Evaluates and improves the exploration-cycle skills, prompts, routing, and artifact quality using baseline-first, one-hypothesis iteration loops with keep-discard decisions and experiment ledgers.
How this skill is triggered — by the user, by Claude, or both
Slash command
/exploration-cycle-plugin:exploration-optimizerThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<example>
Ask for:
Confirm:
This skill implements autoresearch-style optimization for the exploration-cycle system. It uses a baseline-first iteration loop to improve skill prompts and logic.
Usage:
python3 ./scripts/execute.py \
--target ${plugins}/skills/user-story-capture/SKILL.md \
--eval-script ./scripts/eval_runner.py \
--goal "Improve Gherkin block accuracy" \
--iterations 3
For a concrete target-specific playbook, use references/spec-kitty-skill-optimizer-program.md when optimizing the Spec-Kitty agent/workflow files themselves.
The execute.py script follows a disciplined loop:
keep or discard.Always conclude execution with a Source Transparency Declaration explicitly listing what was queried to guarantee user trust: Sources Checked: [list] Sources Unavailable: [list]
./scripts/benchmarking/run_loop.py --results-dir evals/experiments for repeatable improvement loops.audit-plugin to verify the generated artifacts.npx claudepluginhub richfrem/agent-plugins-skills --plugin exploration-cycle-pluginAutomated skill improvement loop that runs evals, diagnoses judge failures from traces and rationale, edits SKILL.md to fix issues, re-runs, and checks for regressions. Use when improving a skill based on eval results without manual iteration.
Runs a rigorous iteration loop for artifacts, prompts, briefings, or skills with baseline scoring, metrics, stop criteria, and keep/reject decisions.
Autonomously optimizes skill prompts using a mutate/score/keep evolutionary loop with git-based revert. Useful for improving SKILL.md performance over time.