CtrlK
BlogDocsLog inGet started
Tessl Logo

ml-paper-writing

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. 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.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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-organized, actionable, and rich in validated workflows and reference pointers, but it runs long and carries noticeable redundancy in the citation-hallucination guidance. A few dangling references to a missing templates/ directory slightly weaken navigation.

Suggestions

Consolidate the citation-hallucination guidance into one section; the ~40% error stat, "never write BibTeX from memory" rule, and placeholder pattern are each repeated 2–3 times.

Either add the missing templates/ directory and templates/README.md, or reword those references so they don't point to non-existent paths.

Move the bulk of the conference-requirements and template-reference tables into the existing references/*.md files to slim the SKILL.md overview.

DimensionReasoningScore

Conciseness

The ~1000-line body is mostly efficient but repeats itself: the ~40% citation error rate, the "never generate BibTeX from memory" rule, and the placeholder pattern each appear two or three times across the "CRITICAL", "Citation Workflow", and summary sections, which could be consolidated.

3 / 5

Actionability

Provides mostly executable guidance — Python snippets for Semantic Scholar/CrossRef BibTeX, bash exploration commands, LaTeX table/figure examples, and concrete checklists — with only minor gaps such as Exa MCP usage lacking a code example.

4 / 5

Workflow Clarity

Multiple numbered workflows (0–4) ship with checklists and explicit validation checkpoints ("Verify template compiles as-is", "If ANY step fails → mark placeholder, inform scientist"), but a few workflows are lighter on feedback-loop detail.

4 / 5

Progressive Disclosure

Good one-level-deep structure with clearly signaled links to six real references/*.md files, but the body also points to a templates/ directory and templates/README.md that do not exist, and some conference/template tables that could live in reference files are inlined.

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 excellent: third-person, concise, and explicitly covers both capabilities and trigger conditions with venue-specific keywords. It is a strong model of a well-written skill description.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions — "drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions" — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ("Write publication-ready ML/AI/Systems 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

Comprehensive natural-term coverage including the venue names users would actually say (NeurIPS, ICML, ICLR, ACL, etc.) plus "research repos", "citations", and "camera-ready submissions".

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — conference-targeted ML/Systems paper writing with venue-specific triggers — making it unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1016 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
OpenRaiser/NanoResearch
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.