skill-optimize
The /skill-optimize command runs an offline training loop that iteratively improves a skill's SKILL.md file by testing candidate refinements against accumulated learning trajectories. Use this command when a skill has gathered eight or more learn-rule corrections and you want to automatically propose and validate bounded patches that increase performance on held-out validation data, with budget and epoch controls to manage optimization costs.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/rohitg00/pro-workflow/HEAD/commands/skill-optimize.md -o ~/.claude/commands/skill-optimize.mdskill-optimize.md
# /skill-optimize - SkillOpt-flavored offline training Run an offline, budget-capped optimization loop over a skill's accumulated `learn-rule` trajectories. Proposes bounded patches via an optimizer LLM, validates each candidate against a held-out portion of the same trajectories, and overwrites SKILL.md only when the candidate strictly improves the weighted score. ## Quick Start ```text /skill-optimize <slug> [--epochs 3] [--budget-usd 0.50] ``` ## What it does 1. Pulls recent `learnings` rows scoped to the skill slug (or global) 2. Splits them into train + validation (~25% holdout, freezes validation set) 3. Runs `epochs` x `minibatches` rounds of: reflect → aggregate → clip → apply → evaluate → gate 4. Stops on: budget exhausted, kill switch (`~/.pro-workflow/STOP`), no improvement, or epochs done 5. If any candidate beat the baseline, overwrites SKILL.md and stamps the new hash ## Requirements - 8 or more existing `learnings` rows for the slug - `ANTHROPIC_API_KEY` (or `OPENAI_API_KEY` / `OPENROUTER_API_KEY` / `FIREWORKS_API_KEY` with matching `--optimizer-provider`) - `npm run build` has been run in the pro-workflow plugin directory at least once ## Examples ```text /skill-optimize pro-workflow /skill-optimize wiki-research-loop --budget-usd 1.0 --epochs 5 /skill-optimize wrap-up --optimizer-model claude-opus-4-7 --evaluator-model gpt-4o-mini ``` The third example mixes providers. The CLI infers the provider from the model id (`claude-*` → anthropic, `gpt-*` / `o*` → openai), so you do not need `--evaluator-provider openai` for `gpt-4o-mini`. Pass an explicit `--optimizer-provider` / `--evaluator-provider` to override inference. See [skills/skill-optimizer/SKILL.md](../skills/skill-optimizer/SKILL.md) for full mechanics, defaults, and the SkillOpt provenance.
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Analyze session token usage and cost patterns. Identify expensive operations and recommend optimizations. Use to understand and reduce session costs.
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
Multi-phase development agent. Research > Plan > Implement with validation gates. Use PROACTIVELY when building features that touch >5 files or require architecture decisions.
Analyze permission denial patterns and generate optimized alwaysAllow/alwaysDeny rules. Use when permission prompts slow down workflow.
Break down complex tasks into implementation plans before writing code. Use when task touches >5 files, requires architecture decisions, or has unclear requirements.
Code review specialist that verifies every finding against actual code before reporting. Use before committing, for PR reviews, or after major changes.
Confidence-gated exploration that assesses readiness before implementation. Scores 0-100 across five dimensions and gives GO/HOLD verdict.