CtrlK
BlogDocsLog inGet started
Tessl Logo

ml-paper-writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper discovery/evaluation criteria.

67

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is well-structured and actionable with clear sequenced workflows and mostly real, one-level-deep references. Its main weaknesses are moderate verbosity from duplicated sections and a broken templates/ reference that leaves a navigation gap.

Suggestions

De-duplicate the citation-hallucination material: keep the full 'Citation Workflow' section and reduce the early '⚠️ CRITICAL: Never Hallucinate Citations' block to a short pointer, since the same rules appear twice.

Create the referenced templates/ directory (with templates/README.md and the per-venue subdirectories) or change the repeated templates/ links to point to existing reference files, so navigation resolves.

Trim the inlined writing-philosophy tables (Gopen & Swan, Perez, Lipton, Steinhardt) to brief summaries and defer the detail to references/writing-guide.md, which already covers them, to reduce token cost.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes several padded/repeated sections — the 'Never Hallucinate Citations' material appears both early (CRITICAL section) and again in the later 'Citation Workflow' section, and writing-philosophy prose is duplicated between the body and references/writing-guide.md. It is not the severely verbose 'explains what a PDF is' level, sitting at the 'mostly efficient with some unnecessary explanation' anchor.

3 / 5

Actionability

Provides concrete executable guidance — bash exploration commands, latexmk/pdflatex compile commands, LaTeX/booktabs snippets, and step-by-step checklists — with only minor gaps, matching the 'mostly executable guidance' anchor rather than fully copy-paste-ready across all cases.

4 / 5

Workflow Clarity

Multi-step workflows (paper writing, citation verification, template setup, format conversion) are clearly sequenced with checklists, and the citation workflow has an explicit feedback loop ('If any step fails → mark as placeholder and report it'). Minor validation gaps keep it just below the explicit-checkpoint anchor.

4 / 5

Progressive Disclosure

Good structure with well-signaled one-level-deep references that mostly resolve to real files, but the body repeatedly references a templates/ directory and templates/README.md that do not exist, and substantial philosophy content is inlined that also appears in references/writing-guide.md — minor organization gaps per the score-4 anchor.

4 / 5

Total

15

/

20

Passed

Description

100%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-differentiated, clearly stating both the capability and explicit trigger conditions with natural phrasing and concrete venue names. It matches the top anchor on every dimension.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — 'drafting papers from research repos', 'conducting literature reviews', 'finding related work', 'verifying citations', 'preparing camera-ready submissions' — giving comprehensive coverage, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers 'what' ('Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM') and 'when' with concrete 'Use when...' trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases ('drafting papers', 'literature reviews', 'related work', 'verifying citations', 'camera-ready submissions') plus the full set of conference venue names, giving comprehensive coverage of natural terms and synonyms.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (conference ML paper writing) with named venues and specific triggers, minimizing conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1123 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, 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 7 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
Reviewed

Table of Contents

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.