All authors
Claude Skills by WenyuChiou
github.com/WenyuChiou9 skills0 installs8 views
- Tool Calling TutorWhen the user is building a tool-calling agent and gets stuck — "為什麼 LLM 不呼叫我的 tool", "我這 schema 哪裡寫壞", "tool 被呼叫但 args 不對", "ReAct loop 跑不停", "the LLM won't call my tool", "help me design a function schema", "debug this tool-use behavior". Walks them through a 4-branch diagnostic + 5-step schema design walkthrough, with references to bad/good schema A/B and SDK-diff cheatsheet. Do NOT use for: pure LangChain / LangGraph / CrewAI framework questions (route to Stage 4 frameworks), MCP server b...Votes: 0GitHub stars: 7,389
- Docs> **Companion to [`when-to-invoke.md`](when-to-invoke.md)**. That doc covers **trigger conditions** for the orchestration skills (splitter / gate / reconciler). This doc covers **per-task scenarios** for the 3 delegation skills (`codex-delegate` / `gemini-delegate` / `coding-agent`).Votes: 0GitHub stars: 28
- Agent Acceptance GateUse when reconciled multi-agent output needs an evidence-based PASS, CONDITIONAL PASS, or FAIL record before authorized delivery.Votes: 0GitHub stars: 28
- Agent Context BudgetUse when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.Votes: 0GitHub stars: 28
- Agent DebateUse when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.Votes: 0GitHub stars: 28
- Agent Output ReconcilerUse when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts before an acceptance decision.Votes: 0GitHub stars: 28
- Agent Plan Act ReflectUse when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from `agent-debate` (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.Votes: 0GitHub stars: 28
- Agent Shared MemoryUse when the user asks to update shared memory, initialize multi-agent memory, summarize decisions so far, identify open questions, or prepare a fresh session primer.Votes: 0GitHub stars: 28
- Agent Task SplitterUse when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for research-domain routing that owns .research, .paper, Zotero, Obsidian, or NotebookLM workflows; use research-hub-multi-ai for those.Votes: 0GitHub stars: 28