diagnose-why-work-stopped
About diagnose-why-work-stopped
A Paperclip skill for investigating why work stopped and, unless the request limits the scope to diagnosis, carrying an authorized repair through testing and delivery. It emphasizes identifying the causal failure, preserving clear ownership, and preventing unbounded recovery loops.
Key features
- 01Locate the first causal failure
- 02Reproduce failures before repair
- 03Repair shared behavioral contracts
- 04Test second-order effects
- 05Verify workflow and deliver a PR
Use cases
- 01Investigate stalled Paperclip work
- 02Diagnose non-progressing issue trees
- 03Repair a failed workflow when authorized
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/diagnose-why-work-stoppedin Claude Code to confirm it loaded.
Details
From the project READMEDiagnose 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.