Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zkbys/whiteboard --skill whiteboard-infographic-pipeline-orchestratorgit clone --depth 1 https://github.com/zkbys/whiteboardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zkbys/whiteboard/whiteboard-infographic-pipeline-orchestrator)<a href="https://agentmods.dev/skills/zkbys/whiteboard/whiteboard-infographic-pipeline-orchestrator"><img src="https://agentmods.dev/badge/skills/zkbys/whiteboard/whiteboard-infographic-pipeline-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zkbys/whiteboard/whiteboard-infographic-pipeline-orchestrator"><img src="https://agentmods.dev/badge/skills/zkbys/whiteboard/whiteboard-infographic-pipeline-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 22 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00212 | $0.03067 |
| Opus 5 | $0.00106 | $0.01533 |
| Sonnet 5 | $0.00042 | $0.00613 |
| Haiku 4.5 | $0.00021 | $0.00307 |
Grade A, and why
whiteboard-infographic-pipeline-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whiteboard Infographic Pipeline Orchestrator
使用场景
Use this skill when the user wants a complete AI 白板信息图讲解视频流水线 run from a topic text file, not another isolated B/C/D/E test. The expected result is a reviewable project directory containing the script package, infographic planning package, model-generated board images, D control package, E rendered video package, and an integration report.
This skill is an orchestrator. It does not replace the existing module Skills. It calls or guides them in a fixed order and enforces the fragile handoff rules between them.
自然语言一键入口
If the user gives a request like:
请使用白板总编排skill帮我做一个视频，我想表达的主题为“AI 工具越多，普通人反而越低效”，时长在30-60秒左右
Start the pipeline directly. Do not ask the user to prepare a separate input file.
Extract:
topic: text inside主题为..., quoted text, or the clearest stated idea.targetDurationSec: if the user says30-60秒, keep B's normal 30-60 second range and default target to about 45 seconds.style: default toIP孵化/商业认知/AI认知类短视频unless the user states another style.
When this internal module is called through the public whiteboard-video Skill, create the run folder under the user's current working directory:
whiteboard-runs/YYYYMMDD-HHMMSS-<topic-slug>/
For direct repository development runs, the legacy ignored location remains available:
orchestrator-runs/YYYYMMDD-HHMM-<topic-slug>/
Inside it, write the user's request into:
topic_input.txt
Then run the normal pipeline using that file as --topic-input and the run folder as --project-dir. Only ask a clarification if the request has no usable topic or gives mutually incompatible requirements. The manual image-download pause applies only when no automatic provider is configured or provider output fails validation.
输入要求
Required:
- Either a natural-language user request containing the topic, or a topic/source-script text file.
- A project output directory for one run. Through
whiteboard-video, default to<current-working-directory>/whiteboard-runs/; direct repository development may use ignoredorchestrator-runs/. - The local module Skill folders in the same workspace:
ip-cognition-script-polisher/ip-hand-drawn-infographic-planner/hand-drawn-infographic-creator/hand-drawn-infographic-video-board/whiteboard-infographic-video-renderer/
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/expected-output-tree.md 1.9 KB
- examples/minimal-topic-input.txt 491 B
- examples/natural-language-invocation.md 1.2 KB
- examples/test-case-ai-tools-overload-topic.txt 731 B
- examples/test-case-ai-tools-overload.md 4.9 KB
- README.md 3.0 KB
- references/contracts.md 8.3 KB
- references/runbook.md 11 KB
- scripts/check_asset_identity.py 5.9 KB runs code
- scripts/generate_board_images.py 15 KB runs code
- scripts/validate_orchestrator_inputs.py 5.8 KB runs code
- scripts/validate_release_candidate.py 22 KB runs code
- scripts/write_board_asset_manifest.py 8.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 199 lines · 212 tokens per session scan A f3193932b744
whiteboard-infographic-pipeline-orchestrator is a skill published in the GitHub repository zkbys/whiteboard (59 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 3,067 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…