Agent Skills › paperclipai/paperclip › diagnose-why-work-stopped

diagnose-why-work-stopped

GitHub

诊断工作停滞原因。作为旧版技能兼容入口，当用户仅请求诊断或需审批时执行调查与安全分析；否则路由至完整修复流程以恢复工作。

.agents/skills/diagnose-why-work-stopped/SKILL.md paperclipai/paperclip

Trigger Scenarios

工作停滞无限循环过度恢复

Install

npx skills add paperclipai/paperclip --skill diagnose-why-work-stopped -g -y

More Options

Non-standard path

npx skills add https://github.com/paperclipai/paperclip/tree/master/.agents/skills/diagnose-why-work-stopped -g -y

Use without installing

npx skills use paperclipai/paperclip@diagnose-why-work-stopped

指定 Agent (Claude Code)

npx skills add paperclipai/paperclip --skill diagnose-why-work-stopped -a claude-code -g -y

安装 repo 全部 skill

npx skills add paperclipai/paperclip --all -g -y

预览 repo 内 skill

npx skills add paperclipai/paperclip --list

SKILL.md

Frontmatter

{
    "name": "diagnose-why-work-stopped",
    "description": "Compatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope."
}

Diagnose Why Work Stopped

Use Fix Failed Paperclip Run. It owns the current workflow: find the first causal failure, reproduce it red, repair the shared contract, test second-order effects, verify the real workflow, and deliver a PR with passing checks. A normal request to fix stopped work continues through that workflow without a separate plan-approval gate.

If the user or calling workflow explicitly asks for diagnosis only or requires approval before implementation, perform the investigation and safety analysis within that scope. For example, a Terminal-Bench diagnosis child does not override the loop's board approval boundary. Keep the next action and its owner explicit.

For issue-tree diagnosis, read the current doc/execution-semantics.md, inspect the relevant subtree and recent repairs, and classify non-progressing nodes:

Genuine wait: a named human or external dependency must act.
Agent-actionable but unrouted: authorized useful work lacks a live path.
Already covered: existing work owns the next action; do not duplicate it.

Preserve these three invariants together:

Productive work has a real next action and owner.
Only genuine blockers stop work, including approval, credentials, and budget.
Recovery is bounded and cannot recursively recover itself.

Frame any repair as a general behavioral contract, check it against a productive counterexample, and follow the new skill through the authorized finish line. Historical task links and private incident access are not required.