Use when code changes should be scanned and reflected back into living specs, docs, or architecture notes without changing product intent.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this skill to run spec-driven agent loops.
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 scanpython3 bin/loop-factory dispatch --agent codex --limit 1python3 bin/loop-factory dispatch --agent codex --limit 1 --stageFor parallel work, explicitly ask Codex to spawn subagents. Use:
spec-implementer for scoped implementationspec-reviewer for independent reviewspec-backpropagator for spec/doc updates from diffsDo not fan out same-file edits. Do not automate product choices. If spec is ambiguous, record assumption or open question.
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 codexPrefer spec-grill-gate, active-spec-verify, independent-review-gate, and backprop-spec-sync for normal spec flow.
Report:
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when code changes should be scanned and reflected back into living specs, docs, or architecture notes without changing product intent.
中文简介正在准备中。当前显示原文说明。
Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work, generating implementation prompts, or deciding next loop state.
中文简介正在准备中。当前显示原文说明。
Use when reviewing active Loop Factory specs against the working tree, checking verification evidence, deciding ACCEPTED or CHANGES_REQUESTED, and archiving accepted specs.
中文简介正在准备中。当前显示原文说明。