Seedance Storyboard Generator
liangdabiao/Seedance2-Storyboard-Generator
专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求：(1) 将文章/故事转换为视频脚本，(2) 生成Seedance 2.0分镜提示词，(3) 规划多集AI视频系列，(4) 为GPT-Image-2、Seedream、Nano Banana…
Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images.
Install Whalechan Image Character
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-character --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/whalechan-image-character .claude/skills/whalechan-image-character && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .claude/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-characterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-character --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/whalechan-image-character .agents/skills/whalechan-image-character && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .agents/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-character --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/whalechan-image-character .cursor/skills/whalechan-image-character && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .cursor/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Neko3000/deepseek-whalechan.git --path skills/whalechan-image-character--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-character --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/whalechan-image-character .gemini/skills/whalechan-image-character && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .gemini/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-characterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/whalechan-image-character .github/skills/whalechan-image-character && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .github/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Neko3000/deepseek-whalechan whalechan-image-character --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neko3000/deepseek-whalechan.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/whalechan-image-character .opencode/skills/whalechan-image-character && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "whalechan-image-character" agent skill from https://github.com/Neko3000/deepseek-whalechan/tree/main/skills/whalechan-image-character into .opencode/skills/whalechan-image-character/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whalechan-image-character", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
whalechan-image-character- GitHub stars
- 237
- Token cost
- ~2k tokens
- SKILL.md length
- 941 words
- Files
- 38 (incl. scripts, references, assets)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images.
- Works in 6 steps: Write the frozen schema v4 assignment… → Build each prompt from the normalized… → Route providers and references according… → …
- Whale-chan identity must stay recognizable while text
- SKILL.md covers Load guidance as needed, Resolve the request, Confirm before spending and Execute the confirmed assignment, plus 1 more section
- Calls python3
What it does
Whalechan Image Character is an agent skill from Neko3000/deepseek-whalechan. Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images. Use when Whale-chan identity must stay recognizable while text, language, background, transparency, style, action, outfit, proportions, or generation parallelism may use defaults or explicit user choices.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 44 other files, including scripts, reference files and assets (for example `agents/openai.yaml`).
It sits in Media & Creative, covering Comics and storyboards. It works with DeepSeek and Google Gemini. The repository describes itself as: Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite. The licence is MIT.
When your agent uses it
- Whale-chan identity must stay recognizable while text
- Generation parallelism may use defaults
- Explicit user choices
Example prompts
- “/whalechan-image-character”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Write the frozen schema v4 assignment described in references/assignment-schema.md, then validate and initialize it
- Build each prompt from the normalized assignment in this order: permanent identity → theme → proportion target → resolved style →…
- Route providers and references according to provider-routing.md. Use one provider call per candidate and stop after the first complete PASS.
- Run deterministic image validation against the frozen resolution mode, inspect the original resolution, measure the frozen proportion, and…
- Retry with one targeted correction at a time. Use at most 2 candidates per provider by default and 8 candidates per image total.
- Finalize through manage-run.py finalize. Preserve failed numbering gaps and report final paths, provider/model, effective prompt…
What it can do on your machine
Read from SKILL.md and the folder at commit 0917fd1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Whalechan Image Character loads about 2k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 941 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from Neko3000/deepseek-whalechan at commit 0917fd1, republished under its MIT licence (© Neko3000). 941 words, ~2,050 tokens.
Download SKILL.mdSave it as
.claude/skills/whalechan-image-character/SKILL.md (or your agent's skills folder). This skill also uses 37 other files; get the full folder from GitHub.- name
- whalechan-image-character
- description
- Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images. Use when Whale-chan identity must stay recognizable while text, language, background, transparency, style, action, outfit, proportions, or generation parallelism may use defaults or explicit user choices.
Whale-chan Image Character
Create verified Whale-chan PNGs. Preserve Whale-chan's permanent identity while resolving every visual dimension independently from the user's request, typed reference images, and canonical defaults. A custom value changes only its own field.
Load guidance as needed
- Read
references/assignment-schema.mdwhenever normalizing, confirming, or freezing a request. - Read
references/character-spec.mdbefore building prompts or deciding whether a requested customization preserves Whale-chan identity. - Read
references/form-profiles.mdwhen resolving or measuring proportions. The five bundled forms are recommended presets, not the only allowed ratios. - Read
references/reference-index.mdwhen selecting bundled or user-supplied references. - Read
references/provider-routing.mdbefore any provider call or parallel run. - Read
references/qa-rubric.mdbefore reviewing or promoting a candidate. - Treat
references/reference-catalog.jsonas the machine-readable authority for bundled paths, hashes, preset ratios, and preset acceptance ranges.
Resolve the request
Normalize the request into schema v4 before presenting a plan. Use the user's explicit instructions first, then references only for their declared roles, then canonical defaults for unresolved fields. Do not let a reference silently control unrelated dimensions.
Defaults remain:
- 3 images;
semi-chibi; canonical style; canonical maid outfit. - Warm ivory-beige solid background
#F5EADD; transparency off. - No visible text. When text is requested without a language, use
zh-Hans; do not translate or invent wording without confirmation. - Full-body centered composition,
1:1, PNG, provider-native resolution, sequential execution with parallelism 1. Prefer 1024×1024 when the selected provider exposes a compatible size control, but do not treat 1024×1024 as a default acceptance requirement.
The user may explicitly request any style, action, outfit, solid/custom/transparent background, exact multilingual text, measurable head ratio greater than 1.0, positive-integer aspect ratio, or exact positive pixel resolution. If the user gives only width and height, derive the aspect ratio; if both are given, require them to agree. Keep extreme but measurable ratios possible; disclose that ratios outside the five presets have no bundled proportion reference and may be harder to satisfy. Provider safety and technical limits still apply.
Input screenshots, chat logs, and dialogue supply subject matter only. They do not authorize copying UI, visible source text, avatars, brands, or visual style unless the user explicitly assigns those roles.
Give the run a kebab-case English name and every image a unique snake_case English name. When one request contains several images, freeze a complete image-level configuration for each one rather than asking workers to inherit unstated choices.
Confirm before spending
Before any image-generation or paid API call, show a compact plan containing:
输入类型与重点：<type>；<focus>
提取主题：<theme>
运行名称与输出位置：<run-name>；artifacts/whalechan-image-character/<run-name>/
图片清单：<name — subject, expression, action, composition>
逐图配置：<proportion; style; costume; background/alpha; exact text/languages or no text>
输出规格：<format; aspect ratio; provider-native with 1024×1024 recommendation, or exact WIDTH×HEIGHT>
参考图权限：<path/id — declared roles and instruction>
模型顺序：Codex → OpenAI → Nano Banana → Seedream
执行方式：<sequential/parallel; requested and currently effective parallelism>
数量与最大候选：<image count> × 8 = <maximum; confirmed run budget>Stop for explicit confirmation. Confirmation freezes image names/order, subjects, actions, composition, all resolved visual fields, typed references and hashes, output intent, execution request, and candidate budget. Provider-native resolution freezes the aspect ratio and provider-selection policy, not an exact pixel size; record the requested, provider-resolved, and actual output geometry for every candidate. Exact resolution freezes width and height. If requested parallelism cannot be known until execution, state that effective parallelism will be capped by 5, ready tasks, runtime worker slots, and provider limits.
More than 3 images normally exceeds the 24-candidate run budget. Show the raised estimate and require explicit approval. Any later material change requires a revised plan and renewed confirmation.
Show full SKILL.md (448 more words)Show less
Execute the confirmed assignment
Write the frozen schema v4 assignment described in
references/assignment-schema.md, then validate and initialize it:bash python3 scripts/manage-run.py validate-assignment --assignment <assignment.json> python3 scripts/manage-run.py init --assignment <assignment.json> \ --effective-parallelism <current-capacity>For the sequential default, omit the flag or use 1. For a parallel run, calculate current capacity from ready images, runtime worker slots, and provider limits before initialization; the recorded effective value may be lower than the confirmed request.
Build each prompt from the normalized assignment in this order: permanent identity → theme → proportion target → resolved style → expression/action/composition → resolved outfit → props/objects → resolved background and alpha → exact text directive → typed-reference role limits → anatomy/contact constraints → output format, aspect ratio, and resolution intent. Include canonical locks only for fields whose mode is
canonical.Route providers and references according to
provider-routing.md. Use one provider call per candidate and stop after the first complete PASS.Run deterministic image validation against the frozen resolution mode, inspect the original resolution, measure the frozen proportion, and complete the assignment-aware visual QA in
qa-rubric.md. Never resize or crop a candidate to make it pass. Promote only when automatic and visual verdicts both pass.Retry with one targeted correction at a time. Use at most 2 candidates per provider by default and 8 candidates per image total.
Finalize through
manage-run.py finalize. Preserve failed numbering gaps and report final paths, provider/model, effective prompt, references, and QA result.
For parallel execution, the main agent is the sole coordinator and manifest writer. Workers may generate and review different ready images in isolated staging directories, but must not mutate the manifest or promote finals. The coordinator serially records and promotes returned results. Never generate two candidates for the same image simultaneously. Request at most 5-way parallelism and downgrade safely when runtime capacity, dependencies, provider capability, or ready-image count is lower.
Hard stops
- Do not generate before explicit confirmation or exceed the confirmed budget.
- Do not weaken permanent Whale-chan identity, anatomy/contact checks, or assignment-specific QA merely because another field is custom.
- Do not accept missing, misspelled, illegible, additional, or wrong-language text. Source UI, signatures, watermarks, usernames, QR codes, and unconfirmed brand marks always fail.
- Do not silently drop a reference, role, alpha requirement, or other confirmed field because a provider lacks the capability; route forward or seek renewed confirmation.
- Do not silently resize, crop, or convert a provider-native result, and do not send an exact-resolution assignment to a provider that cannot guarantee its width and height.
- Do not route around a safety rejection. Record it as a run-level halt, stop new dispatch, and quarantine uncommitted in-flight results.
- Do not promote from automatic checks alone.
- Do not overwrite bundled references, prior runs, attempts, staging results, or final files.
© Neko3000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 37 other files (scripts, references, assets) in skills/whalechan-image-character of Neko3000/deepseek-whalechan.
- SKILL.md
- agents/openai.yaml
- assets/reference-images/chibi/0054_rice_identity_comic_rendered_isolated.webp
- assets/reference-images/chibi/0057_patting_full_belly_rendered_isolated.webp
- assets/reference-images/chibi/0067_angry_you_are_silly_reply_rendered_isolated.webp
- assets/reference-images/compact/0080_lounging_on_chair_rendered_isolated.webp
- assets/reference-images/compact/0102_intimate_relationship_question_rendered_isolated.webp
- assets/reference-images/compact/04_light_turn.webp
- assets/reference-images/semi-chibi/0015_data_still_in_brain_rendered_isolated.webp
- assets/reference-images/semi-chibi/0076_sitting_ready_on_chair_rendered_isolated.webp
- assets/reference-images/semi-chibi/0092_enduring_release_delay_rendered_isolated.webp
- assets/reference-images/standard/01_gentle_wave.webp
- assets/reference-images/standard/03_light_turning_step.webp
- assets/reference-images/standard/05_side_reclining_pose.webp
- … and 24 more
Open the folder on GitHubat commit 0917fd1
Compare with similar skills
Whalechan Image Character next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Whalechan Image Character this skillNeko3000/deepseek-whalechan | 237 | — | ~2k | Automated safety check: Pass | MIT | |
| Seedance Storyboard Generatorliangdabiao/Seedance2-Storyboard-Generator | 2.6k | — | ~2.2k | Automated safety check: Pass | None | |
| BrewreelFinderchangchang/brewreel | 162 | — | ~6.9k | Automated safety check: Pass | Apache-2.0 | |
| Model Routingfal-ai-community/skills | 251 | — | ~1.5k | Automated safety check: Pass | None | |
| ModLens Image Vision Bridgeliustack/modlens | 4.2k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Seedance Storyboard in Shanghai Animation Styleliangdabiao/smy-seedance-storyboard | 138 | — | ~3k | Automated safety check: Pass | None |
Similar skills
Brewreel
Finderchangchang/brewreel
精酿 · BrewReel：四种玩法。宣传片：做竖版产品宣传短片（1080x1920，15–45 秒，抖音/视频号/小红书）。用户要做产品宣传片、推广短视频、App 介绍视频、功能演示视频、上新短片、带货片头时使用。支持软件、餐饮、电商实物、教培、美业、文旅住宿六个行业，支持中英双语。你只写 storyboard.json，校验拦规则和行业合规，一条命令出片。口播配画面：用户有…
Model Routing
fal-ai-community/skills
Choose default fal.ai endpoint IDs for genmedia production skills.
ModLens Image Vision Bridge
liustack/modlens
Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.
Seedance Storyboard in Shanghai Animation Style
liangdabiao/smy-seedance-storyboard
Turns a story, novel or myth into a retro hand-drawn animation style short-drama script, episode breakdown, asset prompts and Seedance 2.0 storyboard prompts.
Space Storyboard Generator
SpaceZephyr/design-buddy
根据用户描述的故事内容，润色故事线并拆分为分镜脚本，批量生成风格一致的故事板插图。提供8种视觉风格选择，基于故事类型推荐最佳风格。调用Gemini API生成图片，保存到Obsidian图片目录。触发词："分镜故事"、"故事板"、"做个分镜"、"创建故事板"、"storyboard"、"画个故事"。
More from Neko3000/deepseek-whalechan
Whalechan Image Comic
Neko3000/deepseek-whalechan
Propose five DeepSeek Whale-chan comic concepts from text, screenshots, images, chat logs, or reasoning traces, then generate verified comics after the user selects concepts and separately confirms…
Related
Works with
Categories
Questions about Whalechan Image Character
What does Whalechan Image Character do?
Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images. Whalechan Image Character is an agent skill from Neko3000/deepseek-whalechan. Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images.
When should I use Whalechan Image Character?
Whalechan Image Character fits situations like: whale-chan identity must stay recognizable while text; generation parallelism may use defaults; explicit user choices.
How do I install Whalechan Image Character in Claude Code?
Run `npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a claude-code`. Or copy the skill folder (skills/whalechan-image-character in Neko3000/deepseek-whalechan) into .claude/skills/whalechan-image-character in your project. Claude Code loads it when a task matches its description.
How do I install Whalechan Image Character in Codex?
Run `npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a codex`. Or copy the skill folder (skills/whalechan-image-character in Neko3000/deepseek-whalechan) into .agents/skills/whalechan-image-character in your project. Codex loads it when a task matches its description.
Can I use Whalechan Image Character in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Neko3000/deepseek-whalechan --skill whalechan-image-character -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/whalechan-image-character, .gemini/skills/whalechan-image-character, .github/skills/whalechan-image-character and .opencode/skills/whalechan-image-character in your project.
What does Whalechan Image Character need to run?
Going by SKILL.md and its folder, Whalechan Image Character needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Whalechan Image Character access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Whalechan Image Character safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Whalechan Image Character use?
Whalechan Image Character is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Whalechan Image Character use?
About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
What are the alternatives to Whalechan Image Character?
Skills that share tags, products or a category with Whalechan Image Character: Seedance Storyboard Generator (liangdabiao/Seedance2-Storyboard-Generator, 2.6k stars), Brewreel (Finderchangchang/brewreel, 162 stars), Model Routing (fal-ai-community/skills, 251 stars) and ModLens Image Vision Bridge (liustack/modlens, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Whalechan Image Character?
Neko3000 (a GitHub user) maintains it in Neko3000/deepseek-whalechan, which has 237 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.
Source: Neko3000/deepseek-whalechan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.