$ loading_
读取计划文档并拆解步骤，生成可直接粘贴的 /orchestrate 链式提示词
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "plan-orchestrate" 技能： 1. 下载 https://raw.githubusercontent.com/affaan-m/ECC/main/skills/plan-orchestrate/SKILL.md 2. 保存为 ~/.claude/skills/plan-orchestrate/SKILL.md 3. 装好后重载技能，告诉我可以用了
请阅读下面的产品发布计划，将其拆解为可执行步骤；为每一步从 ECC catalogue 设计合适的 agent chain，并输出可直接粘贴的 /orchestrate 自定义提示词。不要实际调用 /orchestrate，只生成提示词。计划内容：……
一份按步骤组织的编排方案，包含每步目标、推荐代理链和可直接使用的 /orchestrate 提示词。
这里有一份研究执行方案，请拆分成信息收集、分析、写作、复核等阶段，并为每个阶段设计 ECC 代理链，输出最终可复制的 /orchestrate 提示词集合。只做生成，不要执行。方案内容：……
一组覆盖完整研究流程的阶段化提示词，并附对应代理链安排与衔接说明。
请根据这份开发路线图，拆解为需求澄清、架构设计、编码、测试、发布等步骤；从 ECC catalogue 为每步匹配 agent chain，并输出适合 /orchestrate 的完整提示词模板。不要调用任何命令。路线图：……
一个面向开发流程的分步编排模板，便于用户直接复制到 /orchestrate 中执行。
Bridge a plan document to /orchestrate custom by emitting one ready-to-paste invocation per step. The skill is generative only — it never executes /orchestrate. The user pastes each line when ready.
/orchestrate.Skip when:
/orchestrate custom directly.<plan-doc-path> [--lang=python|typescript|go|rust|cpp|java|kotlin|flutter|auto] [--scope=all|step:<n>|range:<a>-<b>] [--dry-run]
<plan-doc-path> — required; relative or absolute path (@docs/... accepted).--langauto--scope — limits emitted steps; defaults to all.--dry-run — print decomposition + chain rationale only; do not emit final prompts./orchestrate shape (do not deviate){ORCH_CMD} custom "<agent1>,<agent2>,...,<agentN>" "<task description>"
Where {ORCH_CMD} is determined in Phase 0 (see below). The command string in the emitted output always uses one concrete form — never both, never a placeholder.
custom is a sequential chain; each agent's HANDOFF feeds the next.--mode / --gate / --agents=... flags exist — never invent them.\".Two install forms determine the prefix on both the slash command and every agent name. The two MUST stay in sync — one form per output, never mixed:
Let <claude-home> denote the Claude Code home directory: ~/.claude on macOS/Linux, %USERPROFILE%\.claude on Windows. Resolve it the way the host platform resolves the user home directory (do not hardcode ~).
| Form | Detection | {ORCH_CMD} | Agent name format |
|---|---|---|---|
| Plugin install (1.9.0+) | <claude-home>/plugins/marketplaces/everything-claude-code/ exists | /everything-claude-code:orchestrate | everything-claude-code:<name> |
| Legacy bare install | Above absent; agent files under <claude-home>/agents/ | /orchestrate | <name> |
Why this matters: under the plugin install, agents register as everything-claude-code:tdd-guide. Bare names force fuzzy matching, which fails intermittently under parallel calls. Under legacy, the prefixed forms are not registered and fail outright.
General:
planner — requirement restatement, risk decomposition, step planningarchitect — architecture, system design, refactor proposalstdd-guide — write tests → implement → 80%+ coveragecode-reviewer — generic code reviewsecurity-reviewer — security audit, OWASP, secret leakagerefactor-cleaner — dead code, duplicates, knip-class cleanupdoc-updater — documentation, codemap, READMEdocs-lookup — third-party library API lookups (Context7)e2e-runner — end-to-end test orchestrationdatabase-reviewer — PostgreSQL schema, migration, performanceharness-optimizer — local agent harness configurationloop-operator — long-running autonomous loopschief-of-staff — multi-channel triage (rarely a fit for plan steps)Build error resolvers:
build-error-resolver (generic) / cpp-build-resolver / go-build-resolver / java-build-resolver / kotlin-build-resolver / rust-build-resolver / pytorch-build-resolverCode reviewers:
…
通过双评审智能体对结果进行对抗式校验，提升输出发布前的可靠性
分析并优化原始提示词，补全意图与缺口，生成可直接使用的高质量 prompt。