the Gopen & Swan principles table, micro-level tips, and conference-requirements tables fully into references/* (already linked) and keeping only a one-line pointer plus the most critical rule in SKILL.md.

Reconcile the bundle: either create the templates/ directory (with templates/README.md) referenced throughout the body, or remove/redirect those references so navigation is not broken.

Deduplicate the citation-safety messaging—'NEVER generate BibTeX from memory' appears in the critical section, the Golden Rule block, and the closing summary; stating it once with a pointer would save substantial tokens.

Dimension	Reasoning	Score
Conciseness	The body runs ~930 lines with substantial padding—restating 'NEVER generate BibTeX from memory' multiple times, large conference-requirement tables, and verbose philosophy sections that partly restate principles (Gopen & Swan table, micro-tips) already delegated to references/writing-guide.md, a notable over-explanation penalty.	2 / 5
Actionability	Provides mostly executable guidance—real Python snippets for Semantic Scholar/CrossRef BibTeX retrieval, concrete bash commands for repo exploration and template copying, and LaTeX macro examples—with only minor gaps (e.g. Exa MCP usage is described rather than shown as a runnable call).	4 / 5
Workflow Clarity	Multiple clearly sequenced checklists (Workflow 0, 1, 2, 3, 4) with explicit validation checkpoints, most notably the citation workflow's mandatory verify-in-2+-sources-then-fetch-via-DOI steps with explicit placeholder handling on failure, and the template 'compile as-is before editing' gate.	5 / 5
Progressive Disclosure	References to references/*.md and templates/ are one-level-deep and clearly signaled, but the templates/ directory referenced repeatedly in the body does not exist in the bundle, and a large amount of content (writing philosophy tables, conference tables) that could live in the reference files is inlined in SKILL.md, leaving organization only partially realized.	3 / 5
	Total	14 / 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 specific, complete, and well-targeted, clearly stating both what the skill does and when to use it with concrete trigger phrases tied to a narrow ML-paper-writing niche. Minor synonym coverage gaps in trigger terms are the only weakness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('drafting papers from research repos, structuring arguments, verifying citations, preparing camera-ready submissions') plus concrete bundle inclusions (LaTeX templates, reviewer guidelines, citation workflows), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers 'what' (write publication-ready ML/AI papers for the listed venues) and 'when' via the 'Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural triggers like 'drafting papers', 'research repos', 'verifying citations', and 'camera-ready submissions' are well covered, but a few common synonyms a user might say (e.g. 'manuscript', 'rebuttal', 'related work') are missing, keeping it just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Narrow niche (ML/AI conference papers for named venues) with distinctive triggers ('camera-ready submissions', 'verifying citations') makes conflict with other writing 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 (939 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: synthetic-sciences/openscience
Path: backend/cli/skills/writing/ml-paper-writing/SKILL.md
Commit: 3a6c3a9

Reviewed: about 24 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.