terminal-bench-loop Skill
Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifact Published by microsoft in amplifier-app-paperclip.
What is terminal-bench-loop Skill?
Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifact Published by microsoft in amplifier-app-paperclip. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Developers using amplifier-app-paperclip
Technical details
- Install or run with Copy skill directory
When to use terminal-bench-loop Skill
- Use it for developers using amplifier-app-paperclip.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/amplifier-app-paperclip
- Skill file: skills/terminal-bench-loop/SKILL.md
What it does
Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifact
Skill instructions
Terminal-Bench Loop A repeatable operating skill for driving one Terminal-Bench problem to a passing smoke through Paperclip, with explicit issue topology, bounded runs, board-gated product fixes, and worktree continuity. This skill is operational + diagnostic, not engineering. It coordinates issues, artifacts, and approvals around a Terminal-Bench loop. It does not authorize code changes — every accepted product fix lands as a separate implementation child issue after a board confirmation. Canonical execution model: read doc/execution-semantics.md before starting a loop or moving any loop issue. Every loop issue must rest in a state the doc allows: terminal (done/cancelled), explicitly live (active run / queued wake), explicitly waiting (inreview with participant/interaction/approval), or explicit recovery/blocker (blocked with blockedByIssueIds and a named owner). When to use Trigger on an assignment whose title or body matches any of: - "run Terminal-Bench in a loop", "loop <task-n
Explore related resources
Frequently asked questions
What is terminal-bench-loop?
terminal-bench-loop is a open-source AI agent skill with Copy skill directory. Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a.
Who is terminal-bench-loop best for?
terminal-bench-loop is best for reusing agent instructions, scripts, and references.
How do I install terminal-bench-loop?
Install or run terminal-bench-loop using Copy skill directory. Check terminal-bench-loop for the latest setup command.
Is terminal-bench-loop actively maintained?
terminal-bench-loop may need a closer maintenance check before production use.
Auto-fetched from GitHub.
