SKILLEMALL.ai
GitHub ↗ RU Sign in

BF research-paper-figure-skill-factory

Use when the user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence. Generated skills must use a specialized-skill-first workflow, full-feasible local PDF coverage where available, startup-plan-only first replies, strict text/image turn separation, ChatGPT web Create image / ChatGPT Images 2.0 rendering, Codex $imagegen-first rendering, sample-image transfer rules, all-step/current-position state footers, and a mandatory text-candidate to visual-candidate-board to image-only candidate generation to selection workflow after every multi-option figure decision.

ClawHub Agent Skills author: c-narcissus v1.0.1 MIT-0 54 files body ≈ 2 685 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 50/100 · Will not run — References files that are not bundled: references/workflow-and-state-contract.md, references/visual-style-and-board-protocol.md, references/prompt-generation-policy.md

ProcedureInfrastructureSoftware developmenttype 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
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
73
Run on models
none yet
Process rating
F
50/100
Will not run
References files that are not bundled: references/workflow-and-state-contract.md, references/visual-style-and-board-protocol.md, references/prompt-generation-policy.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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 · 0

✓ No critical or high findings

Files scanned: 54. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/workflow-and-state-contract.md
  • warning missing-ref reference to a missing file: references/visual-style-and-board-protocol.md
  • warning missing-ref reference to a missing file: references/prompt-generation-policy.md
  • warning missing-ref reference to a missing file: templates/state-footer-template.md
  • warning missing-ref reference to a missing file: templates/figure-brief-template.md
  • warning missing-ref reference to a missing file: templates/prompt-template.md

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: references/workflow-and-state-contract.md, references/visual-style-and-board-protocol.md, references/prompt-generation-policy.md
  • 0Tools and files. 6 referenced file(s) missing: references/workflow-and-state-contract.md, references/visual-style-and-board-protocol.md, references/prompt-generation-policy.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 85Steps. 50 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 7 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2685 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 676: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 50 items
  • +4Reference files are cited in the instructions (8 of 24)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: clean
This documentation-only skill factory is coherent with its paper-figure workflow purpose, though it may search the web, download open PDFs, write local corpus files, and use image generation when the workflow calls for it.
LLM: benign (high) · VirusTotal: · 29 May 2026