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 kezd088/100x-skill-tiktok --skill 100x-visual-fissiongit clone --depth 1 https://github.com/kezd088/100x-skill-tiktokWrote 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/kezd088/100x-skill-tiktok/100x-visual-fission)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-visual-fission"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-visual-fission/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/kezd088/100x-skill-tiktok/100x-visual-fission"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-visual-fission.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00165 | $0.02275 |
| Opus 5 | $0.00082 | $0.01137 |
| Sonnet 5 | $0.00033 | $0.00455 |
| Haiku 4.5 | $0.00016 | $0.00228 |
Grade A, and why
100x-visual-fission 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-visual-fission
一句话定位
输入 ≥2 条同系列人物/场景参考(反推 JSON 或文字降级描述)+ 产品文案,输出锁定人物/场景/ 产品身份的媒介裂变提示词矩阵:单帧/首尾/首中尾/数日见效四选一媒介结构 × VTP 原版 A/B/C 机位预设,附固定负面词常量。属于 100x 体系 L2 创意生成层,对应"5 视觉裂变"这一步。
何时触发
用户说:
- "帮我裂变这条视觉参考" / "这个产品出几个变体" / "生成裂变提示词矩阵" / "媒介裂变" / "视觉裂变"
- "fission this reference" / "generate prompt variants for this product" / "multiply this reference image into variants"
- 或直接给一组已反推的人物/场景 JSON(或文字描述)+ 产品文案,要求出一套裂变提示词
输入
最小输入(类别 A,硬性必填,两项都要):references[]——至少 2 条同系列的人物/场景
参考材料,可以是已完成的 VTP 反推 JSON(vtp_prompts_01/02 schema),也可以是没有真实
参考图时的文字描述降级(需在产出的 source_material_note 里如实标注);product_brief——
产品名+品类+效果叙事文本。少于 2 条参考无法做"提取共性"(分不清哪些在变),会被拒绝,
详见 workflow.md Phase 1 类别 A 校验。
软性补充(类别 B,缺失走默认值,见 workflow.md):aspect_ratios_wanted(默认
["9:16"])、variant_count(默认 2,这是 VTP 04 步用户自由指定的参数,不是本 skill
的结构性判据)。
上游可选产出(类别 C,缺失静默跳过,不阻塞,也绝不要求用户先跑别的 skill):
100x-persona 产出的 PersonaSceneBundle(若已存在,直接复用其身份锚点,跳过反推)。
输出
结构见 schema.json:constants(人物/场景/产品三锚点)+ variables(VTP 03 步的
共性/变量提取)+ media_plan(四选一媒介结构 + 帧计划)+ prompt_sets(VTP 04 步生成
的 N 组提示词)+ fission_variants(VTP 06 步机位裂变,每帧至少一条)+ negative_prompt
(VTP 07 步固定常量)+ meta。可选再渲染一张人类可读 Markdown 摘要(媒介结构 + 帧列表 +
每帧对应裂变条目)。
核心约束(4 条公理,详见 axioms.md)
- 人物/场景/产品三锚点是定量,必须逐字出现在每一个裂变分支里(子串包含检查是大小写
不敏感的字面匹配,不是语义等价判断——两段用词不同但描述同一个人的文字,或恰好共享
同一句泛泛套话的两件不同产品,都可能让这条检查产生假阴性/假阳性,见
axioms.md公理1) - 媒介裂变轴(单帧/首尾/首中尾/数日见效)叠加在 VTP 原版机位/灯光/调色三档轴之上,
不是替换——这是本 skill 与 VTP 原设计的核心差异点(已知局限:媒介结构判定要求
multi_day分支的理由必须引用一个数字,但机器验证不了这个数字是否忠实反映输入叙事, 见axioms.md公理 2 TODO) - 每一帧计划必须真的被至少一条裂变产物渲染出来,裂变产物引用的来源必须真实存在—— 规划了却没渲染,或渲染了却指向不存在的规划,都判 FAIL
- 每条落地提示词固定负面词常量 + 真实感兜底后缀,不得把不可视化/夸大宣称原句抄进画面
描述(已知局限:不可视化宣称关键词表目前只在保健品类目的英语+西语真实语料上验证过,
跨更多品类大概率需要扩表,见
axioms.md公理 4 TODO)
三阶段流程
详见 workflow.md:Phase 1 接收+校验(类别 A/B/C + 不可视化宣称预检测)→ Phase 2(VTP
七步骨架:01/02 反推或降级 → 03 提取共性 → 媒介结构判定(本 skill 新增) → 04 生成
N 组提示词 → 06 机位裂变 → 07 固定负面词 → 逐条自检)→ Phase 3 用户触发的返工(L1 单条 /
L2 单帧或结构级 / L3 全体)。
What ships with it
20 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.
- axioms.md 19 KB
- evals/example-01-digestive-comfort-multiday.json 11 KB
- evals/example-02-waistline-headtail.json 6.0 KB
- evals/example-03-energy-vial-headmidtail.json 7.4 KB
- evals/example-04-circulacion-multiday-es.json 7.7 KB
- evals/example-05-piernas-headtail-es.json 5.3 KB
- evals/example-06-dormir-headmidtail-es.json 6.3 KB
- metadata.json 7.7 KB
- package-lock.json 2.4 KB
- package.json 986 B
- schema.json 18 KB
- scripts/validate.js 35 KB runs code
- sources.md 15 KB
- test-corpus-samples/bundle-01-v000614-male-vitality-multiday-en.json 9.1 KB
- test-corpus-samples/bundle-02-v000615-circulation-headtail-en.json 6.5 KB
- test-corpus-samples/bundle-03-v001027-nad-singleframe-en.json 6.0 KB
- test-corpus-samples/bundle-04-v000647-circulacion-multiday-es.json 9.9 KB
- test-corpus-samples/bundle-05-v000646-piernas-headtail-es.json 7.3 KB
- test-corpus-samples/bundle-06-v001053-energia-singleframe-es.json 7.2 KB
- workflow.md 16 KB
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 · 112 lines · 165 tokens per session scan A edc684a2be7a
100x-visual-fission is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 15d ago), licensed MIT. It adds 165 tokens to every session and 2,275 once invoked, about $0.0008 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 2026-08-31.
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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.