Openclaw Skill
Sandboxed command runner for AI agents — validates and isolates every shell action inside a Bubblewrap user namespace.
Bootstrap a fresh or existing repo with nyann. TRIGGER when the user says "set up this project", "initialize git workflow", "bootstrap this repo", "scaffold this project", "ngyamm this repo", "use my <name> profile" / "apply the nextjs-prototype profile" (profile mode). ALSO trigger on "standard setup" / "usual stack" / "the usual setup" / "install all the standard hooks" / "give this repo the usual setup" / "make this repo standard" / "install nyann" — these read as opinionated bulk setup, not narrow edits, even though they sound small. Also trigger on any phrasing that mentions wiring up git hooks + branching + conventions + docs as a single opinionated setup. DO NOT trigger on narrow requests like "add a lint hook" or "update CLAUDE.md" — those are edits, not bootstraps. DO NOT trigger on "audit this project" / "fix what's drifted" / "bring into compliance" — those are retrofit. DO NOT trigger on "check this project's health" / "is this healthy" — those are doctor. When in doubt, run the detection step and
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "bootstrap-project" with this command: npx skills add thettwe/skillsmp-thettwe-thettwe-bootstrap-project
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Sandboxed command runner for AI agents — validates and isolates every shell action inside a Bubblewrap user namespace.
Prompt injection defense for OpenClaw agents. Scans emails and skill installations through a two-phase security pipeline (pattern matching + optional LLM ana...
Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a s...
Give your agent the superpower to read the modern web without getting blocked by Cloudflare. Extracts clean JSON, saves 98% of LLM tokens, and executes zero...