fable-orchestrate

Solid

Use when the user wants a task decomposed and driven by a Fable 5 orchestrator delegating implementation to Sonnet 5 workers. The Fable session decomposes into self-contained worker specs, dispatches Sonnet subagents (plain Agents for 1–2 pieces, a Workflow for genuine fan-out), reviews each result inline against its spec, merges into one task branch, and gets a binding final verdict from a fresh Fable reviewer. Trigger on "/fable-orchestrate", "fable-orchestrate <task>", or "orchestrate this with fable".

AI & Automation 43 stars 7 forks Updated today MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
55
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# fable-orchestrate Run a task with **Fable 5 as orchestrator** and **Sonnet 5 workers**. The main agent (you, on Fable) owns decomposition, specs, every accept/reject decision, integration, and the PR; workers own only the mechanical implementation of their piece. Principle: mechanical volume on Sonnet, every judgment call on Fable. ## Input The user provides a task description in prose. If no task is obvious from the invocation or the conversation, ask what to orchestrate before decomposing. ## Model check This skill assumes the session model IS Fable 5 — the orchestrator's judgment is the point. If you are not running on Fable 5, tell the user and ask whether to switch (`/model fable`) or proceed with the current model as orchestrator anyway. ## Steps ### 1. Decompose — biased against fan-out Read the relevant code first, then split the task into worker pieces. Decomposition is the highest-leverage failure point of this whole skill — a bad split wastes everything downstream — so: - **Default to fewer, larger, sequential pieces.** Parallelize only when pieces touch disjoint files; parallelism is an optimization, never the goal. One worker doing the whole task is a valid decomposition. - **Pin the interfaces between pieces upfront.** Where two pieces meet (a function signature, a schema, an event shape, a route contract), the spec states the exact interface both sides build against — workers must never invent their side of a seam. - **Each spec must be fully self-co...

Details

Author
richkuo
Repository
richkuo/rk-skills
Created
3 weeks ago
Last Updated
today
Language
JavaScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

efficient-fable

Use when running an expensive frontier model on codebase-heavy or token-heavy work and the user wants that model to orchestrate, architect, synthesize, and final-judge while cheaper helper agents do bounded heavy lifting (large repo scans, long log reduction, narrow code patches, browser/test verification, etc.). Trigger on requests like "delegate this efficiently", "save tokens on this", "use cheap subagents for the heavy parts", or any task where the expensive model's judgment matters but its throughput does not. Treat subagent reports as leads, not facts — always vet before shipping. Do NOT trigger for trivial single-step work, for high-stakes single-source-of-truth tasks (medical, legal, financial advice), or when no cheap subagents are available.

1 Updated 1 weeks ago
anshmajumdar121
AI & Automation Listed

orchestration

Fable Orchestrator · universal Grok volume agent — session on Fable 5 architects; Grok 4.5 types and self-selects research/explore/critic/device phases for any scenario. USE WHEN implementing, exploring, verifying, writing five-part specs, consulting fable-advisor, fan-out parallel lanes, self-routing subagents, or managing token spend under Fable + SuperGrok Heavy.

1 Updated 1 weeks ago
BuildContext
AI & Automation Listed

orchestrate

Use when bounded fan-out, multi-agent research, cross-family review, parallel audits, Herdr control, or autonomous ready-issue implementation helps. Not for tiny work, coupled debugging, or run-until-STOP jobs; use diagnose or autopilot.

2 Updated today
mblauberg