terminal-bench-loop
FeaturedRun one Terminal-Bench task through a bounded Paperclip smoke/diagnosis/fix loop. Use when asked to drive Terminal-Bench until it passes, rerun a Terminal-Bench loop, or iterate with board-gated fixes and diagnosis.
Install
Quality Score: 92/100
Skill Content
Details
- Author
- paperclipai
- Repository
- paperclipai/paperclip
- Created
- 8 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
running-the-loop
Use when the user wants an unattended build loop over a repo's GitHub issues, with this session as the orchestrator that drives one implementer session task after task, for example "run the issue loop on this repo" or "work through the open issues unattended", or when a handover's first message tells this session to take over a loop. Not for building one feature in this session, and not for passing the loop to a new session (use handing-over).
running-a-bounded-loop
Use when carrying one planned unit of work through to done; when defining what a unit's exit gate has to contain before it can be called finished; or when an unattended run has to decide whether to stop and ask. DO NOT invoke to arrange units, order them, or choose where each runs — route that to ledger:planning-the-work. DO NOT invoke to write the criteria that define done in the first place — route that to ledger:specifying-acceptance.
loop-engineering
Use to design or add a new bounded loop to the kit's SDLC orchestration ("design a new loop", "is this worth a loop"), or mentions the Karpathy loop / autoresearch / hill-climb / search-and-select prompt or parameter tuning. NOT for a one-off in-session Stop-hook goal (use goal-craft), NOT for the debug loop (already exists, use /kit:debug), NOT for building the loop's actual code.