Skill Optimizer

Train an existing SKILL.md the way a deep-learning optimizer trains weights: via rollouts, gradient-like reflections, validation-gated acceptance. No model retraining; only the skill markdown changes.

When to use

Use this skill when:

• A pro-workflow skill has accumulated 8+ learn-rule rows for it
• The user reports the skill is "getting bloated" or "rules keep being repeated"
• The user wants offline, budget-capped improvement over multiple sessions

Do not use when:

• Skill has fewer than 8 trajectories (nothing to learn from)
• The user wants real-time edits (this is offline, single-shot)
• No key has been explicitly configured for the selected provider

Architecture (mirrors SkillOpt's six-stage loop)

rollout      pull recent learnings from SQLite (existing learn-rule rows)
reflect      optimizer LLM analyzes a minibatch, proposes add/delete/replace patches
aggregate    vote-merge patches across minibatches
select       clip by LR budget (default: 3 adds, 2 deletes, 3 replaces per step)
update       apply selected patches to a candidate skill content
evaluate     evaluator LLM scores candidate against held-out validation items
gate         accept candidate only if weighted score >= current + acceptThreshold
slow update  at epoch boundary, consolidate accepted edits into a coherent rewrite

Failed candidates are stored in a rejection buffer and fed back to the next reflect step so the optimizer doesn't propose the same patch twice.

Run it

In a plugin session, use the providers MCP server's run_provider_task tool with task: "optimizer" and args: ["--slug", "<slug>", "--budget-usd", "0.50"]. Keys come from the plugin configuration dialog. Standalone CLI installations use explicit PRO_WORKFLOW_*_API_KEY variables. See provider configuration; never request keys in chat or retrieve existing machine credentials.

/skill-optimize <slug> [options]

Options (all optional; sensible defaults shown):

Kill switch: touch ~/.pro-workflow/STOP aborts the loop between steps.

Output

• Candidate accepted → SKILL.md overwritten, hash stamp appended in HTML comment
• Run details persist in optimization_runs, optimization_candidates, optimization_patches, optimization_rejections
• Validation set persists in optimization_validation (reusable across runs)

Inspect after:

sqlite3 ~/.pro-workflow/data.db "SELECT id, skill_slug, initial_score, best_score, accepted_steps, rejected_steps, spent_usd FROM optimization_runs ORDER BY id DESC LIMIT 5"

Rules

• Validation set is frozen at run start. Never re-derive from new corrections mid-run.
• One candidate per step. No parallel branches.
• Slow-update output is itself a candidate; it must pass the gate to replace the best.
• The optimizer LLM and evaluator LLM may be different models. Mixing a strong optimizer with a cheap evaluator is the SkillOpt-recommended config.
• If spent_usd >= budget_usd at any step boundary, the loop ends with stopped_reason="budget exhausted".
• Patches whose anchor is no longer present in the skill (because a prior patch in the same step removed it) are recorded as rejected with reason anchor_missing.

Provenance

Inspired by Microsoft SkillOpt (arXiv:2605.23904). The six-stage rollout/reflect/aggregate/select/update/evaluate pipeline, LR budget, rejection buffer, and slow / meta update mechanics are adapted to pro-workflow's existing SQLite + learn-rule data plane. No SkillOpt code is reused. "ReflACT" is not a SkillOpt term and is not used here; the loop is referred to by stage names only.