Decide
v1.0.1Self-learn your decision patterns to safely build its own decision-making over time.
⭐ 4· 2.3k·20 current·21 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
Name/description match the required capabilities: local durable decision memory in ~/decide/ is reasonable for a 'decide' skill. No unrelated binaries, cloud credentials, or network endpoints are requested.
Instruction Scope
The runtime instructions direct the agent to read and write files under the user's home (~ /decide/) and to list domain files (find). That file I/O is consistent with the stated purpose, but users should note the skill will create and append to local files when run (the files and exact snippets are in the repo and the skill instructs to seek explicit approval before modifying workspace SOUL/AGENTS files).
Install Mechanism
Instruction-only skill with no install spec and no external downloads; nothing will be written to disk by an installer beyond what the agent is told to create in ~/decide/.
Credentials
Requires no environment variables or credentials and explicitly warns not to persist secrets. The requested access (home-directory files) is proportional to the skill's purpose.
Persistence & Privilege
The skill persists state under ~/decide/ (creates files and suggests adding small AGENTS/SOUL snippets). It is not always-enabled and does not request elevated privileges, but it does instruct the agent to write local files — the user should review any snippets before allowing writes. Autonomous invocation is allowed by platform default (not raised here), so ensure agent policies govern file writes if you want stricter controls.
Assessment
This skill is internally consistent and appears to do what it says: it stores decision rules and logs in ~/decide/ and includes conservative rules (ask-first, explicit promotion of defaults). Before installing, review the provided setup and SOUL/AGENTS snippets so you know exactly what will be written to your workspace. Back up any existing ~/decide/ data you care about. Confirm that you are comfortable with the agent reading and appending those local files, and only approve the skill to write AGENTS or SOUL files after inspecting the exact snippet it will add. If you want stricter control, deny autonomous writes or require explicit user approval in your agent policy.Like a lobster shell, security has layers — review code before you run it.
latestvk977dph3f70fgchsp5pmbdhtvx82k8ph
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
⚖️ Clawdis
OSLinux · macOS · Windows