Vibe Clawing
v1.0.1Transition from vibe coding to vibe clawing by trusting agents with full responsibilities, designing self-closing loops, and climbing the bottleneck ladder.
⭐ 2· 770·4 current·4 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (transitioning from 'vibe coding' to 'vibe clawing') matches the included instructions and supporting markdown files. The files describe delegation patterns, loop design, and tracking; nothing asks for unrelated capabilities or credentials.
Instruction Scope
The SKILL.md and companion files instruct the agent to create and maintain files under ~/vibe-clawing (e.g., memory.md, loops.md). Writing small user-facing state in a dedicated folder is coherent with the skill's purpose, but it does imply local persistence (the agent will create and later read/write these files). There are no instructions to read system configs, access secrets, or call external endpoints.
Install Mechanism
No install spec or code is provided (instruction-only). That minimizes risk: nothing will be downloaded or written beyond the user-tracked files the instructions request.
Credentials
The skill requests no environment variables, credentials, or config paths. The local file writes it suggests are proportionate to the stated goal of tracking progress and loop state.
Persistence & Privilege
The skill is not always:true and does not request elevated privileges. It does recommend persistent files in the user's home directory and a changelog entry mentions preferences persisting across updates — this is consistent with a coaching/tracking skill but means it will keep local state the user may want to inspect or remove.
Assessment
This skill is instruction-only and consistent with its goal of helping you delegate and track 'closed loops.' Before installing, consider: (1) the skill will create and later read/write files under ~/vibe-clawing (memory.md, loops.md, etc.) — inspect those files periodically and don't store secrets or credentials there; (2) there is no code to execute or external URLs requested by the skill itself, so installation risk is low; (3) autonomous agent invocation is the platform default — if you plan to let agents act on your behalf, set appropriate guardrails and escalation triggers (as the skill recommends) and review logs or the created files to ensure behavior matches your expectations.Like a lobster shell, security has layers — review code before you run it.
latestvk9788552r9wv9rec3cp2ks3t2x8161pr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.