SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

yao-meta-skillyaojingang/yao-meta-skill

Turns AI agent skills from ad-hoc prompts into engineering assets that can be designed, ported, evaluated and governed.…

No ratings yet Rate this skill
Stars2.7k
Forks253
Watchers2.7k
Open Issues4

InstallOne-line install

Installable · 14 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add yaojingang/yao-meta-skill

This repository bundles 14 skills, and you can install just one:

12 more are not listed — run npx skills@latest add yaojingang/yao-meta-skill --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Turns AI agent skills from ad-hoc prompts into engineering assets that can be designed, ported, evaluated and governed. Key capabilities include: 1. Scaffold: generates skill skeletons in exploratory, production and library modes so every new skill starts with a consistent structure; 2. Skill IR: describes skills in a platform-neutral intermediate representation so one skill can be compiled to different agent platforms; 3. Target compilers and adapters: compiles and adapts the Skill IR to target platforms, cutting the work of rewriting skills per platform; 4. Output Eval Lab: evaluates and compares skill outputs so skill changes have a measurable quality basis; 5. Review Studio 2.0: performs structured skill reviews and produces review conclusions, turning review from verbal discussion into traceable records; 6. SkillOps loop: chains skill building, evaluation, review and iteration into a closed operations loop; 7. Localized doc sync check: checks whether multilingual documentation stays in sync, preventing translated versions from drifting from the main version; 8. PR review report: automatically generates PR review reports so code change reviews share a consistent output format.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID363
Data sourceGitHub
Repositoryyaojingang/yao-meta-skill
CategoryAI & Agent Engineering / Skill Engineering & Governance
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1197197392
Node IDR_kgDOR1vIUA
Rank#358 (position within the source ranking)
Site-wide popularity rank#427 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k2026-09-302026-10-112026-09-30 · 2,6832026-10-11 · 2,696
  • Now2,696
  • Previous point · 09-30 2,683
  • vs previous point +13
  • 2 data points 11 days
01002003002026-09-302026-10-112026-09-30 · 2532026-10-11 · 253
  • Now253
  • Previous point · 09-30 253
  • vs previous point ±0
  • 2 data points 11 days

TimelineTimeline

Repository created2026-03-31 11:59:357 months ago
Data last updated2026-10-26 11:56:5723 days ago
Last commit2026-08-17 09:19:433 months ago

CommitLatest commit

Committed by yaojingang. Update Category: Routine Updates & Maintenance. Commit details: Merge pull request #17 from yaojingang/codex/trusted-generation-core-v1. This update performs routine maintenance and minor adjustments.

f5d8f68 yaojingang 2026-08-17

Next stepsNext steps