智能体
Agent 规划、多步流程与编排
template-skill
NoizAI
Reusable template for authoring new Agent Skills with clear triggers, workflow, and I/O contracts.
chat-with-anyone
NoizAI
Chat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and generating audio replies. Also supports generating a matching voice from an uploaded image. Use when the user says "我想跟xxx聊天", "你来扮演xxx跟我说话", "让xxx给我讲讲这篇文章", "我想跟图片中的人说话", or similar.
source-command-audit-starfield-skill
matiaszanolli
Audit Starfield per-game compatibility — BA2 v2/v3 with LZ4 block compression, CDB materialsbeta.cdb material lookup, BSGeometry .mesh resolution, and the walkable Cydonia interior. Use when the user requests a Starfield compatibility, per-game Starfield, or Starfield data-flow audit.
langsmith-fetch
ComposioHQ
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
pan-pause
eltmon
"pan pause <id> [--reason <reason>] — persistently pause an agent and stop it if running"
pan-unpause
eltmon
"pan unpause <id> — clear an agent pause gate without spawning it"
all-up
eltmon
"Compatibility redirect: /all-up has been renamed to /pan-flywheel"
pan-knowledge
eltmon
"pan knowledge <id> — spawn a knowledge agent to maintain the project's Open Knowledge Format (OKF) bundle"
pan-docs
eltmon
Find, update, and structure Overdeck documentation using the docs index and documentation guide
pan-show
eltmon
"pan show <id> — show agent state, work history, context, or health for an issue"
pan-admin-cloister
eltmon
"pan admin cloister <cmd> — deacon-lite management: status, start, stop, emergency-stop"
qoder-wiki
chujianyun
Qoder 官方文档知识库，包含产品介绍、用户指南、功能配置、扩展能力、账户定价和故障排查。当用户询问 Qoder 相关问题（如安装、使用、功能、定价、快捷键、MCP、Skills、Quest Mode、Repo Wiki 等）时使用此 skill。
plugin-best-practices
FradSer
Validates Claude Code plugins against architectural best practices for Agents, Skills, MCP, and Progressive Disclosure. Use when validating plugin structure, reviewing manifest files, checking frontmatter compliance, or verifying tool invocation patterns.
erc-8004
tenequm
Build with ERC-8004 Trustless Agents - on-chain agent identity, reputation, validation, and discovery on EVM chains. Use when registering AI agents on-chain, building agent reputation systems, searching/discovering agents, working with the Agent0 SDK (agent0-sdk), or implementing the ERC-8004 standard. Triggers on ERC-8004, Agent0, agent identity, agent registry, agent reputation, trustless agents, agent discovery.
create-feishu-doc
FradSer
This skill should be used when the user asks to "create a Feishu doc", "create a new doc in Feishu", "open Feishu and create document", "create document in leiniao-ibg", or mentions creating documents in Feishu/Lark workspace.
ai-app
laguagu
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI application, Next.js AI, useChat, streamText, ai-elements, build AI app, create chatbot
say-hi
amilich
Respond with a friendly greeting. Use when the user says hi, hello, greets the agent, or asks to be greeted.
source-command-audit-parsers-skill
matiaszanolli
Parser-discipline audit of the non-NIF, non-ESM readers of untrusted game input — BSA/BA2/CSG archives, BGSM/BGEM, Starfield CDB, Havok HKX packfiles, FaceGen sidecars, MenuXml parsing, and Steam VDF/ACF. Use when the user requests a parser-discipline, archive-reader, or untrusted-format audit.
source-command-audit-papyrus-skill
matiaszanolli
Deep audit of the Papyrus frontends — the .pex reader and 5-phase decompiler (crates/pex, Champollion port) and the .psc lexer and Pratt parser (crates/papyrus) — for untrusted-input bounds, decompiler soundness, and depth caps. Use when the user requests a Papyrus, .pex, or .psc frontend audit.
source-command-audit-sync-skill
matiaszanolli
Re-sync every ByroRedux audit skill (.claude/commands/audit-/SKILL.md and the shared _audit- files) against the code landed since the last sync — closed-issue sweep, delta read, premise re-measure, ownership-map fold-in. Use when the user asks to update, refresh, or re-sync the audit skills.
source-command-audit-regression-skill
matiaszanolli
Verify that closed ByroRedux bug fixes haven't regressed by dynamically discovering closed GitHub issues, locating each fix and its guard test, and reporting any fix that has gone missing as a regression. Use when the user requests a regression verification or closed-fix recheck audit.
source-command-audit-scripting-skill
matiaszanolli
Deep audit of the M30/M47 scripting runtime — the AST-to-ECS recognizer chain (decline-on-unmodeled), fragment and quest-stage dispatch, ECS event/timer/condition/trigger systems, cell-loader script attach, scene/package/cinematic playback, legacy ObScript quest execution, and the SKSE/JContainers provider-compat layer. Use when the user requests a scripting-runtime, recognizer, fragment-dispatch, event-runtime, ObScript, or provider/extender-compat audit.
source-command-audit-safety-skill
matiaszanolli
Audit ByroRedux for unsafe-code violations, undefined behavior, FFI lifetime bugs, memory and resource leaks, Vulkan specification errors, GPU layout drift, teardown hazards, and sandbox trust-boundary failures. Use when the user requests a safety, memory-safety, Vulkan-safety, or unsafe-code audit.
source-command-audit-tech-debt-skill
matiaszanolli
Audit ByroRedux accumulated technical debt — stale markers, dead code, logic duplication, magic numbers, stub implementations, doc rot, audit-finding rot, oversized files, and test hygiene. Use when the user requests a tech-debt, code-debt, or cleanup-candidate audit.