BF sogni-creative-agent-skill
Sogni Creative Agent Skill: agent skill and CLI for image, video, and music generation using Sogni AI's decentralized GPU network. Supports promptless RTX VSR image upscaling through 16K, promptless FlashVSR video upscaling to 1080p/1440p, one-click image-folder loop reels, personas (named people with saved reference photos and voice clips), persistent memories, custom personality, style transfer, angle synthesis, MiniMax H3/H3 Balanced/LightX2V Turbo/FastH3 Turbo/Seedance/HappyHorse/LTX/WAN video, music/lyrics, hosted chat, durable workflows, replay records, and multi-step creative workflows. Ask the agent to "draw", "generate", "create an image", "upscale an image", "upscale a video", "make a video/animate", "turn this image folder into a loop", "make music", "apply a style", or "generate me as a superhero".
Sogni Creative Agent Skill: agent skill and CLI for image, video, and music generation using Sogni AI's decentralized GPU network.
As a process F 54/100 · Will not run — References files that are not bundled: references/
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 13917 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 88, 94): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: references/
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 13917 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 43 steps, 1 vague phrases
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (18 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 821: 120–800 characters recommended
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 28 headings
- +3Step-by-step instructions: 43 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (13 of 13)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.