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 maciejdzierzek/kling-ai-prompt-generator --skill kling-aigit clone --depth 1 https://github.com/maciejdzierzek/kling-ai-prompt-generatorWrote 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/maciejdzierzek/kling-ai-prompt-generator/kling-ai)<a href="https://agentmods.dev/skills/maciejdzierzek/kling-ai-prompt-generator/kling-ai"><img src="https://agentmods.dev/badge/skills/maciejdzierzek/kling-ai-prompt-generator/kling-ai/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/maciejdzierzek/kling-ai-prompt-generator/kling-ai"><img src="https://agentmods.dev/badge/skills/maciejdzierzek/kling-ai-prompt-generator/kling-ai.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 System Prompt Leakage · line 171 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00089 | $0.07992 |
| Opus 5 | $0.00044 | $0.03996 |
| Sonnet 5 | $0.00018 | $0.01598 |
| Haiku 4.5 | $0.00009 | $0.00799 |
Grade A, and why
kling-ai 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kling AI Video Generation
Source-of-truth for the facts in this skill: the official Kling release notes at kling.ai/release-note and the API pricing page at kling.ai/dev/pricing. Verified 2026-08-04. When numbers, durations, credit costs, or language lists matter for a deliverable, verify them there before quoting.
Scope: this skill covers Kling's video models. Kling also ships image models (the IMAGE 3.0 series, IMAGE O1, Image Series Mode, 2K/4K image output) - those are out of scope here; for still images use the nano-banana skill or check Kling's release notes directly.
Platform Access
Primary interface: app.klingai.com/global (or kling.ai/app)
Alternative platforms with Kling integration: Higgsfield, Pollo.ai, Fal.ai, Media.io, Artlist, Vidful.ai, Scenario, BasedLabs, LetzAI, PiAPI, kie.ai
Quick Start: Animate an Image in 60 Seconds
- Go to app.klingai.com/global - AI Videos - Image to Video
- Select VIDEO 3.0 (or VIDEO 3.0 Turbo if the shot has dialogue or you are generating a batch, or VIDEO 3.0 Omni if you have reference images / video elements to anchor identity)
- Upload your image
- Write a short motion prompt - describe only what moves, not the whole scene:
Subtle breeze moves through hair. Eyes blink naturally. Camera static. - Set duration: 5s for loops/social, 10-15s for narrative (3.0 supports up to 15s)
- Set output: 1080p Standard for drafts; switch to native 4K only for finals (4K costs ~30 credits/sec)
That's it. For model selection, advanced prompting, avatars, and multi-shot workflows - read on.
Model Lineup (as of August 2026)
| Model | Best For | Resolution | Audio | Max Duration | Released |
|---|---|---|---|---|---|
| VIDEO 3.0 | Cinematic storytelling, multi-shot, native audio, multilingual dialogue | up to 4K | Yes (5 langs) | 15s | 2026-01-31 |
| VIDEO 3.0 Turbo | Same job as 3.0 but faster and cheaper per second; strongest audio-visual sync and lip-sync | 720p / 1080p (no 4K) | Yes, always on | 15s | 2026-06-17 |
| VIDEO 3.0 Omni | VIDEO 3.0 capabilities + video element reference + element voice control + video editing | up to 4K | Yes (5 langs) | 15s | 2026-01-31 (editing upgraded 2026-06-17) |
| VIDEO 3.0 Motion Control | Motion transfer with high facial consistency, including occlusions and multi-angle | 1080p | Optional | 30s | 2026-03-04 |
| Avatar 2.0 | Talking avatars from 1 image + 1 audio file, up to 5 minutes | 1080p / 48fps | Lip-sync to provided audio | 5 min | 2025-12-04 |
| Kling 2.6 | Older Native Audio pipeline (EN+ZH), good fast/budget option | 1080p | EN + ZH | 10s | 2025-12-03 |
| Kling 2.5 Turbo | Fastest, simplest scenes, draft work | 1080p | No | 10s | earlier |
What ships with it
3 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.
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 · 485 lines · 89 tokens per session scan A f1819bb76555
kling-ai is a skill published in the GitHub repository maciejdzierzek/kling-ai-prompt-generator (28 stars, last pushed 29d ago), licensed MIT. It adds 89 tokens to every session and 7,992 once invoked, about $0.0004 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
vibe-creating-prompt
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…
autoclip
A local video tool that finds notable moments in long lectures, interviews, podcasts, or courses and turns them into short clips. It can use subtitles or transcribe the video, then render clips with ffmpeg, a video-processing program.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.