meta-apply

Solid

Privileged 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.

AI & Automation 11,977 stars 1099 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 96/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Meta-Apply: the privileged landing gate for self-modification patches This skill exists to enforce a **privilege boundary**. Producers like [`/meta-optimize`](../meta-optimize/SKILL.md) (and, later, `corpus-audit`) are **read-only** — no `Write`/`Edit`, no apply step; they can only *stage* candidate patches under `.aris/meta/pending/`. **This skill is the only place a staged patch becomes a real change to the corpus.** Splitting "propose" from "land" across two skills with different tool grants is what makes "a loop cannot apply its own patch" structural rather than a sentence the producer is asked to obey. It is **human-invoked only.** It runs when the user explicitly types `/meta-apply` after reading the producer's REPORT. That invocation IS the landing authorization (the locked 2026-05-30 decision: the human stays at the landing gate). ## The acquittal is generated HERE, not relayed The earlier design trusted a `jury_verdict: pass` field in the producer's manifest. That is **forgeable** — the producer writes that field, so a buggy/misaligned producer could stage a killed patch labelled "pass." **So this skill does not trust any producer-written verdict.** It runs the cross-model jury **itself, at landing time, on the actual staged diff** (fresh thread, paths-only). The verdict is produced where it is consumed, by the privileged human-invoked skill — nothing to forge. ## The non-negotiable rules (jury-at-landing, reject-default) For each staged patch the user asks t...

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

AI & Automation Solid

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.

11,977 Updated yesterday
wanshuiyin
AI & Automation Listed

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.

0 Updated today
mytechsonamy
AI & Automation Listed

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).

20 Updated today
apache