From d-nd-core
Auto-optimize skills through mutate-verify loops. Use when skill tests show failures or when asked to optimize a skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/d-nd-core:autoresearchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The system improves its own skills through iterative loops.
The system improves its own skills through iterative loops.
Run /eval on the target skill. Record trigger accuracy and fidelity.
For each failure:
ONE change per iteration. Never more than one variable at a time.
Run /eval again. Compare with baseline:
Baseline → final score, what changed, how many iterations.
npx claudepluginhub grazianoguiducci/d-nd-seed --plugin d-nd-coreAutonomously optimizes skill prompts using a mutate/score/keep evolutionary loop with git-based revert. Useful for improving SKILL.md performance over time.
Autonomously optimizes Claude Code skills by iteratively running them on test inputs, scoring against binary evals, reflecting on failures to mutate prompts, and archiving improvements. Invoke via /auto-optimize for skill enhancement or autoresearch.
Automated 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.