SKILLEMALL.ai
GitHub ↗ RU Sign in

BC kandinsky

Генерация изображений и видео через Kandinsky API (модели Kandinsky K6/K5, GigaAvatar). Используй, когда пользователь просит "сгенерируй картинку", "нарисуй", "перерисуй (i2i)", "оживи картинку", "сделай видео из фото или по тексту", "апскейл/увеличь картинку", "озвучь аватар". Покрывает t2i, i2i, super-resolution (×2/×4), t2v (text-to-video), i2v (image-to-video, lite/sd/hd) и giga_avatar (фото+аудио → говорящий аватар). Триггеры: Kandinsky, Кандинский, Kandinsky API, K6, K5, t2i, i2i, t2v, i2v, апскейл, оживить, аватар.

ClawHub Agent Skills author: Nikolay-Gerasimenko v1.0.2 MIT-0 5 files body ≈ 2 423 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Генерация изображений и видео через Kandinsky API (модели Kandinsky K6/K5, GigaAvatar).

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationMedia 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
B
88/100
safety, quality, tests
Safety 60%
90
Quality 40%
86
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Inputs and preconditions w 11
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-credential-use SKILL.md:215
    Credential used in a network call (verify the destination is the intended service)
    curl -s "$BASE/tasks/abc123" -H "Authorization: Bearer $KANDINSKY_API_KEY"
  • medium Exfiltration net-credential-use SKILL.md:219
    Credential used in a network call (verify the destination is the intended service)
    curl -s "$BASE/tasks/abc123/result" -H "Authorization: Bearer $KANDINSKY_API_KEY" -o out.png

Files scanned: 1. 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")

Process rating: all ten parameters 52/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 30 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2423 tokens
  • 100Progress reporting. Reports progress

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +5Description quotes 7 example trigger phrases
  • +3Description length 527: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 1 scripts are documented
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

External checks

ClawHub: suspicious
This skill is mostly purpose-aligned, but it needs review because it documents and defaults to an unencrypted HTTP API endpoint that can receive an API key and user media.
LLM: suspicious (high) · VirusTotal: · 20 Jun 2026