BC higgsfield-product-photoshoot
Generate brand-quality product images via mode-specific prompt enhancement on Higgsfield's gpt_image_2 model. The single entry point for any professional brand visual involving a product. Use when: "make a product photo", "studio shot", "lifestyle photo", "in use", "Pinterest pin", "hero banner", "website header", "carousel", "Meta ads", "ad creatives", "model wearing", "virtual try-on", "person holding product", "closeup with hands", "levitating product", "floating", "splash shot", "CGI style", "surreal product", "restyle", "Christmas version", "in [aesthetic] style", or any request involving a product, brand, or paid social creative. Modes: product_shot, lifestyle_scene, closeup_product_with_person, pinterest_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the final prompt — never write gpt_image_2 prompts freehand. Always go through this skill. NOT for: raw text-to-image with no brand/product (use higgsfield-generate), branded marketing video with avatars (use higgsfield-generate's Marketing Studio), Soul Character training (use higgsfield-soul-id).
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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:39Pipe-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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1143 chars, limit 1024
Process rating: all ten parameters 64/100
- 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
- 50When it triggers. No condition that starts the skill
- 65Failures and branches. 3 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2027 tokens
- 100Running it twice. Mutating operations check current state
- low 12 top-level sections: this looks like several domains in one skill
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 1142: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 22 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 19 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.