Investigate stalled or repeatedly recovering task trees in Paperclip using task states, run records, and recent changes. Produce an evidence-based cause analysis and a phased product-rule plan for approval, without changing code.
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 traces parent tasks, child tasks, and dependencies in Paperclip to find where work stopped or recovery began repeating. It uses run records, comments, and state changes to explain the cause. It classifies work as needing human action, actionable by an agent, or already being handled. It also reviews recent related changes and documents rules to prevent recurrence, together with a phased plan.
Use it when you need an explanation of why work stopped, or when recovery tasks keep multiplying. The plan must meet three conditions together: work that can proceed continues, only real blockers stop work, and infinite loops are prevented.
The scope is diagnosis and planning; it does not change code. Read doc/execution-semantics.md before investigating. After plan approval, the work is divided into child tasks with assignees and dependencies. It respects access restrictions on other companies’ information and explicitly labels explanations based on inference.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
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:
Preserve these three invariants together:
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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Add or extend Paperclip end-to-end evaluations that exercise real browser workflows across the server, database, and runner. Define expected outcomes, check independent evidence, and connect results to the existing reporting pipeline for local or Daytona execution.
Add or extend Paperclip Runner evaluations that test real sessions against a mock control service. Define observable pass conditions, validate cases and run selections, and retain source revisions, evidence, and costs for authorized live runs.
Use a real browser to verify web pages and apps through short, supervised interactions. Capture screenshots, inspect errors and network requests, and document reproducible steps for UI bugs or expected behavior checks.
Read email linked to assigned Paperclip tasks, send new messages or replies through an assigned AgentMail inbox, and check delivery outcomes. Follow task permissions and preserve retry identifiers to avoid duplicate sends.
Inspect proposed changes in GitHub, GitLab, or Perforce for review feedback, failed automated checks, and incomplete descriptions. It separates actionable findings from informational or resolved comments, then helps fix issues and close addressed review threads when requested.
Create an AI agent company or team package from an idea or an existing repository. Define roles, reporting lines, skills, and work handoffs, then generate structured files that follow the Agent Companies specification.