long-running-task-management

Detects when the agent is stuck in a loop and escapes systematically.

Bootstrap skill — teaches the agent how to find and invoke skills.

Scaffolds and validates new superpowers skills.

Prevents context overflow on long-running OpenClaw sessions.

Parallel subagent execution for complex tasks.

Executes plans task-by-task with verification.

Structured ideation before any implementation.

Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent

Scores a skill's description field against sample user prompts to predict whether OpenClaw will correctly trigger it — before you publish or install.

Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on

Validates that a skill's companion scripts declare their OS and binary dependencies correctly, and checks whether those dependencies are actually present on…

Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete…