clawlist
v0.0.1MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.
⭐ 3· 4.5k·26 current·26 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match the actual instructions: the skill orchestrates brainstorming → plan → execute → verify and manages long-running/infinite tasks. However, the SKILL.md repeatedly refers to persistent agent memory files (e.g., memory/tasks/ongoing-tasks.md, memory/plans/...) and to platform features (heartbeat, sessions_spawn) while the skill metadata declares no required config paths or platform permissions. That omission is an inconsistency to be aware of.
Instruction Scope
Instructions tell the agent to read project state (files, docs, commits), write and update persistent memory files, spawn subagents, and let a heartbeat process read ongoing-tasks.md to execute due tasks. All of that is in-scope for a task-orchestration skill, but it does mean the agent will access and persist project data and may act repeatedly over time—so check whether you want those filesystem/memory operations and any automated dispatching of subagents.
Install Mechanism
Instruction-only skill with no install spec or code files to run. Lowest-risk install surface—nothing is downloaded or written by an installer.
Credentials
The skill requests no environment variables or external credentials, which is proportional to its stated purpose. Note: it implicitly relies on the agent's persistent memory and platform features (heartbeat, session spawning) but does not request additional secrets.
Persistence & Privilege
The skill is not force-included (always:false) but is designed for long-running and infinite tasks and instructs the agent to update persistent memory and rely on a heartbeat to execute tasks. Autonomous invocation is allowed (disable-model-invocation:false) — typical for skills, but because this one is intended to schedule/drive repeated actions and spawn subagents, it raises operational risk if you don't want ongoing automated behavior.
Assessment
This skill appears to do what it says: orchestrate multi-step and long-running workflows. Before installing, consider: 1) The skill reads and writes agent memory files (memory/tasks/ongoing-tasks.md, memory/plans/...), but the metadata doesn't declare those config paths — confirm your platform's memory policy and whether you consent to those persistent writes. 2) It expects to spawn subagents and rely on a heartbeat to run recurring tasks; if you don't want autonomous or frequent background actions, do not enable autonomous invocation or set limits. 3) Because it can read project files and commits, avoid using it on repositories containing secrets unless you trust its behavior and storage. 4) Test with a non-sensitive project first, monitor the agent's actions and memory writes, and set explicit boundaries (frequency, scope, and allowed outputs) for infinite/long-running tasks.Like a lobster shell, security has layers — review code before you run it.
alphavk975jrjv9b356f0mwvyh7yj8k9809nzjlatestvk975jrjv9b356f0mwvyh7yj8k9809nzj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.