SKILLEMALL.ai

BB paper-deep-reading-teaching-explainer

Deep-read research papers into authoritative, evidence-grounded teaching reports, reproducibility/defense-ready explanations, innovation-mining artifacts, staged multi-image cartoon storyboard plans with continuity/cinematography and anti-hallucination source checks grounded in PDF and/or LaTeX sources, and final image-PDF assembly guidance. Use when users need rigorous paper understanding, teachable explanations, answer-prep material, reproducibility checks, and presentation-ready visual workflows without mixing report generation and image generation in one turn.

ClawHub Agent Skills author: c-narcissus v10.1.8 MIT-0 46 files body ≈ 14 781 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 78/100 · Nearly there — weak spots: result and completion, execution cost

ProcedureLaTeXData and analyticsLearningMedia and videotype and topics are labelled automatically from the skill text
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
71
Run on models
none yet
Process rating
B
78/100
Nearly there
Result and completion w 14
40
Execution cost w 6
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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: 46. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 14781 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 78/100

  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 14781 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 70Failures and branches. 37 branches
  • 100Steps. 466 steps
  • 100When it triggers. States when to use and when not to
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model

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
  • -31 of 8 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 570: enough signal without eating the budget
  • +4Structure: 52 headings
  • +3Step-by-step instructions: 466 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: clean
This skill is a disclosed paper-reading, teaching, storyboard, and local PDF-bundling workflow, with no evidence of hidden execution, credential use, persistence, or exfiltration.
LLM: benign (high) · VirusTotal: · 29 May 2026