Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillnpx agentmods add skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facsWrote 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/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facs)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facs"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facs/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/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facs"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-facs.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 Prompt Injection · line 100 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00155 | $0.07163 |
| Opus 5 | $0.00077 | $0.03581 |
| Sonnet 5 | $0.00031 | $0.01433 |
| Haiku 4.5 | $0.00015 | $0.00716 |
Grade B, and why
higgsfield-facs scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
(`../higgsfield-seedance/SKILL.md` § Prompt-Craft Laws). Never tell the user a How it starts
The opening of the file, as written. The whole thing — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield FACS Director
Direct a face the way an animator does — by muscle, not by mood. FACS (the
Facial Action Coding System) names each facial movement as an Action Unit:
AU12 is the lip-corner puller (smile), AU6 is the cheek raiser, AU4 is the
brow lowerer. Put those codes in a Seedance 2.0 prompt and the model renders the
corresponding action. It is the highest-resolution facial control available on
the platform, and it is where forced smiles, uncanny faces, mixed emotions, and
honest micro-performance in close-up dialogue come from.
This skill is a facial-control layer on top of
../higgsfield-seedance/SKILL.md. Every FACS prompt is still a Seedance prompt — six-slot formula, Prompt-Craft Laws, preflight linter. FACS only changes how you specify the face: AU codes instead of (or alongside) emotion words. It is the muscle-level case of the Voice Rewrite rule "describe physics, not emotion."
QUICK FACTS
Routing aids — read the linked sections for the actual rules.
- FACS = facial expressions as Action Unit codes (muscle movements), not emotion labels; you write the codes into the prompt →
- Provenance split: the AU vocabulary is standard human science; Seedance's interpretation of codes in a prompt is [EMPIRICAL] — high success rate, not a guarantee →
- Plan first. Decide the 3–4 expressions you need → generate a FACS sheet for only those → write the codes. Generating the full 49-AU sheet and cherry-picking is the anti-pattern →
- 3–4 expressions max per generation. Accuracy drops as you stack more AUs into one clip →
- Two specification styles — codes-only (
AU12) vs codes + short anatomical description; test both, neither is universally better → - The reference sheet is a labelled-grid image (GPT Image 2 / Nano Banana Pro); the LLM can mislabel AUs, so iterate and verify →
- The character photo is optional — codes work without it; attach it only for identity consistency →
- Common emotions decompose to standard AU recipes (Duchenne smile = AU6+AU12; sadness = AU1+AU4+AU15) →
- The payoff is dialogue / monologue: AU-per-beat schedule, combined with the
[AUDIO: Xs]lip-sync block; every line gets pre / during / post-line beats → - [OFFICIAL] Body-level micro-beat recipes beyond the face (throat, breath, skin, posture) + the no-perfect-sync stagger (0.3–0.5s) and listeners-in-bokeh rules →
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 · 570 lines · 155 tokens per session scan B a49bf8a6bbe8
higgsfield-facs is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 155 tokens to every session and 7,163 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
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"…
dramaclaw
A skill for answering identity and self-introduction questions, and for working with the DramaClaw/NovelVideo pipeline. The description also covers turning novels or stories into short vertical videos.
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
kling-ai
Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…