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 ip-cognition-script-polishergit 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/ip-cognition-script-polisher)<a href="https://agentmods.dev/skills/zkbys/whiteboard/ip-cognition-script-polisher"><img src="https://agentmods.dev/badge/skills/zkbys/whiteboard/ip-cognition-script-polisher/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/ip-cognition-script-polisher"><img src="https://agentmods.dev/badge/skills/zkbys/whiteboard/ip-cognition-script-polisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00104 | $0.00882 |
| Opus 5 | $0.00052 | $0.00441 |
| Sonnet 5 | $0.00021 | $0.00176 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
ip-cognition-script-polisher 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IP Cognition Script Polisher
Overview
Use this skill to turn a topic, rough opinion, or partial draft into a reviewable script package for IP incubation, business cognition, and AI cognition short videos. The output is not a final video; it is the upstream script contract for whiteboard infographic planning, voiceover timing, and later rendering.
Workflow
- Read the user's brief and extract the core stance, target audience, promised value, and any non-negotiable wording.
- Preserve the user's core viewpoint. Sharpen framing and rhythm, but do not reverse the stance or smuggle in a different conclusion.
- If the input is only a topic, infer a conservative thesis and make the inference explicit in
polished_voiceover.mdunderStance basis. - Produce exactly six voiceover segments in this role order:
hook,反常识,例子,转折,方法,结论. - Keep the total estimated voiceover length between 30 and 60 seconds. Default target is 45 seconds unless the user specifies otherwise.
- Add
spokenAnchorsandvisualIntentto every segment. Use anchors that appear verbatim in the segment text or caption. - Create only necessary visual beats. Do not turn every sentence into a board object; group the script into 3-6 strong visual ideas.
- Validate the package with the bundled script before handing it off.
Outputs
Write these files into the requested package directory, usually script/ inside a workflow project:
script/
├── polished_voiceover.md
├── voiceover_segments.json
└── visual_beats.json
voiceover_segments.json is the source of truth for narration. visual_beats.json is the source of truth for the next infographic-planning skill. polished_voiceover.md is the human review surface.
Segment Rules
hook: Start with a sharp, memorable tension. Avoid vague openings such as "今天聊聊".反常识: State the counterintuitive claim without overclaiming beyond the user's brief.例子: Use one concrete scene, comparison, or mini case. Prefer business/IP/AI operator details over generic life advice.转折: Reframe the issue and connect the example back to the core thesis.方法: Give a repeatable 2-4 step method, checklist, or decision rule.结论: End with a compact sentence that can become the final subtitle or board title.
What ships with it
8 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.
- agents/openai.yaml 282 B
- examples/input_brief.md 334 B
- examples/output/polished_voiceover.md 1.0 KB
- examples/output/visual_beats.json 3.5 KB
- examples/output/voiceover_segments.json 3.7 KB
- references/schema.md 2.2 KB
- references/script_patterns.md 1.9 KB
- scripts/validate_script_package.py 11 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.
- 9d ago First seen · 79 lines · 104 tokens per session scan A 6574c511531c
ip-cognition-script-polisher is a skill published in the GitHub repository zkbys/whiteboard (59 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 882 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.