SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ars-academic-paper

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

ClawHub Agent Skills author: sedey999 v3.3.2 MIT-0 80 files body ≈ 12 237 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

12-agent academic paper writing pipeline.

As a process F 53/100 · Will not run — References files that are not bundled: references/shared/style_calibration_protocol.md, references/shared/intent_clarification_protocol.md, references/shared/review_criteria_consumer_protocol.md

ProcedureLaTeXWordResearchAI and agentstype 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
83/100
safety, quality, tests
Safety 60%
99
Quality 40%
58
Run on models
none yet
Process rating
F
53/100
Will not run
References files that are not bundled: references/shared/style_calibration_protocol.md, references/shared/intent_clarification_protocol.md, references/shared/review_criteria_consumer_protocol.md
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Obfuscation obf-hex-escape-chain references/guides/venue_disclosure_policies.md:128
    Escaped/char-code string obfuscation (documentation of a security skill)
    | Source URL | Official submission guide: https://gjyk.ijournals.cn/gjykcn/site/menu/20120104163914001 ; GenAI notice: https://gjyk.ijournals.cn/uploadfile/gjykcn/20260423/%E7%94%9F%E6%88%90%E5%BC%8F%
    security skill

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 12237 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/shared/style_calibration_protocol.md
  • warning missing-ref reference to a missing file: references/shared/intent_clarification_protocol.md
  • warning missing-ref reference to a missing file: references/shared/review_criteria_consumer_protocol.md
  • warning missing-ref reference to a missing file: references/shared/sprint_contract.schema.json
  • warning missing-ref reference to a missing file: references/shared/contracts/writer/full.json
  • warning missing-ref reference to a missing file: references/templates/revision_tracking_template.md
  • warning missing-ref reference to a missing file: references/shared/mode_spectrum.md
  • warning missing-ref reference to a missing file: references/shared/contracts/patch/revision_patch.schema.json
  • warning missing-ref reference to a missing file: references/shared/cross_document_consistency_advisory_protocol.md
  • warning missing-ref reference to a missing file: references/shared/model_tiering.md

Process rating: all ten parameters 53/100

Will not run. References files that are not bundled: references/shared/style_calibration_protocol.md, references/shared/intent_clarification_protocol.md, references/shared/review_criteria_consumer_protocol.md
  • 0Tools and files. 10 referenced file(s) missing: references/shared/style_calibration_protocol.md, references/shared/intent_clarification_protocol.md, references/shared/review_criteria_consumer_protocol.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 28 mutating operations with no state check
  • 40Execution cost. Instruction body is 12237 tokens: crowds the task out of the window
  • 85Steps. 103 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 26 top-level sections: this looks like several domains in one skill

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)
  • +2Single-language instructions
  • +3Description length 564: enough signal without eating the budget
  • +4Structure: 51 headings
  • +3Step-by-step instructions: 103 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (3 of 9)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: clean
This is a large text-only academic writing workflow with disclosed manuscript editing, formatting, local outputs, and optional external verification, but no artifact-backed deception or malicious behavior.
LLM: benign (high) · VirusTotal: · 22 Aug 2026