Enforce a quality-guarded continuation workflow when an AI stop hook triggers.
npx skills add https://github.com/liuzhengdongfortest/skills --skill continuous-work
Please help me install this Agent Skill. Skill: continuous-work Source: https://github.com/liuzhengdongfortest/skills/tree/main/continuous-work Command: npx skills add https://github.com/liuzhengdongfortest/skills --skill continuous-work
Continuous-work prevents premature stopping by enforcing a “stop hook” decision gate that triggers a full, structured continuation workflow when the AI or configuration requests stopping before the job is verified and safely recorded.
.ai/continuous.yaml enables it, with repeat limits and session-scoped state.Ask your AI to follow the continuous-work execution rules before stopping, with your project’s stop configuration enabled via .ai/continuous.yaml.
High-intent search queries and answers about installing and using this skill.
A continuous-work stop hook intercepts premature AI termination decisions and enforces a structured continuation workflow, ensuring code quality checks and evidence-based verification complete before safely recording the session.
A stop hook workflow executes iterative roadmap tasks across Codex, Claude Code, and OpenCode by triggering a shared decision script that enforces top-down project recalibration and bounded repeat continuation when `.ai/continuous.yaml` enables it.
Top-down project recalibration is a comprehensive scan from project profiles to task indexes, ensuring the next execution step matches current project truth before proceeding with roadmap execution.
Yes, continuous-work mode requires configuring `.ai/continuous.yaml` to enable the stop hook, ensuring the AI follows execution rules and applies repeat limits before stopping iterative coding sessions.
When an AI agent gets blocked during a continuous-work coding cycle, the workflow enforces deep digging for evidence, applies anti-stall behavior, and expands inspection across inward, outward, and meta layers to choose the safest next action.
Yes, you can enforce strict code and engineering quality checks before an AI stop decision ends task execution by applying hard constraints within the continuous-work continuation workflow.
BumblebiberInstall and configure the hmem MCP server across system-wide or project-local scopes.
liuzhengdongfortestExecute client goals via task or roadmap workflows with .boss/ artifacts.
arendon1Design and optimize AI agent context management under token constraints.
ManuelKugelmannDisable continuous work mode so Claude waits for explicit user input.