study8677

High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes `refresh_filesystem` and `ask_filesystem` for building and querying the knowledge graph.

Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

Bootstraps a new multi-agent repository from the RepoBrain template via `init_agent_repo`. Supports quick scaffold and full runtime profile setup including MCP toggle, swarm preference, sandbox type, and optional git init. LLM configuration is handled later…

Performs deep research on a topic via `deep_research`. Simulates a multi-step research process and returns a comprehensive research result as a string.

One-click initialization of a multi-agent repository from the RepoBrain template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including MCP toggle, swarm preference context, sandbox…

Use when the user asks to curate, deduplicate, merge, pin, archive, mark stale, promote, or clean up MemoBox memories.

Use at the start of non-trivial work when the current project already contains .memobox, or when the user explicitly asks to inspect a MemoBox index.

Use at the end of non-trivial work in an opted-in .memobox project only when the result passes the durable-memory worthiness gate, or when the user explicitly asks to save a memory.

Use automatically for non-trivial work when the current project already contains .memobox, or when the user explicitly asks to read, write, or maintain MemoBox memory.

Create or extend scion agent team templates from a high-level description of roles and workflow. Use when the user describes a multi-agent team, panel, crew, pipeline, or any scenario requiring coordinated LLM agents with distinct roles. Also use when adding…

Manage concurrent LLM-based code agents with scion - orchestrate parallel agents with isolated workspaces

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests.

Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.

Run python examples in auto mode with logging, rerun helpers, and background control.

Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.

生成一份对外可分享、脱敏的 AI-Native 开发者 README。 量化展示我对 Claude Code + Codex CLI + Kiro (AWS) + Trae (ByteDance) + Gemini Antigravity (Google) + Cursor 的使用深度、AI 协作风格、 项目与领域分布、兴趣主题，以及与 GitHub 提交的产出关联。 Trigger when the user says: "生成我的 AI 档案" / "做一份 AI-native README" / "分析我的…

引导式「架构共创」教练。当用户面对一个新项目 / 新系统、想在动手写代码前把架构想清楚时使用, 也适用于系统设计面试练习、技术方案讨论、架构评审、现有方案读图。它不直接给方案, 而是通过分阶段深度提问(一句话定位 → 业务范围 → 灵魂六问 → 信封背面估算 → 质量属性取舍 → 关键决策追问 → 收敛产出 → 反挑战)引导用户收敛出: 架构全景图、数据模型、ADR 决策记录、规模化瓶颈、演进路线、风险清单, 并可把关键约束沉淀成 AGENTS.md / 适应度函数 / eval 门禁。方法论与案例知识源自…

Use AVC (Agent View Controller) to present complex execution plans, architecture changes, and multi-step operations as interactive visual UIs. Instead of dumping walls of text, pipe structured JSON to `avc` for human visual review and confirmation. The human…