Openclaw Skill
Sandboxed command runner for AI agents — validates and isolates every shell action inside a Bubblewrap user namespace.
Run a full ROM 2.4b6 → Python parity audit on a single ROM C source file (e.g. act_obj.c, scan.c, special.c). Use when starting a new file-level audit, when the user says "audit X.c", or when ROM_C_SUBSYSTEM_AUDIT_TRACKER.md shows a P0/P1 file as Partial/Not Audited. Encodes the 5-phase methodology: (1) read ROM C and Python entry point, (2) write per-file audit doc with gap table, (3) ID gaps with stable IDs (FILE-001 etc.), (4) close gaps via integration tests + implementation (defer to rom-gap-closer per gap), (5) flip tracker rows and write a session summary. Not for single-gap closures — use rom-gap-closer for those.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "rom-parity-audit" with this command: npx skills add Nostoi/skillsmp-nostoi-nostoi-rom-parity-audit
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...