SKILL

goal-driven-delivery

在仓库中端到端交付书面定义、可由机器检查的增量:一个目标契约,每阶段启动新的编写智能体,由操作者重跑关卡,使用脚本化合并关卡,并保留持久阶段台账,使后续会话可用三个命令恢复。用于端到端委派且包含合并的增量。不用于一行修复、无验收标准的探索,或机器无法检查的工作;后者应通过沟通处理,而非按交付流程执行。

译文已校对
查看英文原文

Land a written, machine-checkable increment in a repo end to end — one goal contract, one fresh authoring-agent run per stage, gates the operator re-runs, a scripted merge gate, and a durable stage ledger so a later session can resume in three commands. Use when an increment is delegated end to end, including the merge. Do not use for one-line fixes, exploration with no acceptance criteria, or work no machine can check (that is a conversation, not a delivery).

适用对象:对象待分类。自动收录 · 待核查。

原作者说明节选

从固定版本的 SKILL.md 提取,保留原文语言。以下内容属于作者说明,本站尚未验证安装、兼容或运行结果。

查看英文原文

原文涵盖的主题

  • Goal-driven delivery
  • When to Use
  • Stage order — fixed, no skipping
  • Roles — authoring vs inspection
  • Phase 0 — the dispatch contract
  • Phase 1 — branch and dispatch
  • Phase 2 — verify before believing anything
  • Phase 3 — simplify, then apply

One written increment (a goal), authored by a coding agent, verified and landed by the operator, with the loop running end to end and no per-step approval. This file is the protocol and nothing else. Repo facts live in a project profile — a profile is deltas only and may never restate or override the protocol. Transport mechanics live in references/transport.md. Language- and stack-specific build knowledge lives in its own skill. One fact, one home. "Start the next goal", "run the goal-driven flow", "finish this the usual way". 中文同义说法同样触发:开始下一个 goal、推进 goal driven 流程、按老流程把这个做完。 Any multi-hour repo increment: a feature, a research-feasibility study, a migration, a docs rewrite — anything with a written completion contract and machine-checkable gates. A repo where the operator delegates end to end, including the merge. Not for: one-line fixes, exploratory poking with no acceptance criteria, or work whose result no machine can check. Both two-phase steps are mandatory: an unapplied report or an unfixed review does not close a stage. Caps: implement 2 recovery attempts, simplify 2 rounds, review→fix 2 rounds. On a third round, stop and report — do not burn budget in silence. The agent

这里只展示节选,请以完整原文和当前要求为准。

来源仓库
wxxb789/hoa
源文件
skills/goal-driven-delivery/SKILL.md
固定版本
beb1eca66d8fed7c3942dc3ef50990bf37837706
阅读完整原作者说明 ↗

准备条件

  • 本条仅收录原作者的技能元数据;请阅读完整说明,确认依赖、许可与使用条件。

第一件可以尝试的小事

先阅读原作者说明,再决定是否在自己的 AI 工具中使用。

对应 AI 工具说明

作者有说明不等于本站实机验证。没有证据时,不自动标为兼容、安全或免费。

来源与内容状态

本条为自动发现的元数据,尚未完成人工文档核查;适用性与运行结果待核查。

原作者:wxxb789/hoa · 原作者仓库元数据。文档核查:未核查。最近来源检查:2026-11-09T20:02:15.373Z。

分类由名称、说明与路径规则生成,分类不代表已核实适配。

许可与权利归属

MIT。第三方内容及版权归原作者,使用条件以原文为准。

许可原文 ↗

本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。

限制与注意事项

  • 元数据收录不代表本站已经安装、适配、实测或进行安全审查。