BB higgsfield-generate
Generate images and videos via Higgsfield AI through 30+ models including Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, GPT Image 2, plus Marketing Studio for branded ad video/image with curated avatars and imported products. Use when: "generate an image", "make a picture", "create artwork", "make a video", "animate this photo", "image-to-video", "img2vid", "edit this image with AI", "stylize a photo", "remix this image", "produce a clip", "render a scene", "create an ad", "make a UGC video", "generate marketing video", "make a product demo", "create unboxing", "TV spot", "virtual try-on", "product showcase", "brand video", "presenter video for product", "import product from URL", "create avatar for ad". Supports text-to-image, image-to-image, image-to-video, reference-based generation, and Marketing Studio (avatars + products + ad modes). Auto-detects whether passed IDs are uploads or previous jobs. Chain with higgsfield-soul-id when the user wants their face in the output. NOT for: training Soul Character (use higgsfield-soul-id), professional product photoshoots with mode-specific prompt enhancement (use higgsfield-product-photoshoot), text-only / chat / TTS tasks.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:38Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1207 chars, limit 1024
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 55 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2477 tokens
- low The response is described with custom markup (6 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 1206: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 24 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.