CtrlK
BlogDocsLog inGet started
Tessl Logo

research-paper-writing

Write, rewrite, and polish academic papers (ML/CV/NLP style). Use when the user drafts or revises Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; asks "does this flow / 这段通顺吗 / polish this paragraph"; turns bullet points or a Chinese draft into publication-quality English; runs a pre-submission self-review or reviewer-style critique; fixes paper figures/tables/LaTeX formatting; or compiles/converts the paper to PDF (LaTeX build, 编译PDF, 转成PDF). Trigger on mentions of paper, draft, camera-ready, rebuttal-facing revision, CVPR/ICCV/NeurIPS/ICLR/ACL-style venues, or .tex files being edited for a paper.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a well-organized, concise overview that routes by request size and loads only needed references, with concrete formats, grep patterns, and a review checklist. Its main weakness is that a few writing principles stay abstract and the PDF build verification loop lives in the reference rather than inline.

Suggestions

Add one short inline before/after example of a polished paragraph so the 'Quick polish' workflow demonstrates the expected transformation rather than only describing it.

Inline the PDF compile verify-retry loop (e.g., 'if build fails, read the first error, fix, rebuild; confirm the PDF opens and has the expected page count') so the fragile build workflow has an explicit feedback checkpoint in SKILL.md.

Tighten Core Writing Principles 1–2 from abstract directives into a quick self-check format (e.g., a one-line test per principle) to match the concreteness of the routing and review sections.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a paper, venue, or LaTeX is — and every section (routing table, Hard Rules, workflows) earns its tokens; the opening framing line is purposeful rather than padding.

5 / 5

Actionability

Highly actionable for an instruction-only skill: concrete grep patterns (\section, \begin{abstract}), exact preservation rules (\cite, \ref byte-for-byte), and copy-paste formats (Claim: ... | Evidence: ... | Status: ...). Held at 4 because some Core Writing Principles are abstract directives rather than concrete steps, and there is no inline worked example of a rewritten paragraph.

4 / 5

Workflow Clarity

Steps are clearly sequenced (diagnose/route → get facts → workflows A/B/C) with checkpoints such as the 3-question cap, structural-problem escape hatch, and the review checklist; capped at 4 because the PDF compile workflow's verify-retry loop is deferred to the reference rather than stated inline, leaving a minor validation gap for a fragile build operation.

4 / 5

Progressive Disclosure

SKILL.md is a tight overview; the routing table's Load column and the References section clearly signal one-level-deep files (abstract.md, introduction.md, method.md, etc.), all of which were verified to exist, and bulk detail is appropriately split out with easy navigation.

5 / 5

Total

18

/

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 a strong, third-person statement that comprehensively covers capabilities, triggers, and the use-when condition with bilingual synonyms and file extensions. It is specific, complete, and clearly distinct from generic writing skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the full paper lifecycle — "Write, rewrite, and polish", "runs a pre-submission self-review", "fixes paper figures/tables/LaTeX formatting", "compiles/converts the paper to PDF" — giving comprehensive coverage rather than the minor gaps of a 4.

5 / 5

Completeness

Explicitly answers both "what" (write/rewrite/polish academic papers with listed actions) and "when" via a detailed "Use when the user drafts or revises..." clause plus a "Trigger on mentions of..." sentence with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including bilingual synonyms ("does this flow" / "这段通顺吗", "编译PDF", "转成PDF"), venue names (CVPR/ICCV/NeurIPS/ICLR/ACL), and the .tex file extension, matching the anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (ML/CV/NLP academic paper writing) with distinct triggers (venue names, camera-ready, rebuttal-facing, .tex editing) and minimal overlap risk with generic writing skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
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.