BC sogni-gen

Generate images **and videos** using Sogni AI's decentralized network. Ask the agent to "draw", "generate", "create an image", or "make a video/animate" from a prompt or reference image.

modbender/skill-library-mcp Agent Skills author: modbender MIT 9 files body ≈ 5 189 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Generate images and videos using Sogni AI's decentralized network.

As a process C 57/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

Generator Media and videotype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

75/100

safety, quality, tests

Safety 60%: 79
Quality 40%: 69
Run on models: none yet

Process rating

57/100

Has gaps

Inputs and preconditions w 11: 0
Progress reporting w 2: 0
Running it twice w 4: 30

the three weakest of ten parameters · all ten

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.

For the model run — optional

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 · 21

✓ No critical or high findings

Medium and low: 21

low Secrets in code secret-high-entropy-token mcp-server.mjs:518

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
Uses SDXL Turbo (core…_ad) at 1024x1024 by default.
```
quoted
low Secrets in code secret-high-entropy-token mcp-server.mjs:533

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
description: 'Model ID (default: core…_ad)',
```
quoted
low Secrets in code secret-high-entropy-token mcp-server.mjs:745

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
core…_ad — Fast, face transfer (SDXL Turbo, default for --photobooth)
```
quoted
low Secrets in code secret-high-entropy-token mcp-server.mjs:752

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
Photobooth:       core…_ad
```
quoted
low Secrets in code secret-high-entropy-token openclaw.plugin.json:25

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"default": "core…_ad",
```
quoted
low Secrets in code secret-high-entropy-token package-lock.json:141

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…byA+l3XtsAj+Q8tf…oOo+X6HZ…Q8A==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:189

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…bSm+x6ETixtKZBh/qbRE…8Sr/Wcyx…yGA==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:237

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…UzJ+En8KcVm9Lk5+uGUQ…GXw==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:269

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…595+ujv0…pwV/GONa…zQo/1O6zRIkh0m/8+5Bjr…SZw==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:357

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…bUj+rBev…oyX+04WG…4jg==",
```
detector
low Secrets in code secret-high-entropy-token README.md:113

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"defaultPhotoboothModel": "core…_ad",
```
quoted
low Secrets in code secret-high-entropy-token README.md:264

High-entropy token-like string (may be an id, hash or a credential)
```
node sogni-gen.mjs --photobooth --ref face.jpg -m core…SDE "anime style"
```

low Secrets in code secret-high-entropy-token README.md:267

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)

Uses SDXL Turbo (`core…_ad`) at 1024x1024 by default. The face image is passed via `--ref` and styled according to the prompt. Cannot be combined with `--video` or `-c/--context`.

quoted

low Secrets in code secret-high-entropy-token README.md:354

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| `core…_ad` | Fast | Photobooth face transfer (SDXL Turbo) |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:169

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"defaultPhotoboothModel": "core…_ad",
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:217

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| `core…_ad` | Fast | Photobooth face transfer (SDXL Turbo) |
```
table

low Secrets in code secret-high-entropy-token SKILL.md:273

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)

Uses SDXL Turbo (`core…_ad`) at 1024x1024 by default. The face image is passed via `--ref` and styled according to the prompt. Cannot be combined with `--video` or `-c/--context`.

quoted

low Secrets in code secret-high-entropy-token sogni-gen.mjs:524

High-entropy token-like string (may be an id, hash or a credential)
```
function pick…Box(refWidth, refHeight, desiredWidth, desiredHeight, { allowImperfect = false } = {}) {
```
low Secrets in code secret-high-entropy-token sogni-gen.mjs:1505

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
options.model = options.model || openclawConfig?.defaultPhotoboothModel || 'core…_ad';
```
quoted
low Secrets in code secret-high-entropy-token sogni-gen.mjs:1675

High-entropy token-like string (may be an id, hash or a credential)
```
const candidate = pick…Box(dims.width, dims.height, options.width, options.height, { allowImperfect: true });
```
low Secrets in code secret-high-entropy-token sogni-gen.mjs:2305

High-entropy token-like string (may be an id, hash or a credential)
```
const candidate = pick…Box(startDims.width, startDims.height, clipWidth, clipHeight);
```

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")
warning body-long SKILL.md body ≈ 5189 tokens (recommended < 5000); move details to references/
note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 57/100

0Inputs and preconditions. Does not say what the process needs to start
0Progress reporting. Says nothing while it works
30Running it twice. 3 mutating operations with no state check
40Consistency. Frontmatter name (sogni-gen) differs from the folder (openclaw-sogni-gen)
50When it triggers. No condition that starts the skill
60Tools and files. Uses tools (bash, git) that frontmatter does not declare
60Result and completion. Output format stated, no completion criterion
70Execution cost. Instruction body is 5189 tokens
85Steps. 38 steps, 1 vague phrases
100Failures and branches. 1 branches, has a failure section

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 19 top-level sections: this looks like several domains in one skill
low The response is described with custom markup (21 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)
+1No license
+2Single-language instructions
+5Description quotes 3 example trigger phrases
+3Description length 186: enough signal without eating the budget
+4Structure: 26 headings
+3Step-by-step instructions: 38 items
+3Output format is stated explicitly
+4Has examples (22 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 9

README.md 14K
SKILL.md 21K
llm.txt 7K
mcp-server.mjs 31K
openclaw-plugin.mjs 0K
openclaw.plugin.json 4K
package-lock.json 68K
package.json 2K
sogni-gen.mjs 128K

Frontmatter

version: 1.5.4

homepage: https://sogni.ai

metadata: {"clawdbot":{"emoji":"🎨","os":["darwin","linux","win32"],"requires":{"bins":["node"]},"install":[{"id":"npm","kind":"ex

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:17 UTC

Last seen in crawl 27 h ago

Score history

Date		Score	Safety	Qual.
7 Sept 2026	B	75	79	69

Similar skills

B sogni-gen LeoYeAI/openclaw-master-skills
B sogni-gen modbender/skill-library-mcp