hermes-agent/website/docs/user-guide/skills/optional/creative/creative-baoyu-comic.md
Siddharth Balyan 5eea87882a
Clarify: one question shape and one result shape on every surface (skip, cancel, timeout and undelivered are told apart) (#127760)
* refactor(desktop): split clarify-tool.tsx into a clarify/ folder

Pure moves, no behaviour change. Parsing, the question-card core
(shell, choice rows, question block), the delivery watchdog, and each
pending/settled card get their own file so the core can be reused.

* feat(clarify): one questions[] shape with per-question status and one outcome

The clarify tool now takes only questions=[{question, choices?, multi_select?}].
A wrong shape is a tool error that names the right one, so a model that
sends the old top-level question/choices corrects itself on the next call.

Every result has the same shape on every surface: each response carries
status (answered, skipped, unanswered) with user_response null unless
answered, and the result carries one outcome (submitted, cancelled,
timed_out, undelivered) plus an optional surface-written notice. The
timeout and cancel sentences that used to pose as the user's answer are
gone, and the compressor reads status instead of matching their prefixes.

The callback contract is callback(questions) -> {answers, outcome, notice?}
(None = skipped, missing qid = unanswered). tui_gateway settles a batch the
same way for the last lock, a cancel, an interrupt and the deadline, and
clarify.lock keeps a null answer as a skip. A multi-select answer that is
not a JSON array counts as one typed ("Other") answer. The tool-row preview
reads the first question.

* feat(clarify): every surface asks through the one question card

CLI: the batch panel is the only panel; Enter on an empty field skips a
question, Ctrl+C cancels and keeps the locked answers, the deadline returns
timed_out. -q and -z return undelivered with a no-user notice.

Ink TUI: the single-question prompt is gone; the card supports multi-select
(Space or a digit toggles, Enter locks, typed Other text joins the picks),
an empty submit skips, Esc cancels, and "Batch" names are dropped.

Desktop: the single-question card is deleted and its keyboard handling moved
into the one card (arrows, letters and digits, auto-advance, Enter picks then
confirms). Confirm enables at one answer; blank questions lock null; Skip and
a composer message cancel; the settled card shows No answer for unanswered
questions. The bots room card follows the same contract.

Messaging: one card per question with a "Reply skip to skip" line in every
locale; timeouts and delivery failures map to timed_out and undelivered.

* fix(clarify): cancelled for a released messaging card, labels win over the skip word

A prose reply to a messaging choice card, /new and session end released
the wait with "", which read as timed_out. They now resolve with a
CANCELLED marker and the tool gets outcome cancelled.

A typed reply that matches a choice label ("Skip") now resolves to that
choice; the skip word applies only when no choice matches.

The bots room card sends the picked labels as they are; the tool already
strips the recommendation label. Unused OUTCOMES and a new docstring and
comment are removed.

* fix(tui): re-editing a multi-select answer keeps its picks

The Ink card stored a multi-select answer as display text ("A, B"), so
revisiting the question put the whole string into Other and re-locked it
as one item. The answers map now keeps the raw JSON array, the card
restores the picks on revisit, and only the display lines format it.

Comments that earlier edits reworded are restored to their original
words, minus the phrases the change made wrong. The compute-host clarify
lock accepts None for a skipped question.

* test(clarify): align three checks with the one-answer confirm and the regenerated keys

The desktop Cmd+Enter test now expects a send with one answer (the blank
question locks null), the compressor test expects the single-answer summary
the code gives, and locales/_keys.desktop.json is regenerated for the
removed and added clarify strings.

* test(tui): the one-question card header is singular
2026-09-29 18:33:44 +05:30

16 KiB
Raw Permalink Blame History

title sidebar_label description
Baoyu Comic — Knowledge comics (知识漫画): educational, biography, tutorial Baoyu Comic Knowledge comics (知识漫画): educational, biography, tutorial

{/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}

Baoyu Comic

Knowledge comics (知识漫画): educational, biography, tutorial.

Skill metadata

Source Optional — install with hermes skills install official/creative/baoyu-comic
Path optional-skills/creative/baoyu-comic
Version 1.56.1
Author 宝玉 (JimLiu)
License MIT
Platforms linux, macos, windows
Tags comic, knowledge-comic, creative, image-generation

Reference: full SKILL.md

:::info The following is the complete skill definition that Hermes loads when this skill is triggered. This is what the agent sees as instructions when the skill is active. :::

Knowledge Comic Creator

Adapted from baoyu-comic for Hermes Agent's tool ecosystem.

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

When to Use

Trigger this skill when the user asks to create a knowledge/educational comic, biography comic, tutorial comic, or uses terms like "知识漫画", "教育漫画", or "Logicomix-style". The user provides content (text, file path, URL, or topic) and optionally specifies art style, tone, layout, aspect ratio, or language.

Reference Images

Hermes' image_generate tool is prompt-only — it accepts a text prompt and an aspect ratio, and returns an image URL. It does NOT accept reference images. When the user supplies a reference image, use it to extract traits in text that get embedded in every page prompt:

Intake: Accept file paths when the user provides them (or pastes images in conversation).

  • File path(s) → copy to refs/NN-ref-{slug}.{ext} alongside the comic output for provenance
  • Pasted image with no path → ask the user for the path via clarify, or extract style traits verbally as a text fallback
  • No reference → skip this section

Usage modes (per reference):

Usage Effect
style Extract style traits (line treatment, texture, mood) and append to every page's prompt body
palette Extract hex colors and append to every page's prompt body
scene Extract scene composition or subject notes and append to the relevant page(s)

Record in each page's prompt frontmatter when refs exist:

references:
  - ref_id: 01
    filename: 01-ref-scene.png
    usage: style
    traits: "muted earth tones, soft-edged ink wash, low-contrast backgrounds"

Character consistency is driven by text descriptions in characters/characters.md (written in Step 3) that get embedded inline in every page prompt (Step 5). The optional PNG character sheet generated in Step 7.1 is a human-facing review artifact, not an input to image_generate.

Options

Visual Dimensions

Option Values Description
Art ligne-claire (default), manga, realistic, ink-brush, chalk, minimalist Art style / rendering technique
Tone neutral (default), warm, dramatic, romantic, energetic, vintage, action Mood / atmosphere
Layout standard (default), cinematic, dense, splash, mixed, webtoon, four-panel Panel arrangement
Aspect 3:4 (default, portrait), 4:3 (landscape), 16:9 (widescreen) Page aspect ratio
Language auto (default), zh, en, ja, etc. Output language
Refs File paths Reference images used for style / palette trait extraction (not passed to the image model). See Reference Images above.

Partial Workflow Options

Option Description
Storyboard only Generate storyboard only, skip prompts and images
Prompts only Generate storyboard + prompts, skip images
Images only Generate images from existing prompts directory
Regenerate N Regenerate specific page(s) only (e.g., 3 or 2,5,8)

Details: references/partial-workflows.md

Art, Tone & Preset Catalogue

  • Art styles (6): ligne-claire, manga, realistic, ink-brush, chalk, minimalist. Full definitions at references/art-styles/<style>.md.

  • Tones (7): neutral, warm, dramatic, romantic, energetic, vintage, action. Full definitions at references/tones/<tone>.md.

  • Presets (5) with special rules beyond plain art+tone:

    Preset Equivalent Hook
    ohmsha manga + neutral Visual metaphors, no talking heads, gadget reveals
    wuxia ink-brush + action Qi effects, combat visuals, atmospheric
    shoujo manga + romantic Decorative elements, eye details, romantic beats
    concept-story manga + warm Visual symbol system, growth arc, dialogue+action balance
    four-panel minimalist + neutral + four-panel layout 起承转合 structure, B&W + spot color, stick-figure characters

    Full rules at references/presets/<preset>.md — load the file when a preset is picked.

  • Compatibility matrix and content-signal → preset table live in references/auto-selection.md. Read it before recommending combinations in Step 2.

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:

File Description
source-{slug}.md Saved source content (kebab-case slug matches the output directory)
analysis.md Content analysis
storyboard.md Storyboard with panel breakdown
characters/characters.md Character definitions
characters/characters.png Character reference sheet (downloaded from image_generate)
prompts/NN-{cover|page}-[slug].md Generation prompts
NN-{cover|page}-[slug].png Generated images (downloaded from image_generate)
refs/NN-ref-{slug}.{ext} User-supplied reference images (optional, for provenance)

Language Handling

Detection Priority:

  1. User-specified language (explicit option)
  2. User's conversation language
  3. Source content language

Rule: Use user's input language 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 Analyze content
  - [ ] 1.2 Check existing directory
- [ ] 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
  - [ ] 7.1 Generate character sheet (if needed) → characters/characters.png
  - [ ] 7.2 Generate pages (with character descriptions embedded in prompt)
- [ ] Step 8: Completion report

Flow

Input → Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard → [Review?] → Prompts → [Review?] → Images → Complete

Step Summary

Step Action Key Output
1.1 Analyze content analysis.md, source-{slug}.md
1.2 Check existing directory Handle conflicts
2 Confirm style, focus, audience, reviews User preferences
3 Generate storyboard + characters storyboard.md, characters/
4 Review outline (if requested) User approval
5 Generate prompts prompts/*.md
6 Review prompts (if requested) User approval
7.1 Generate character sheet (if needed) characters/characters.png
7.2 Generate pages *.png files
8 Completion report Summary

User Questions

Use the clarify tool to confirm options. Put independent questions in one questions array (up to 5); ask separately any question whose options depend on an earlier answer. See references/workflow.md for the full Step 2 question set.

Timeout handling (CRITICAL): clarify can return "outcome": "timed_out" with responses marked "status": "unanswered" — this is NOT user consent to default everything.

  • Treat it as a default for the unanswered questions only. Each question is an independent consent point.
  • Surface the default to the user visibly in your next message so they have a chance to correct it: e.g. "Style: defaulted to ohmsha preset (clarify timed out). Say the word to switch." — an unreported default is indistinguishable from never having asked.
  • Do NOT collapse Step 2 into a single "use all defaults" pass after one timeout. If the user is genuinely absent, they will be equally absent for all five questions — but they can correct visible defaults when they return, and cannot correct invisible ones.

Step 7: Image Generation

Use Hermes' built-in image_generate tool for all image rendering. Its schema accepts only prompt and aspect_ratio (landscape | portrait | square); it returns a URL, not a local file. Every generated page or character sheet must therefore be downloaded to the output directory.

Prompt file requirement (hard): write each image's full, final prompt to a standalone file under prompts/ (naming: NN-{type}-[slug].md) BEFORE calling image_generate. The prompt file is the reproducibility record.

Aspect ratio mapping — the storyboard's aspect_ratio field maps to image_generate's format as follows:

Storyboard ratio image_generate format
3:4, 9:16, 2:3 portrait
4:3, 16:9, 3:2 landscape
1:1 square

Download step — after every image_generate call:

  1. Read the URL from the tool result
  2. Fetch the image bytes using an absolute output path, e.g. curl -fsSL "<url>" -o /abs/path/to/comic/<slug>/NN-page-<slug>.png
  3. Verify the file exists and is non-empty at that exact path before proceeding to the next page

Never rely on shell CWD persistence for -o paths. The terminal tool's persistent-shell CWD can change between batches (session expiry, TERMINAL_LIFETIME_SECONDS, a failed cd that leaves you in the wrong directory). curl -o relative/path.png is a silent footgun: if CWD has drifted, the file lands somewhere else with no error. Always pass a fully-qualified absolute path to -o, or pass workdir=<abs path> to the terminal tool. Incident Apr 2026: pages 06-09 of a 10-page comic landed at the repo root instead of comic/<slug>/ because batch 3 inherited a stale CWD from batch 2 and curl -o 06-page-skills.png wrote to the wrong directory. The agent then spent several turns claiming the files existed where they didn't.

7.1 Character sheet — generate it (to characters/characters.png, aspect landscape) when the comic is multi-page with recurring characters. Skip for simple presets (e.g., four-panel minimalist) or single-page comics. The prompt file at characters/characters.md must exist before invoking image_generate. The rendered PNG is a human-facing review artifact (so the user can visually verify character design) and a reference for later regenerations or manual prompt edits — it does not drive Step 7.2. Page prompts are already written in Step 5 from the text descriptions in characters/characters.md; image_generate cannot accept images as visual input.

7.2 Pages — each page's prompt MUST already be at prompts/NN-{cover|page}-[slug].md before invoking image_generate. Because image_generate is prompt-only, character consistency is enforced by embedding character descriptions (sourced from characters/characters.md) inline in every page prompt during Step 5. The embedding is done uniformly whether or not a PNG sheet is produced in 7.1; the PNG is only a review/regeneration aid.

Backup rule: existing prompts/…md and …png files → rename with -backup-YYYYMMDD-HHMMSS suffix before regenerating.

Full step-by-step workflow (analysis, storyboard, review gates, regeneration variants): references/workflow.md.

References

Core Templates:

Style Definitions:

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

Workflow:

Page Modification

Action Steps
Edit Update prompt file FIRST → regenerate image → download new PNG
Add Create prompt at position → generate with character descriptions embedded → renumber subsequent → update storyboard
Delete Remove files → renumber subsequent → update storyboard

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.

Pitfalls

  • Image generation: 10-30 seconds per page; auto-retry once on failure
  • Always download the URL returned by image_generate to a local PNG — downstream tooling (and the user's review) expects files in the output directory, not ephemeral URLs
  • Use absolute paths for curl -o — never rely on persistent-shell CWD across batches. Silent footgun: files land in the wrong directory and subsequent ls on the intended path shows nothing. See Step 7 "Download step".
  • Use stylized alternatives for sensitive public figures
  • Step 2 confirmation required - do not skip
  • Steps 4/6 conditional - only if user requested in Step 2
  • Step 7.1 character sheet - recommended for multi-page comics, optional for simple presets. The PNG is a review/regeneration aid; page prompts (written in Step 5) use the text descriptions in characters/characters.md, not the PNG. image_generate does not accept images as visual input
  • Strip secrets — scan source content for API keys, tokens, or credentials before writing any output file