Infinity Poke Recipe Generator
v0.1.2Generate a small, specific, daily-life Poke recipe MVP from idea to Kitchen-ready draft (name, onboarding, integrations, automations, sandbox tests), with a...
⭐ 0· 78·0 current·0 all-time
byGerald He@skylinehk
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (generate Poke recipe MVPs) match the included helpers and templates. The scripts scaffold recipe/integration JSON, sandbox prompts, a verdict, and render Kitchen upload instructions — all coherent with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to perform a lightweight listing check by fetching https://poke.com/recipes and to read user repo spec files in Upload-assist mode. Both actions are reasonable for duplicate-checking and mapping uploads, but they involve network requests and reading user files. The instructions do not ask for unrelated system secrets or broad file system access, but you should be aware the workflow expects the agent (or user-run scripts) to read local recipe files and to fetch a public website.
Install Mechanism
No install spec and no external downloads. This is instruction-only with two small local helper scripts that only read/write files — low install risk.
Credentials
The skill does not request any environment variables, credentials, or config paths. The only external interaction is a suggested GET of https://poke.com/recipes (public listing) and generated CLI commands for users to run manually (npx poke@latest ...). No unexplained secret access is requested.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills. The scripts write files to an output folder chosen by the user — expected behavior for a scaffolding tool.
Assessment
This skill is internally coherent and low-risk, but review a few points before installing or running it:
- Template/key mismatches: the included templates and scripts use slightly different field names (e.g., references use serverUrl/authType while some generated/integration JSON and the renderer expect url/authentication). This will likely lead to missing fields in rendered instructions; verify and fix field names before publishing or relying on automation.
- Network access: the SKILL.md recommends fetching https://poke.com/recipes to check for duplicates. That is a public GET; confirm you are comfortable with the agent or your environment making that outbound request, and ensure no sensitive data is sent to that site.
- File reads/writes: the scripts read recipe.json and write files into the out path you provide. Run them in a safe, intended directory and double-check the generated files before running any generated CLI commands.
- CLI bootstrap commands (npx poke@latest ...): these are only printed into instructions; the skill does not execute them. Inspect the generated commands and integration URLs before running them. Replace any 'TODO' placeholders with real endpoints and validate authentication requirements.
- Source transparency: the skill has no homepage and an unknown source. That by itself isn't a security red flag for this scaffolding tool, but if you need higher assurance prefer code from a known author or run the scripts in an isolated environment first.
If you plan to use the Upload-assist mode, be explicit about which local files the agent can read and make sure no unrelated sensitive files are accessible to the agent.Like a lobster shell, security has layers — review code before you run it.
latestvk975zqznmzsyy5ng08fgxzpyd583cs2n
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
