Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

trampoline-ai

@trampoline-ai source repo

5 published skills

  1. ▌
    Avalanche · trampoline-ai bundle
    Design, build, run, and refactor agentic workflows with Avalanche. Use when a user describes an outcome that should become a typed multi-step workflow, or when creating an Avalanche flow or belt, choosing deterministic versus PredictRLM-backed agent steps, composing DAGs with >> and &, selecting embedded/operator/browser/TUI execution, or using Iceberg or Lance persistence.
    0
    installs
  2. ▌
    Fractal · trampoline-ai bundle
    Delegate analysis- and context-heavy work to Fractal, an agentic CLI powered by a self-harnessed Recursive Language Model (predict-rlm), by running it non-interactively (fractal -p). Reach for it when a task needs reasoning over a large or deep codebase, synthesizing an answer across many files, auditing, or open-ended investigation — work that would otherwise flood your own context. The RLM reasons over context programmatically (no context rot) and returns a distilled answer. Use when asked to run Fractal headless, script it, call it from CI or another agent, or offload a heavy analysis/large-context task. Less suited to trivial single-file edits you can do directly.
    0
    installs
  3. ▌
    Fractal Add Provider · trampoline-ai
    Guide contributors through adding or updating Fractal model providers, provider auth wiring, and provider model options. Use when adding a Fractal provider, changing provider defaults/model_options/restricted_models, updating setup model menus, or preparing provider-related commits and PRs.
    0
    installs
  4. ▌
    Rlm · trampoline-ai
    Plan and build a new callable Recursive Language Model with predict-rlm. Use when a user wants to design an RLM, assess whether an RLM fits a workflow, or implement an RLM package with structured boundaries, skills, host-side tools, custom adapters, or runtime-kernel extensions. For optimization of an existing RLM, use rlm-gepa instead.
    0
    installs
  5. ▌
    Rlm Gepa · trampoline-ai
    Add, evaluate, and optimize RLM-GEPA projects for an existing PredictRLM. Use when a user wants to improve reusable RLM instructions from execution traces, build a train/validation optimization harness, configure AgentSpec or OptimizeConfig, run optimize --check, or inspect RLM-GEPA run artifacts. For creating the base RLM itself, use rlm first.
    0
    installs