Project Workflow Scheduler
v1.0.0Break a project, objective, or task list into safe, bounded one-time OpenClaw cron work blocks with dependencies, risk classification, and strong isolated ag...
⭐ 0· 189·0 current·0 all-time
bySebastian The Claw@sebclawops
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 match the SKILL.md: the skill is an instruction pattern for creating supervised one-time cron/agentTurn jobs. It does not request unrelated binaries, credentials, or config paths and does not attempt capabilities beyond scheduling and payload construction.
Instruction Scope
Runtime instructions stay on-topic: they guide splitting work into small blocks, classifying risk, and producing bounded cron payloads. They explicitly forbid destructive or customer-facing actions and require user approval for risky phases. The only potentially sensitive action is 'inspect the project structure and deployment touchpoints' — but that is coherent with audit/prep tasks and is called out as discovery-only.
Install Mechanism
Instruction-only skill with no install spec, no downloads, and no code files — minimal disk footprint and no third-party install risks.
Credentials
No environment variables, credentials, or config paths are requested. This is proportionate to a scheduling/orchestration guidance skill. Note: actual scheduled agentTurn runs may need access to project files or services at runtime; the skill correctly emphasizes preconditions and user approval rather than requesting secrets upfront.
Persistence & Privilege
Does not set always:true and is user-invocable only. It advocates creating future one-time scheduled agentTurn jobs — which will run under normal autonomous invocation — but the skill itself does not request persistent or elevated platform privileges.
Assessment
This skill is coherent and conservative, but before you use it: (1) Confirm where and under what identity the cron/agentTurn jobs will run — ensure the runtime has only the minimum file/system/network access needed. (2) Require the agent to include explicit 'Do not' clauses in every scheduled payload (the skill recommends this; enforce it). (3) Review proposed schedules and payloads before they are actually created or run, and avoid pre-scheduling any customer-facing, destructive, or infra-changing blocks without explicit approval. (4) Verify scheduled runs cannot access secrets or external endpoints unless you explicitly permit them, and ensure audit logs/announcements are enabled so you can review what ran.Like a lobster shell, security has layers — review code before you run it.
latestvk97d4pry1t11trezb551ea0aqd832j0k
License
MIT-0
Free to use, modify, and redistribute. No attribution required.