Review stalled, blocked, or pending-review issues in Paperclip and choose one concrete next action for each. Clarify ownership and status, then resume work, reassign it, resolve blockers, request a decision, or close the issue.
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
This skill reviews assigned issues in Paperclip and identifies each issue's owner, status, and one action needed to move it forward. It checks whether work is still running, needs a prompt to resume, requires a different owner, or has a blocker to resolve. It also handles requests for decisions and closing completed, duplicate, or unnecessary issues. Each reviewed issue gets a short summary of the decision and action taken.
Use it for a morning progress review or when unfinished assignments make priorities unclear. Managers can check progress without asking every agent individually. It also helps when a comment flags an old issue as stalled. Reviews cover work without recent updates, reviews without a reviewer, and blocked issues whose dependencies are complete.
The skill retrieves assignments and issue states through the Paperclip API. It excludes work already underway on a specific issue and questions awaiting user answers. Cross-team issues go to their responsible manager rather than being cancelled. Status changes require reasons. Issues that cannot be assessed quickly are referred for a decision instead of guessed at.
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.
Convert a noisy inbox into a small set of clear next actions. Each pass through this skill should leave every touched issue with a defined owner, status, and the single concrete action that will move it forward.
in_progress, in_review, and blocked assignments.request_confirmation or ask_user_questions. Wait for the response — re-triage is noise.GET /api/agents/me/inbox-lite for the compact assignment list.GET /api/issues/{issueId}/heartbeat-context for compact state including blockerAttention, executionState, ancestors, and commentCursor.For each issue, classify into exactly one of:
in_progress or move to todo so the assignee picks it up.in_review only if the new assignee is human, otherwise leave in_progress.blockedByIssueIds entry is now done or cancelled. If cancelled, replace or remove it from blockedByIssueIds. The blockers-resolved wake will fire automatically when all are done.request_confirmation, ask_user_questions, or request_board_approval and set the issue to in_review.done or cancelled with a one-line reason.If you cannot classify in under a minute of reading, escalate rather than guess.
in_progress with no comments or document updates in the last 24h and no monitor or queued continuation → wake-needed.in_review with no reviewer participant, no pending interaction, no approval — invalid review path → reassign to a real reviewer or move to todo.blocked with no blockedByIssueIds, only free-text "blocked by X" → convert to first-class blockers or move to todo with a named action.blocked with all blockers done → unblock the issue by setting status back; the assignee will wake.in_progress → confirm parent acceptance, then close.blocked issue if your most recent comment was also a blocked update with no reply since.A short comment chain or summary message that lists, per issue touched:
This is the bar for "the triage is done."
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.