Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

gsd-settings

Configure GSD workflow toggles and model profile

6.67k repo starsObserved in 1 repos
Agent Building

agent-auto-battle-config

OneDragon ZZZ 脚本速成指南 - 自动战斗 YAML 配置的完整语法与设计模式

6.64k repo starsObserved in 1 repos
Agent Building

agent-definition

角色模板配置指南 - 在一条龙中新增可自动战斗角色所需的 Agent 定义、头像模板、状态模板与自动战斗配置

6.64k repo starsObserved in 1 repos
Agent Building

new-config

新建配置工具 - 创建新的 agent state 模板、自动战斗 YAML 配置等,并运行构建脚本合并产物

6.64k repo starsObserved in 1 repos
Agent Building

maintainer-orchestrator

Open-source maintainer orchestration: Codex app workers, work recovery, dependencies, vision, releases.

6.40k repo starsObserved in 1 repos
Agent Building

developing-genkit-tooling

Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.

6.24k repo starsObserved in 2 repos
Agent Building

k-skill-cleaner

Interview the user and inspect coding-agent skill trigger counts to recommend unused K-skills for removal.

6.22k repo starsObserved in 2 repos
Agent Building

k-skill-setup

After installing the full k-skill bundle, configure and verify the shared cross-platform setup, then optionally wire update checks and GitHub starring with explicit user consent.

6.22k repo starsObserved in 1 repos
Agent Building

history-explorer

Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'

6.08k repo starsObserved in 1 repos
Agent Building

skill-creator-linter

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xml_escape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.

6.08k repo starsObserved in 1 repos
Agent Building