SKILLEMALL.ai
GitHub ↗ RU Sign in

BF nature-paper-hub

Full-pipeline Nature-series journal writing assistant. Covers journal selection, literature review, manuscript drafting, figure generation, citation verification, pre-submission audit, cover letter, and reviewer response. Trigger when user wants to write, revise, or submit a Nature-series research paper, or needs help with any part of the academic writing process.

ClawHub Agent Skills author: Yang Bai v1.0.0 MIT-0 13 files body ≈ 4 788 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 52/100 · Will not run — References files that are not bundled: templates/nature-latex.tex

GeneratorResearchInfrastructurePersonal productivitytype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
75
Run on models
none yet
Process rating
F
52/100
Will not run
References files that are not bundled: templates/nature-latex.tex
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token data/papers-index.json:503
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "title": "Electrodeposited MoxSyOz/NiTribological CoatingsPublished aspartofLangmuirvirtualspecialissue“2023…ial",
    quoted
  • low Secrets in code secret-high-entropy-token data/papers-index.json:508
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "abstract": "Electrodeposited MoxSyOz/NiTribological CoatingsPublished aspartofLangmuirvirtualspecialissue“2023…ial Tomas F.Babuska, Christopher L.Reed, Dhego Ban
    quoted
  • low Secrets in code secret-high-entropy-token data/papers-index.json:671
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "title": "Stabilization ofaMn\u000…ion in JavierVillalobos,[a]DulceM.Morales,[a]DenisAntipin,[a]GötzSchuck,[b]RonnyGolnak,[c]",
    quoted
  • low Secrets in code secret-high-entropy-token data/papers-index.json:676
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "abstract": "Stabilization ofaMn\u000…ion in JavierVillalobos,[a]DulceM.Morales,[a]DenisAntipin,[a]GötzSchuck,[b]RonnyGolnak,[c] Improving thestabilityofelectrocatalysts forth
    quoted
  • low Secrets in code secret-high-entropy-token data/papers-index.json:1540
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "abstract": "Machine Learning BigData SetAnalysis Reveals C−C Electro- HaoboLi,§XinyuLi,§Pengtang Wang,§ZhenZhang,KennethDavey,JavenQinfengShi, ABSTRACT: Carbon−carbon (C−C)couplingisessentialinthe el
    quoted

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: templates/nature-latex.tex

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: templates/nature-latex.tex
  • 0Tools and files. 1 referenced file(s) missing: templates/nature-latex.tex
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Result and completion. Does not say what the result is
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 5 branches
  • 70Execution cost. Instruction body is 4788 tokens
  • 100Steps. 136 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -32 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 366: enough signal without eating the budget
  • +4Structure: 42 headings
  • +3Step-by-step instructions: 136 items
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: suspicious
This academic writing skill is not overtly malicious, but it needs Review because it can expose research queries externally and includes a contaminated bundled literature index.
LLM: suspicious (high) · VirusTotal: · 29 May 2026