skill-improverlisted

Autoresearch loop for Claude Code skills — greedy keep/discard hill climbing on a 10-dimension quality rubric, with blind subagent validation for self-scoring bias. Given only a skill name, it reads that skill's history and picks which modes to run. Modes: `score` rates a skill out of 100 without editing it; `freshen` probes external references (release notes, docs, deprecation signals) and applies verified updates; `trigger` measures and tunes the frontmatter description until it fires when it should and stays silent when it shouldn't (60/40 train/test, 7 runs/query); `ages` prints every skill's verification age vs last content change; `floor` measures what a bare model already knows about a skill's subject.
air-gapped/skills · ★ 5 · AI & Automation · score 80

Install: claude install-skill air-gapped/skills

# Skill Improver — Autoresearch for SKILL.md > **Core Philosophy:** The human programs the researcher, not the research. > Apply Karpathy's autoresearch methodology — greedy hill climbing with > keep/discard against a scalar metric — to autonomously improve Claude Code > skills. ## Invocation Argument grammar: ``` /skill-improver <mode> <target> [--opts] ``` - `<mode>` — omitted = Auto | `improve` | `score` | `freshen` | `trigger` | `floor` | `ages` | `batch` - `<target>` — skill name (e.g. `gh-cli`), absolute SKILL.md path, `--all`, or glob (e.g. `vllm-*`) - `[--opts]` — mode-specific flags (e.g. `--iterations 15`, `--probe-budget 30`, `--runs-per-query 5`) Examples: ``` /skill-improver ages /skill-improver ages 'vllm-*' /skill-improver freshen autoresearch /skill-improver score gh-cli /skill-improver improve ~/.claude/skills/helm /skill-improver trigger vllm-caching /skill-improver trigger gh-cli --missed "find issue with label X" /skill-improver batch freshen --all /skill-improver freshen --group 'vllm-*' ``` If `<mode>` is omitted, run **Auto** (below). If `<target>` is omitted and mode is not `batch`, prompt the user. For `batch`, the target after `batch` selects the sub-mode (`freshen`, `improve`, or `trigger`, default `improve`); the target list comes from `scripts/scan-skills.sh`. The `--missed "<phrase>"` flag (trigger mode only, repeatable) seeds the eval set with user-reported failures as gold should-trigger queries. ## Auto (no mode given) `/skill-improv