RepoAI
Browse MCPs

Efficient Fable

85TrustedInstructions only

Orchestrate complex coding tasks by delegating routine labor to lighter models.

What it does

Efficient Fable changes how your assistant handles large-scale development by establishing a hierarchy of labor. Instead of relying on a high-tier model for every repetitive scan or routine edit, this approach positions the primary assistant as an architect and judge. It offloads repetitive data gathering, log analysis, and preliminary coding passes to more economical, specialized sub-agents.

The system ensures that high-cost reasoning tokens are reserved for critical decision-making, such as resolving architectural conflicts, reconciling disparate research findings, and performing final quality verification. By structuring the workflow this way, you maintain high-level oversight while significantly reducing the overhead associated with massive codebase interactions.

When it earns its place

Reach for it when…

Apply this pattern when navigating large, unfamiliar codebases or complex multi-file refactors where the breadth of the task would otherwise exhaust your primary assistant's token limits. It is ideal for scenarios involving deep log exploration, broad documentation reviews, or extensive test suites that require gathering significant evidence before a meaningful fix can be determined.

Look elsewhere when…

Do not employ this strategy for compact tasks, simple one-off code snippets, or highly iterative debugging where the back-and-forth between the user and assistant is too rapid to support intermediate delegation. If the cost of orchestrating the sub-agents exceeds the time saved by automating the research phase, direct interaction with a single model remains the faster and more straightforward path.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • help me plan a large refactor across these modules
  • analyze why this integration is failing across multiple services
  • summarize the API usage patterns throughout the entire repo
  • manage this feature request by splitting up the implementation tasks

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/BuilderIO/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/efficient-fable ~/.claude/skills/efficient-fable

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/skills/skills/efficient-fable .claude/skills/efficient-fable

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.