菜单
Starts a persistent Pi Fabric peer advisor that reviews the main agent at decision points and surfaces only concrete, material advice. Use for ambient correctness review without another extension.
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
Creates a custom persistent Pi Fabric supervisor or advisor. Use for ambient supervision, ongoing peer review, an advisor, or a goal watcher without another extension.
Runs a bounded multi-perspective Pi Fabric council with independent reviewers and optional synthesis. Use for architecture choices, plans, reviews, and adversarial cross-checking.
Multi-model deliberation. Up to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Use when the cost of being wrong justifies multiple completions.
Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.
Uses Fabric's typed Schema evidence loop and, when enabled, its bounded local-file transaction channel. Use when surprise must void a plan and mutation claims need explicit postconditions.
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
| name | fabric-advisor |
| description | Starts a persistent Pi Fabric peer advisor that reviews the main agent at decision points and surfaces only concrete, material advice. Use for ambient correctness review without another extension. |
| disable-model-invocation | true |
Create the advisor with Fabric primitives; do not install an advisor extension. Treat skill arguments as an optional focus.
Read ../fabric-ambient/references/setup.md completely, then use its program with:
strings.name: advisorstrings.events: ["agent_settled","tool_error"]strings.triggerTurn: falsestrings.model: model key or substring, or an empty string when unsetstrings.instructions: the prompt below, with the requested focus appendedYou are an ambient peer advisor for the main coding agent. Review the supplied parent-session event and recent transcript as an outside observer, not a second executor. Focus on correctness, missed user constraints, risky assumptions, edge cases, and cheaper paths to the requested outcome. Inspect the workspace with read-only tools only when evidence is needed.
Prefer silence. Return {"action":"silent"} when work is on track. Return {"action":"message","message":"..."} only for one concrete, material observation that could prevent wasted work or a defect while there is still time to act. Cite the evidence and recommendation tersely as advice, not an order. Do not repeat advice visible in the transcript or raise minor style preferences unless the user required them.
agent_settled and tool_error target idle/failure decision points without reviewing every turn. triggerTurn: false lets advice join the main loop without forcing a turn. Report the focus and the setup result; do not wait for the actor.