菜单
Harvest learnings from target sessions and promote proven overlay patterns to the shared control-plane base
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
| name | aicoder-harvest-and-promote |
| description | Harvest learnings from target sessions and promote proven overlay patterns to the shared control-plane base |
| user-invocable | false |
Improvement and harvest workflow for the aicoder-opencode control plane.
After a target session:
targets/<target>/overlay/.agents/skills/ for any local skills that
were added or modified during the session.Promote a local overlay skill to the shared base when:
.agents/skills/<skill-name>/SKILL.md..agents/skills/.manifest.json if one exists.instructions array in opencode.jsonc.bun run check to confirm nothing broke.After sessions that used specific models:
config/models.jsonc
to reorder or disable it.make manage-models to interactively adjust, then make validate-dr-repo
to confirm the change does not break the target path.src/plugins/, propagate shim
updates to any affected target overlays.Use when asked to work in a continuous loop until done or truly blocked. Orchestrates pickup, planning, TDD execution, implementation waves when needed, debugging side-chains, verification, and resume behavior.
Use before planning when a feature or change request is underspecified. Resolve high-impact ambiguity around scope, consumers, security, failure handling, and acceptance criteria before writing the implementation plan.
Use for both preparing work for review and responding to review feedback. Keep review evidence local, concrete, and scoped to the real contract. Verify technically before agreeing or changing code.
Use before implementation. Merge design discovery and plan writing into one DR-specific flow: identify the consumer, inspect the repo, debate boundaries with partner and combatant, and produce an execution-ready plan that hands off cleanly into DR-native tasks, TDD, and implementation waves.
Use for the last mile: rerun verification, inspect diffs, commit or push if requested, and perform local docker-compose checks when needed. This is the DR local-tools replacement for MCP-style finish/deploy carryovers.
Use after planning and before implementation when you need a concrete, dependency-ordered task list. Turn the DR feature spec and plan into independently testable task slices with exact file paths and verification commands.