菜单
Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work, generating implementation prompts, or deciding next loop state.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work to Codex or Claude agents, generating implementation prompts, or deciding next loop state.
Use when code changes should be scanned and reflected back into living specs, docs, or architecture notes without changing product intent.
Use when reviewing active Loop Factory specs against the working tree, checking verification evidence, deciding ACCEPTED or CHANGES_REQUESTED, and archiving accepted specs.
Use when code changes should be scanned and reflected back into living specs, docs, or architecture notes without changing product intent.
Use when reviewing active Loop Factory specs against the working tree, checking verification evidence, deciding ACCEPTED or CHANGES_REQUESTED, and archiving accepted specs.
| name | loop-factory |
| description | Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work, generating implementation prompts, or deciding next loop state. |
Run spec-driven agent loops.
!python3 bin/loop-factory scan
grill-me pattern before dispatch: ask one question at a time, provide recommended answer, and record final decisions in # Grill Gate.python3 bin/loop-factory dispatch --agent claude --limit 1python3 bin/loop-factory dispatch --agent claude --limit 1 --stage/loop)When driven by /loop (e.g. /loop 30m /loop-factory) or asked to run "autonomous"/"drain the inbox", do one self-contained pass with no human present:
python3 bin/loop-factory scan to see the inbox.grill: completed, or a filled # Grill Gate. Skip un-grilled specs and report them as "needs grilling". Never answer grill questions yourself.python3 bin/loop-factory dispatch --agent claude --limit 1 --stage, implement the acceptance criteria, run the spec's verification commands.active/. Do not archive — acceptance stays human.Use project subagents when isolation helps:
spec-implementerspec-reviewerspec-backpropagatorUse dynamic workflows only when many independent specs or cross-checks justify script-owned orchestration.
Do not automate product decisions. Record assumptions or open questions.
Use repo-native loops when user asks for repeated work:
python3 bin/loop-factory loops listpython3 bin/loop-factory loops show <loop-id>python3 bin/loop-factory loops prompt <loop-id> --agent claudeFor interval loops, render prompt then use Claude Code /loop <interval> when appropriate.