一键导入
aos-product-orchestrator
Groom Agentic OS self-improvement proposals into spec packets and Linear issues. Use for AOS Product Orchestrator or Auto Groom.
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。
菜单
Groom Agentic OS self-improvement proposals into spec packets and Linear issues. Use for AOS Product Orchestrator or Auto Groom.
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 | aos-product-orchestrator |
| description | Groom Agentic OS self-improvement proposals into spec packets and Linear issues. Use for AOS Product Orchestrator or Auto Groom. |
Use this skill to turn Agentic OS ideas, self-improvement suggestions, and rough operating-system changes into execution-ready specs and Linear issues.
The default automation invocation is a self-improvement proposal from the
Self Improvement Notion database with Auto Groom checked.
Use the relevant Agentic OS skills as needed:
$os-navigator$spec-intake-router$auto-spec-intake$context-audit$workflow-builder$automation-qualifier$linear-product-orchestratorDo not run implementation unless the user or queued action explicitly asks for implementation. Auto Groom is a product/spec grooming action.
harness/rules/os-authoring-rules.md for changes to skills, commands,
workflows, automation, runtime templates, tools, or registries.agentic-os-intake-row \
--title "<proposal title>" \
--type <idea|spec|investigation|...> \
--route-text '<proposal source words>' \
--body-file <packet SPEC.md path>
agentic-os-intake-sync will create/update the Linear issue from the intake
row — this avoids double-writes. If the row create fails, record the error in
the packet worklog and continue.
8. Leave a receipt that names the spec packet, Linear issue identifier/URL,
evidence used, skipped items, and blockers.
Agentic OS project before any Linear
write.Resolve context.
Draft the spec packet.
spec-intake-router or auto-spec-intake for packet placement.Map the implementation.
Write the unified intake row (replaces direct Linear issue creation).
agentic-os-intake-sync.agentic-os-intake-row (non-blocking):agentic-os-intake-row \
--title "<proposal title>" \
--type <idea|spec|investigation|...> \
--route-text '<proposal source words>' \
--body-file <packet SPEC.md path>
agentic-os-intake-sync propagates the row to Linear automatically.Maintain this compact bundle while grooming:
Populate only sections that are mature enough for the current stage.
The skill is complete when the Agentic OS proposal has a source-backed spec
packet, a verified Linear issue under the Agentic OS project, sanitized
evidence, QA/rollout notes, and a local receipt describing what was created,
updated, skipped, or blocked.
Groom rough software ideas into source-backed implementation specs with original intent, capability discovery, tracker hierarchy, QA, Gherkin, and Notion documentation projection.
Append environment variables to ~/.zshenv on bigmac, genomesbox, and the Mac laptop in one step. Use when the user pastes `KEY=value` pairs and asks to add them to zshenv, or when setting secrets that need to be available on all three hosts. ssh aliases `bigmac`, `genomesbox`, and `mac` are already configured where needed.
Commit all local changes in logical groups until the repository is clean. Use when the user asks to commit everything, make all needed commits, or cleanly commit the full worktree without pushing.
Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with `composio listen`, script workflows with `composio run`, and call authenticated app APIs with `composio proxy`. Use when the user asks how to do something with `composio`, wants to run a known tool slug, needs to discover a slug with `composio search`, fix a missing connection with `composio link`, inspect tool inputs with `--get-schema` or `--dry-run`, troubleshoot top-level CLI flows, or explicitly needs `composio dev` guidance.
Use when the user wants to work a LOS Jira ticket or non-trivial LOS task in a dedicated fast worktree, especially when they mention /workon, /orchestrate, fast worktree, use a worktree, or parallel agents.
Use when working or resuming LOS Jira implementation in a fast worktree with minimal chat output, especially after noisy /workon loops, repeated stack setup, test polling, or context/token burn.