SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision—none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells, and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills.

Frontier language models are increasingly deployed as agents, from single-prompt callers to multi-step execution harnesses with tools, files, and verifiers. In such settings, domain adaptation is no longer only about model weights or prompts: it also requires improving the procedures by which the agent gathers evidence, calls tools, follows domain conventions, and formats outputs. Agent skills provide a natural interface for this procedural adaptation: a skill is a portable natural-language artifact that packages procedures, domain heuristics, tool policies, output constraints, and failure modes, letting a frozen agent adapt through external text. If the recurring object of adaptation is the agent's procedure, the skill document itself should be trainable. Yet weight adaptation is often unavailable for closed frontier models and expensive for open ones, while manually written or one-shot skills are brittle under a target domain or harness.

We introduce SkillOpt, a text-space optimizer for agent skills. Given a target domain, an initial skill, and the model being adapted, SkillOpt repeatedly samples trajectory batches, analyzes successes and failures, and asks a frontier optimizer model to propose structured add/delete/replace edits. It then aggregates and ranks candidate edits under a textual learning-rate budget, applies a bounded update to the skill document, and evaluates the candidate skill on a held-out selection split before accepting it. Rejected edits are retained as negative feedback, while the epoch-wise slow/meta update preserves longer-horizon regularities. The deployed output is a compact best_skill.md file of roughly 300–2,000 tokens, with the adapted model and execution harness remaining fixed. The deep-learning analogy is operational rather than decorative. Rollout and reflection batch sizes control the noise in the evidence used for each edit; the textual learning rate and schedule control how far one skill version is allowed to move from the previous one; the held-out gate plays the role of validation; and the epoch-wise slow/meta update acts like a momentum term, carrying stable editing directions across epochs.

The learned artifacts also transfer beyond the exact training setting. A SpreadsheetBench skill trained on GPT–5.4 improves every smaller GPT variant we test; a Codex-trained spreadsheet skill transfers to Claude Code with a +59.7 point gain; and an OlympiadBench skill yields positive gains on Omni-MATH. These transfer results are important for the paper's application value: a skill can be optimized once, audited, and reused across related models, harnesses, or tasks without changing model weights. Our ablations explain why this works. Bounded textual learning outperforms uncontrolled rewriting, held-out gating prevents harmful proposals from accumulating, the rejected-step buffer converts failed edits into negative feedback, and the epoch-wise slow/meta update improves long-horizon refinement without bloating the deployed skill. Finally, per-benchmark case studies show that the learned skills remain compact, inspectable, and procedural rather than instance-specific.