Handoff

v1.0.0

Create temporary handoff docs and propose/apply permanent knowledge updates in a shared Obsidian vault.

0· 151·0 current·0 all-time
byRadon Co@radonx
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the SKILL.md: all actions are restricted to a single shared vault root ($HOME/.openclaw/shared) and concern creating/searching/updating handoff and knowledge files. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
Instructions are narrowly scoped to reading and writing files under the declared vault path and include sensible safeguards (must state absolute paths and ask for confirmation before any write; propose-only behavior for permanent docs unless explicit --apply). Note: work-log guidance asks the agent to record commands executed and key outputs which could capture sensitive data from files the agent reads; users should verify what will be recorded before confirming writes.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is downloaded or written by an installer. Lowest install risk.
Credentials
No required environment variables or credentials are declared. The skill does implicitly rely on $HOME and on the agent runtime providing values such as agentId/sessionKey if available; that implicit dependence is reasonable but worth noting (the skill will operate relative to the user's home directory).
Persistence & Privilege
always:false and user-invocable:true (normal). The skill does not request permanent presence, nor does it instruct modifying other skills or global agent settings.
Assessment
This skill appears coherent and limited to working inside $HOME/.openclaw/shared (an Obsidian vault). Before installing or using it, confirm: (1) the vault path is where you expect data to be written; (2) you want the agent to have filesystem access to that path; (3) you understand that work logs may capture commands and outputs (which can include sensitive info) — review those logs before confirming writes; (4) permanent-doc edits require explicit confirmation and --apply per the instructions, so only approve writes you expect. If you prefer stricter control, test in a disposable vault directory and verify the confirm prompts occur as described.

Like a lobster shell, security has layers — review code before you run it.

latestvk974snc7qd6rek2a82wfnvsq1h82tnkn

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🧷 Clawdis

Comments