meta-apply
SolidPrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved. The ONLY skill permitted to mutate the skill corpus from a self-modification proposal. Runs the cross-model jury AT LANDING (on the staged diff, not a producer-written claim), requires human approval, enforces author≠reviewer family, backs up, applies, stamps provenance, logs. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
Install
Quality Score: 96/100
Skill Content
Details
- Author
- wanshuiyin
- Repository
- wanshuiyin/Auto-claude-code-research-in-sleep
- Created
- 3 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
meta-optimize
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
apply-arbiter-patch
Reads the patch manifest produced by consensus-arbiter, shows a git-style diff summary, archives every target file to .vibeflow/archive/ (a timestamped version trail) AND snapshots it for one-command rollback before touching anything, asks for explicit operator confirmation (unless --yes), and applies via `git apply`. Updates `arbiter-decisions.md` with applied:true + timestamp. Optional `--run-tests` runs the project's test command afterward and reminds the operator how to revert if they break.
magpie-optimize-skill
Optimize an existing framework skill (or sweep a set of them) by applying the restructuring patterns proven on the security-skill suite: split an oversized `SKILL.md` into linked sibling docs, lift concrete/project-specific values out of the body into `<project-config>` placeholders, replace in-agent-context body reads with out-of-context tool calls, batch per-item fetches into a single upfront pass, and add a deterministic pre-flight no-op classifier ahead of LLM passes. Every change is a behavior- preserving proposal the maintainer signs off on; the skill validator must stay green before and after. The refactoring sibling of `write-skill` (which authors net-new skills).