Proactive-Do
v0.1.1Proactive todo execution, heartbeat-driven review, and structured follow-up for a markdown todo system. Use when the agent needs to review `todo/todo.md`, pi...
⭐ 0· 145·1 current·1 all-time
byYi@hyharry
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 instructions: the skill only manipulates todo/todo.md, creates agent_work folders, ranks and works on up to 3 [new] todos, and drafts reports — all coherent with a todo workflow.
Instruction Scope
Instructions modify local files (todo/todo.md and agent_work/*), create journal folders, perform web searches when needed, and optionally send email via a CLI if available. These actions are within the stated purpose, but the agent will create and write files in the workspace and may send outbound email/network requests.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install surface. No downloads or package installs are requested.
Credentials
The skill declares no required environment variables or credentials. It does recommend using a 'gog' (Gmail/Google Workspace) CLI if present to send emails; that capability is optional but may require runtime credentials not declared in the package.
Persistence & Privilege
always is false and the skill does not request system-wide settings or modify other skills. It will write workspace-local files (agent_work/, todo/) which is appropriate for its purpose.
Assessment
This skill appears coherent: it will create and update local files (todo/todo.md and agent_work/*), pick and work on up to three [new] todos, keep per-task journals, and optionally send heartbeat emails. Before enabling it: (1) confirm you are comfortable with the agent editing todo/todo.md in-place (it promises not to delete lines automatically), (2) expect it to create files/folders under agent_work/, (3) if you want to allow email delivery, prepare a delivery_prefs file or be ready to provide CLI credentials for your email tool (the skill may prompt for them at runtime), and (4) if you do not want autonomous reviews, either disable autonomous invocation or limit scheduling (cron events) so work only runs when you explicitly invoke it.Like a lobster shell, security has layers — review code before you run it.
latestvk97325tnbdw97hgc2qjmj0cpc9838ze1
License
MIT-0
Free to use, modify, and redistribute. No attribution required.