搜索

PythonReactSEOPDF

Metta-AI AI Skills

GitHub ↗

浏览 Metta-AI 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。

作者统计

已收录技能

45

收录技能的仓库 Stars 合计

90

仓库 Forks

45

平均每个技能的仓库 Stars

2

同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。

45 个技能

全部技能

GitHub

graphite-stack

Metta-AI

Split changes into a Graphite stack with PR titles and descriptions. Use when asked to create or propose a stacked PR series.

GitHub

sync-main

Metta-AI

Sync the branch with origin/main by fetching and merging or rebasing, then resolve conflicts and summarize changes. Use when asked to sync with main.

GitHub

review-main

Metta-AI

Review branch changes vs main using a merge-base diff and return prioritized findings, risks, and cleanup opportunities. Use when asked to review changes against main/origin/main.

GitHub

pr-summary

Metta-AI

Generate a PR title and description from the branch diff vs main. Use when asked for a PR summary or PR description.

GitHub

test-triage

Metta-AI

Diagnose pytest or CI failures, identify root cause, and implement the minimal fix. Use when tests fail or CI reports errors.

GitHub

recipe-curriculum-audit

Metta-AI

Explain maps, variants, and curriculum ordering used by a training command or recipe. Use when asked to audit a recipe configuration.

GitHub

cleanup-refactor

Metta-AI

Simplify code and remove legacy/backcompat shims while preserving behavior. Use when asked to clean up or simplify code.

GitHub

simplify-diff

Metta-AI

Make an existing change more concise without altering behavior. Use when asked to simplify or reduce a diff.

GitHub

sync-nim-python

Metta-AI

Compare Nim and Python scripted agent implementations and align behavior. Use when asked to port or ensure parity between Nim and Python.

GitHub

checkpoint-find

Metta-AI

Locate the latest checkpoint for a run id and provide a follow-up play/eval command. Use when asked to find a checkpoint.

GitHub

lint-fix

Metta-AI

Run lint autofix (default `metta lint --fix`), address remaining lint errors, and summarize changes. Use when asked to fix lint issues.

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。