Task Decomposition

Plan, track, and learn from complex multi-step tasks. Decomposes requests into dependency-aware subtasks with parallel execution, progress tracking, and a le...

This skill appears coherent and low-risk, but it will read and write files inside the agent's workspace (plans/, patterns.md and archived plan files). Before installing, consider: (1) Run it in a workspace that doesn't contain secrets you wouldn't want written to disk. (2) Ensure .env or other secret-containing files are gitignored or not present if you don't want endpoints/credentials stored — the example suggests saving endpoints to .env. (3) Review any plans/patterns the agent creates before committing or sharing them. (4) If you plan to let the agent run autonomously, remember it can create and update these local files without additional prompts; if you want tighter control, invoke it manually. Overall this skill matches its stated purpose; the main risk is accidental local persistence of sensitive data, not unexpected network access or credential exfiltration.

Type: OpenClaw Skill Name: task-decomp Version: 2.0.0 The provided skill bundle contains metadata and a detailed markdown document (`SKILL.md`) outlining instructions for an AI agent to perform task decomposition, planning, tracking, and learning. All instructions, including file operations (reading, writing, renaming), are strictly confined to a designated `plans/` directory and are directly aligned with the stated purpose of managing project plans and learning patterns. There is no evidence of prompt injection with malicious intent, data exfiltration, unauthorized execution, persistence mechanisms, or obfuscation. The skill's functionality appears to be entirely benign and focused on its described task management capabilities.