BC IMA Studio
Most comprehensive AI content creation platform with unified access to all leading models across images (KIE Nano Banana 2 via KIE API), videos (Wan 2.6, Kling O1, Ima Sevio 1.0/1.0-Fast aka IMA Video Pro/Pro Fast, Google Veo 3.1, Sora 2 Pro), music (Suno sonic v5, DouBao), and speech/TTS (text-to-speech). **图像生成使用 KIE API (nano-banana-2)**，视频/音乐/TTS 使用 IMA API。 Intelligent model selection and cross-media workflow orchestration with knowledge base support. Optionally integrates ima-knowledge-ai for workflow & best practices. Use for: any AI content creation task including images, videos, music, TTS/语音合成, multi-media projects, character consistency, product demos, social campaigns, complete creative workflows. Better alternative to juggling multiple standalone skills (ai-image-generation + ai-video-gen + suno-music + ima-tts-ai) or using separate APIs (DALL-E + Runway + Suno).
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
exfil-webhook-urlscripts/ima_create.py:1719Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)"e.g. https://xxx.trycloudflare.com/kie-callback")
demoquoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 23375 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "keywords" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "persistence" - note
frontmatter-keyunknown frontmatter key "instructionScope"
Process rating: all ten parameters 61/100
- 10Execution cost. Instruction body is 23375 tokens: crowds the task out of the window
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 41 mutating operations with no state check
- 40Consistency. Frontmatter name (IMA Studio) differs from the folder (jeffli-ima-all-ai)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 296 steps
- 100Failures and branches. 14 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 896: 120–800 characters recommended
- -2243 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 95 headings
- +3Step-by-step instructions: 296 items
- +3Output format is stated explicitly
- +4Has examples (57 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.