Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Baoyu Comic

v0.1.1

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image genera...

0· 268·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for nengnengz/baoyu-comic-2.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Baoyu Comic" (nengnengz/baoyu-comic-2) from ClawHub.
Skill page: https://clawhub.ai/nengnengz/baoyu-comic-2
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install baoyu-comic-2

ClawHub CLI

Package manager switcher

npx clawhub@latest install baoyu-comic-2
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description align with included files and a small TypeScript helper (merge-to-pdf.ts). Requiring a JS/TS runtime via bun or npx is coherent for running local scripts. One oddity: the ohmsha preset mandates using Doraemon characters by default, which is a surprising/legal design decision not implied by the general 'knowledge comic' purpose.
!
Instruction Scope
SKILL.md instructs the agent to perform a blocking first-time setup that must complete before any other workflow and to write EXTEND.md either to the project (.baoyu-skills/) or the user's home (~/.baoyu-skills/). The skill also requires computing its baseDir and executing TypeScript scripts via bun/npx. These are within a comic workflow but expand scope to creating/modifying files in the user's home and to executing local scripts — actions the user should explicitly approve.
Install Mechanism
No install spec is provided (instruction-only), which is lower risk. However runtime execution depends on bun or npx; using npx could download and run code on demand. There is one small included script (scripts/merge-to-pdf.ts) — the code should be inspected before running, but no external arbitrary-download install step was found.
Credentials
The skill requests no environment variables or credentials. The only peripheral requirement is write access to a preferences file location (project or user scope) which is proportionate for storing user preferences.
!
Persistence & Privilege
The skill writes persistent configuration (EXTEND.md) and forces the first-time setup to complete before other actions; it offers to save to ~/.baoyu-skills/ by default. While not an elevated system privilege, this persistent user-level presence and mandatory blocking behavior should be acceptable to the user and explicitly granted. The skill does not set always:true or modify other skills.
What to consider before installing
This skill appears to implement a coherent comic-creation workflow, but review the following before installing: - Inspect included scripts (scripts/merge-to-pdf.ts) to confirm they do only local PDF merging and contain no unexpected network calls or harmful shell commands. Running the skill will execute TypeScript via bun or npx, which can run arbitrary code. - The first-time setup is blocking and will create EXTEND.md either in the project (.baoyu-skills/) or in your home directory (~/.baoyu-skills/). If you don't want files written to your home, prepare to choose the project-scoped save or run in an isolated environment. - The ohmsha preset explicitly defaults to using Doraemon characters unless you override it. That is a copyright/branding concern — if you need legally clean outputs, change presets or character defaults before generating content. - There are no requested secrets/credentials, which is good, but be cautious about where image generation is performed: SKILL.md relies on the agent's image-generation capability but does not specify a provider or endpoint. Understand which image service your agent will call and how generated images are stored or transmitted. If you want this skill but are uncomfortable with the defaults: run it in a sandbox/container, or pre-create an EXTEND.md (project-scoped) to avoid the blocking setup; and override the ohmsha character defaults. If you can share the merge-to-pdf.ts contents or any other scripts, I can re-check for network IO or suspicious operations and raise/lower my confidence.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Any binbun, npx
latestvk9777nm1w13g5wa6v1s78grr85837vtf
268downloads
0stars
2versions
Updated 22h ago
v0.1.1
MIT-0

Knowledge Comic Creator

Create original knowledge comics with flexible art style × tone combinations.

Usage

/baoyu-comic posts/turing-story/source.md
/baoyu-comic article.md --art manga --tone warm
/baoyu-comic  # then paste content

Options

Visual Dimensions

OptionValuesDescription
--artligne-claire (default), manga, realistic, ink-brush, chalkArt style / rendering technique
--toneneutral (default), warm, dramatic, romantic, energetic, vintage, actionMood / atmosphere
--layoutstandard (default), cinematic, dense, splash, mixed, webtoonPanel arrangement
--aspect3:4 (default, portrait), 4:3 (landscape), 16:9 (widescreen)Page aspect ratio
--langauto (default), zh, en, ja, etc.Output language

Partial Workflow Options

OptionDescription
--storyboard-onlyGenerate storyboard only, skip prompts and images
--prompts-onlyGenerate storyboard + prompts, skip images
--images-onlyGenerate images from existing prompts directory
--regenerate NRegenerate specific page(s) only (e.g., 3 or 2,5,8)

Details: references/partial-workflows.md

Art Styles (画风)

Style中文Description
ligne-claire清线Uniform lines, flat colors, European comic tradition (Tintin, Logicomix)
manga日漫Large eyes, manga conventions, expressive emotions
realistic写实Digital painting, realistic proportions, sophisticated
ink-brush水墨Chinese brush strokes, ink wash effects
chalk粉笔Chalkboard aesthetic, hand-drawn warmth

Tones (基调)

Tone中文Description
neutral中性Balanced, rational, educational
warm温馨Nostalgic, personal, comforting
dramatic戏剧High contrast, intense, powerful
romantic浪漫Soft, beautiful, decorative elements
energetic活力Bright, dynamic, exciting
vintage复古Historical, aged, period authenticity
action动作Speed lines, impact effects, combat

Preset Shortcuts

Presets with special rules beyond art+tone:

PresetEquivalentSpecial Rules
--style ohmsha--art manga --tone neutralVisual metaphors, NO talking heads, gadget reveals
--style wuxia--art ink-brush --tone actionQi effects, combat visuals, atmospheric elements
--style shoujo--art manga --tone romanticDecorative elements, eye details, romantic beats

Compatibility Matrix

Art Style✓✓ Best✓ Works✗ Avoid
ligne-claireneutral, warmdramatic, vintage, energeticromantic, action
manganeutral, romantic, energetic, actionwarm, dramaticvintage
realisticneutral, warm, dramatic, vintageactionromantic, energetic
ink-brushneutral, dramatic, action, vintagewarmromantic, energetic
chalkneutral, warm, energeticvintagedramatic, action, romantic

Details: references/auto-selection.md

Auto Selection

Content signals determine default art + tone + layout (or preset):

Content SignalsRecommended
Tutorial, how-to, programming, educationalohmsha preset
Pre-1950, classical, ancientrealistic + vintage
Personal story, mentorligne-claire + warm
Martial arts, wuxiawuxia preset
Romance, school lifeshoujo preset
Biography, balancedligne-claire + neutral

When preset is recommended: Load references/presets/{preset}.md and apply all special rules.

Details: references/auto-selection.md

Script Directory

Important: All scripts are located in the scripts/ subdirectory of this skill.

Agent Execution Instructions:

  1. Determine this SKILL.md file's directory path as {baseDir}
  2. Script path = {baseDir}/scripts/<script-name>.ts
  3. Replace all {baseDir} in this document with the actual path
  4. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun

Script Reference:

ScriptPurpose
scripts/merge-to-pdf.tsMerge comic pages into PDF

File Structure

Output directory: comic/{topic-slug}/

  • Slug: 2-4 words kebab-case from topic (e.g., alan-turing-bio)
  • Conflict: append timestamp (e.g., turing-story-20260118-143052)

Contents:

FileDescription
source-{slug}.{ext}Source files
analysis.mdContent analysis
storyboard.mdStoryboard with panel breakdown
characters/characters.mdCharacter definitions
characters/characters.pngCharacter reference sheet
prompts/NN-{cover|page}-[slug].mdGeneration prompts
NN-{cover|page}-[slug].pngGenerated images
{topic-slug}.pdfFinal merged PDF

Language Handling

Detection Priority:

  1. --lang flag (explicit)
  2. EXTEND.md language setting
  3. User's conversation language
  4. Source content language

Rule: Use user's input language or saved language preference for ALL interactions:

  • Storyboard outlines and scene descriptions
  • Image generation prompts
  • User selection options and confirmations
  • Progress updates, questions, errors, summaries

Technical terms remain in English.

Workflow

Progress Checklist

Comic Progress:
- [ ] Step 1: Setup & Analyze
  - [ ] 1.1 Preferences (EXTEND.md) ⛔ BLOCKING
    - [ ] Found → load preferences → continue
    - [ ] Not found → run first-time setup → MUST complete before other steps
  - [ ] 1.2 Analyze, 1.3 Check existing
- [ ] Step 2: Confirmation - Style & options ⚠️ REQUIRED
- [ ] Step 3: Generate storyboard + characters
- [ ] Step 4: Review outline (conditional)
- [ ] Step 5: Generate prompts
- [ ] Step 6: Review prompts (conditional)
- [ ] Step 7: Generate images ⚠️ CHARACTER REF REQUIRED
  - [ ] 7.1 Generate character sheet FIRST → characters/characters.png
  - [ ] 7.2 Generate pages WITH --ref characters/characters.png
- [ ] Step 8: Merge to PDF
- [ ] Step 9: Completion report

Flow

Input → [Preferences] ─┬─ Found → Continue
                       │
                       └─ Not found → First-Time Setup ⛔ BLOCKING
                                      │
                                      └─ Complete setup → Save EXTEND.md → Continue
                                                                              │
        ┌─────────────────────────────────────────────────────────────────────┘
        ↓
Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard → [Review?] → Prompts → [Review?] → Images → PDF → Complete

Step Summary

StepActionKey Output
1.1Load EXTEND.md preferences ⛔ BLOCKING if not foundConfig loaded
1.2Analyze contentanalysis.md
1.3Check existing directoryHandle conflicts
2Confirm style, focus, audience, reviewsUser preferences
3Generate storyboard + charactersstoryboard.md, characters/
4Review outline (if requested)User approval
5Generate promptsprompts/*.md
6Review prompts (if requested)User approval
7.1Generate character sheet FIRSTcharacters/characters.png
7.2Generate pages with character ref*.png files
8Merge to PDF{slug}.pdf
9Completion reportSummary

Step 7: Image Generation ⚠️ CRITICAL

Character reference is MANDATORY for visual consistency.

7.1 Generate character sheet first:

  • Backup rule: If characters/characters.png exists, rename to characters/characters-backup-YYYYMMDD-HHMMSS.png
  • Invoke an installed image generation skill such as baoyu-image-gen
  • Read that skill's SKILL.md and follow its documented interface rather than calling its scripts directly
  • Use characters/characters.md as the prompt-file input
  • Save output to characters/characters.png
  • Use aspect ratio 4:3

Compress character sheet (recommended): Compress to reduce token usage when used as reference image:

  • Use available image compression skill (if any)
  • Or system tools: pngquant, optipng, sips (macOS)
  • Keep PNG format, lossless compression preferred

7.2 Generate each page WITH character reference:

Skill CapabilityStrategy
Supports --refPass characters/characters.png with EVERY page
No --ref supportPrepend character descriptions to EVERY prompt file

Backup rules for page generation:

  • If prompt file exists: rename to prompts/NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.md
  • If image file exists: rename to NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png
  • Invoke the installed image generation skill for each page
  • Use prompts/01-page-xxx.md as the prompt-file input
  • Save output to 01-page-xxx.png
  • Use aspect ratio 3:4
  • If the chosen skill supports reference images, pass characters/characters.png as --ref

Full workflow details: references/workflow.md

EXTEND.md Paths ⛔ BLOCKING

CRITICAL: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to content analysis, do NOT ask about art style, do NOT ask about tone — ONLY complete the preferences setup first.

PathLocation
.baoyu-skills/baoyu-comic/EXTEND.mdProject directory
$HOME/.baoyu-skills/baoyu-comic/EXTEND.mdUser home
ResultAction
FoundRead, parse, display summary → Continue
Not foundBLOCKING: Run first-time setup ONLY (references/config/first-time-setup.md) → Complete and save EXTEND.md → Then continue

EXTEND.md Supports: Watermark | Preferred art/tone/layout | Custom style definitions | Character presets | Language preference

Schema: references/config/preferences-schema.md

References

Core Templates:

Style Definitions:

  • references/art-styles/ - Art styles (ligne-claire, manga, realistic, ink-brush, chalk)
  • references/tones/ - Tones (neutral, warm, dramatic, romantic, energetic, vintage, action)
  • references/presets/ - Presets with special rules (ohmsha, wuxia, shoujo)
  • references/layouts/ - Layouts (standard, cinematic, dense, splash, mixed, webtoon)

Workflow:

Config:

Page Modification

ActionSteps
EditUpdate prompt file FIRST--regenerate N → Regenerate PDF
AddCreate prompt at position → Generate with character ref → Renumber subsequent → Update storyboard → Regenerate PDF
DeleteRemove files → Renumber subsequent → Update storyboard → Regenerate PDF

IMPORTANT: When updating pages, ALWAYS update the prompt file (prompts/NN-{cover|page}-[slug].md) FIRST before regenerating. This ensures changes are documented and reproducible.

Notes

  • Image generation: 10-30 seconds per page
  • Auto-retry once on generation failure
  • Use stylized alternatives for sensitive public figures
  • Maintain style consistency via session ID
  • Step 2 confirmation required - do not skip
  • Steps 4/6 conditional - only if user requested in Step 2
  • Step 7.1 character sheet MUST be generated before pages - ensures consistency
  • Step 7.2 EVERY page MUST reference characters - use --ref or embed descriptions
  • Watermark/language configured once in EXTEND.md

Comments

Loading comments...