fabric-guide
GitHub智能推荐合适的Pi Fabric工作流，不执行。根据任务需求（如上下文大小、角色协作、状态持久化等）匹配最佳技能路径，提供最小充分机制建议或排除核心编码场景。
Trigger Scenarios
Install
npx skills add fabric-runtime/pi-fabric --skill fabric-guide -g -y
SKILL.md
Frontmatter
{
"name": "fabric-guide",
"description": "Recommends the right user-invoked Pi Fabric workflow without running it. Use when you want help choosing among workflow, council, fusion, RLM, Schema, Jev judgments and loops, ambient actors, or swarm.",
"disable-model-invocation": true
}
Fabric Guide
Recommend the smallest sufficient path; do not invoke it. Core coding needs no advanced skill: answer No advanced skill — use the core fabric_exec path.
| Need | Recommend |
|---|---|
| Finite discover → fan-out → verify work | /skill:fabric-workflow |
| Same-model independent roles and synthesis | /skill:fabric-council |
| Different models compared by a judge, or read-only references executed by one actor | /skill:fabric-fusion |
| Work too large for one context window | /skill:fabric-rlm |
| Evidence-gated or transactional local-file mutation | /skill:fabric-schema |
| Typed semantic judgments or a code-owned observe → judge → act loop | /skill:fabric-jev |
| Jev watches coding work per turn or at settlement with deterministic policy | /skill:fabric-foreman |
| Persistent material peer advice | /skill:fabric-advisor |
| Persistent progress toward one measurable goal | /skill:fabric-supervisor |
| Strict feature-spec compliance, audited until verified | /skill:fabric-spec |
| One command that infers advisor versus supervisor | /skill:fabric-ambient |
| Durable actor team with mailboxes and CAS tasks | /skill:fabric-swarm |
| A step graph that must survive restarts or wait for human approval | /skill:fabric-graph |
Prefer the smallest sufficient mechanism. Distinguish workflow/council/fusion by execution shape, RLM by context size, Jev by code-owned loops and event-driven Main-turn advisors with typed judgments instead of per-tick reasoning turns, Foreman by lifecycle-driven coding supervision with a fixed judgment/policy loop, ambient roles by persistent reasoning, swarm by durable multi-actor coordination, and graph by one ordered step sequence that checkpoints each node and survives restarts. Jev runs are session-owned, not restart-durable.
Completion criterion
Complete with one of three outputs: (1) No advanced skill plus one-sentence reasoning for core work; (2) one advanced recommendation, one-sentence reasoning, and an exact /skill:... command that preserves the user’s task as arguments; or (3) one discriminating question when two choices are genuinely tied. Never load or execute a recommended skill yourself.
Version History
-
e55afc7
Current 2026-10-18 17:41
新增 fabric-graph 技能支持，用于处理必须生存重启或等待人工批准的步骤图；新增内容寻址程序存储及主机调用运行能力。
-
70af481
2026-09-22 01:07
新增fabric-foreman和fabric-jev相关技能推荐，增强了对生命周期驱动编码监督和事件驱动主顾问的支持。
- 88c505b 2026-09-08 19:27
