efficient-fablelisted

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.
anshmajumdar121/skill-x · ★ 0 · AI & Automation · score 72

Install: claude install-skill anshmajumdar121/skill-x

# Efficient Fable (retweaked) Use a high-cost frontier model as the **orchestrator, architect, synthesizer, and final judge**. Use cheaper subagents for the **bounded heavy lifting** that does not require the orchestrator's full judgment. The orchestrator retains truth-judgment; the subagents retain signal-gathering. > This is the retweaked version adapted for the > [skill-x](https://github.com/<your-org>/skill-x) collection. The > original lives at > [BuilderIO/skills](https://github.com/BuilderIO/skills/tree/main/skills/efficient-fable); > this version generalizes the orchestrator role beyond Claude > Fable, adds an explicit when-NOT-to-use section, and cross-references > the other skills in this collection. ## When this skill shines Reserve the orchestrator for: - **Decomposing ambiguous work into clean parallel slices.** - **Architecture, product, and safety tradeoffs** that need full judgment. - **Reading conflicting subagent reports** and deciding what matters. - **Integrating partial implementations** into one coherent plan. - **Final review, risk assessment, and user-facing synthesis.** ## When NOT to use this skill Skip the delegation pattern if any of these is true: - The work cannot be sliced into independent chunks (one tightly coupled piece of logic). - No cheap subagents are available (you ARE the orchestrator and the only worker). - The task is high-stakes single-source-of-truth (medical, legal, financial advice) — keep all reasoning with the orch