SKILLEMALL.ai
GitHub ↗ RU Sign in

BB Cooking

Cooks and rescues real dishes at the stove: heat control, seasoning, doneness, timing, substitutions, and food safety. Use when a dish is bland, too salty, burnt, tough, dry, watery, rubbery, greasy, or gummy; when a sauce breaks, splits, curdles, or will not thicken; when meat, fish, eggs, rice, pasta, beans, bread, or a cake come out wrong; when adapting a recipe for a missing ingredient, a different pan, an air fryer, altitude, or a doubled batch; when asking what temperature something is done at, how long to rest it, how much salt, or whether leftovers are still safe; when searing, braising, roasting, frying, grilling, baking, fermenting, or curing; or when ordering the work so a whole meal lands hot at once. Not for weekly menus and shopping lists (`meal-planner`, `grocery`), recipe collections and recipe walkthroughs (`recipe`, `chef`), calorie or macro counting (`calories`), or micronutrients (`nutrition`).

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Iván v1.0.2 MIT-0 21 files body ≈ 7 454 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

ReferenceInfrastructuretype 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
76/100
safety, quality, tests
Safety 60%
82
Quality 40%
66
Run on models
none yet
Process rating
B
70/100
Nearly there
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

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 1

  • high Exfiltration intent-browser-credential-store baking.md:15
    Accesses a browser credential / cookie store
    Convection: reduce the temperature by **15-20°C** and expect roughly **25% less time**, and start checking earlier than that. Convection dries surfaces, which is excellent for pastry, roast potatoes,

Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 7454 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 8 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, read) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 7454 tokens
  • 100Steps. 43 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 927: 120–800 characters recommended
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 43 items
  • +3Output format is stated explicitly

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This cooking skill is useful and mostly transparent, but it needs Review because it automatically reads and writes persistent cooking, health, and contact records, including allergies and guest constraints.
LLM: suspicious (high) · 27 Jul 2026