Skill
OPRO LLM as optimizer
OPRO: given (prompt, score) history, ask local Ollama to iteratively propose better prompts; pre-ILP draft-generation role in the harvest loop
Primitives inside (5)
auto-refine-before-review-paneldisciplineRun a cheap automatic prompt optimizer (OPRO ~10 steps, TextGrad, a rubric-driven pass) on the draft BEFORE a multi-round multi-reviewer panel starts, and hand its output to the panel as the R0 baseline — the panel stays the quality gate (a rubric-as-loss evaluator misses what reviewers catch), the optimizer exists so the first round refines instead of reconstructing a weak start; the versioned store update (SUPERSEDES, immutable append) stays downstream of the gate.
When: A draft prompt is about to enter a multi-round multi-reviewer improvement loop (ILP-style panel) from a naive or hastily-written start, and an optimizer + rubric metric are available for a 5-10 step pass.
opro-history-overflow-trim-oldestgotcha-fixWhen the (prompt, score) history overflows the optimizer model's context, trim the oldest pairs first — preserve the recent trajectory rather than truncating arbitrarily.
When: A long-running LLM-as-optimizer loop whose accumulated history approaches the model's context window.
opro-optimizes-the-judge-not-ground-truthgotcha-fixAn LLM-as-optimizer maximizes the judge metric, not ground truth — metric gaming is an expected failure mode; a downstream refinement/review gate must catch it before adoption.
When: Any automated optimization loop whose score comes from an LLM judge or proxy rubric rather than ground truth.
opro-plateau-temperature-jittergotcha-fixWhen the OPRO score trajectory plateaus, the optimizer may cycle without improvement — add temperature jitter to break the cycle instead of burning more identical steps.
When: An LLM-as-optimizer run shows flat scores across consecutive steps.
opro-score-history-optimize-looptool-sequenceTreat prompt optimization as black-box optimization: feed an LLM the history of (prompt, score) pairs plus the rubric and ask it to propose a better prompt; iterate ~10 steps, track the score trajectory, emit the best — pure local Ollama HTTP, no DSPy/TextGrad.
When: You need an automatically improved prompt draft and have (or can build) a rubric metric that scores candidate prompts.
Get the whole skill
All 5 primitives of this skill as one package, with the order to apply them.
Buy only the primitives you need
Each primitive is 1 credit (≈ €0.10). Pick them from the list above — the button is next to each one.
Upgrade your own skill
Paste your skill; we pick the 5 primitives from the shelf that fit it best, as one bundle for 5 credits (≈ €0.50).
Upgrade my skillNeighbour skills
Skills whose primitives are closest to this one (bge-m3 similarity):