跪拜 Guibai
← All articles
AIGC · AI Programming

Five Prompts, Zero Code: Running a Stick-Figure Video Skill in WorkBuddy to Three MP4s

By 小虎AI生活 ·
Read original on juejin.cn ↗ Google Translate ↗ Alt translation

Turning AI video generation into a repeatable, checkable pipeline means the outcome stops being a lottery: the planning comes from the model, but the pixels come from deterministic local code, and the character stays stable because the drawing rules are literal. The character-anchor trick also shows a cheap, effective way to fight AI inconsistency without heavier tooling.

Summary

WorkBuddy's stickman-video-director skill is not a single mega-prompt. It installs as a folder: SKILL.md plus 52 contract files in references/ and 41 scripts in scripts/. Each contract owns one concern, from style catalog to voice continuity, storyboard templates, and acceptance checklists. In director mode (the A mode tested here), a single sentence produces a full proposal: hook, five-beat emotional arc, three accent-color meanings, BGM direction, and an English narration split into 10-second blocks at 20–25 words per block.

The most notable piece is the character anchor. Instead of writing 'keep the character consistent', the skill emits a frozen specification: hollow circular head, no face, no eyes, black line art, exactly two arms and two legs, and a rule that raising an arm replaces the previous line, never leaving a resting arm underneath. The author reports this is precisely to stop the model from drawing an extra hand. Each of the three clip prompts is self-contained with 12 sections, so any of them can be dropped into any prompt-to-video tool.

Rendering happens locally via a Python script (PIL per-frame drawing plus an ffmpeg pipe) and purely on CPU. The outputs: a 30-second 1280×720 MP4 at 1.1MB and a 10-second 720×1280 MP4 at 0.43MB, both verified with ffprobe for H.264/AAC and exact durations. Switching to a second style (Style 2A) means swapping the entire character anchor and color discipline, not just renaming a style.

Takeaways
— The skill installs as a folder: SKILL.md, 52 contracts, 41 scripts.
— Director mode (A) outputs a proposal, storyboard, and three self-contained clip prompts, each requiring human confirmation before proceeding.
— The character anchor is a frozen textual spec of drawing rules; writing 'same character' doesn't work, but the exact block repeated three times does.
— Each clip prompt contains 12 sections including output spec, canvas, character lock, color scheme, composition, first-frame inheritance, three-beat action, narration, sound profile, BGM, end-frame handoff, and negative constraints, and works in any prompt-to-video tool.
— Local rendering uses a Python script (PIL + ffmpeg pipe), CPU-only, no video model or TTS calls.
— A 30-second 16:9 MP4 renders at 1280×720, 1.1MB; a 10-second 9:16 MP4 at 720×1280, 0.43MB; both pass ffprobe for H.264/AAC and exact durations.
— Switching aspect ratio requires re-layout (vertical stacking for 9:16), not cropping the 16:9 version.
— The production pack saves as a 16.9KB file, and six reusable text sets are provided in the post.
Conclusions

The character anchor treats consistency as an engineering spec instead of a model behavior to hope for; that's a generalizable pattern for any AI generation where identity must persist across segments.

The skill's structure as a set of single-purpose contracts plus acceptance checklists is what makes it repeatable; the model isn't being asked to remember the whole production, it's following a process with explicit gates.

Dividing the work into model-authored prompts and deterministic local rendering means the only AI-indeterminate part is the planning; the actual pixels are fixed, so the output is verifiable and editable.

The article shows a full workflow, but it also exposes a boundary: full auto mode (B) requires npm deps and a heavier environment; the author prefers reusing the prompt output with a local script, suggesting the skill's value is in the planning layer, not the renderer.

Concepts & terms
Agent Skill
A folder of instructions and contract files that an AI agent can load; here, SKILL.md plus references and scripts define a complete workflow with acceptance criteria.
Character anchor
A block of fully specified drawing rules frozen in text and reused verbatim across all prompts to keep a character visually consistent, preventing extra limbs or style drift.
Contract file
A single-purpose specification file in the skill's references folder, each covering one aspect such as style, sound continuity, storyboard template, or acceptance checklist.
Source: juejin.cn ↗ Google Translate ↗ Backup ↗