gsd-settings
Configure GSD workflow toggles and model profile
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Configure GSD workflow toggles and model profile
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
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
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
Open-source maintainer orchestration: Codex app workers, work recovery, dependencies, vision, releases.
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.
Interview the user and inspect coding-agent skill trigger counts to recommend unused K-skills for removal.
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.
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?'
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.