hive.context-preservation
aden-hive/hive11k
aden-hive/hive11khive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
扩展智能体 Skill
「扩展智能体」分类共 662 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。
全部文档与办公202前端与设计261需求与规划324编码与调试449浏览器与测试380安全269Git 与发布465运维与云391数据181图表98写作与翻译239图像与视频451营销与商业510扩展智能体662科研189其他310
hive.note-takingaden-hive/hive11k
aden-hive/hive11khive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
hive.terminal-tools-troubleshootingaden-hive/hive11k
aden-hive/hive11khive.terminal-tools-troubleshooting
Read when a terminal-tools call returned something surprising — empty stdout despite no error, exit_code is null, output_handle came back expired, "too many jobs" / "session busy" / "too many PTYs", warning was set unexpectedly, semantic_status disagrees with exit_code. Diagnostic recipes only — load on demand. Don't preload; the foundational skill covers the happy path.
mcp-builder
jnMetaCode/superpowers-zh8.3k
jnMetaCode/superpowers-zh8.3kmcp-builder
在构建 MCP 服务器或 MCP 工具时使用 —— 系统化的生产级 MCP 构建方法论，覆盖工具设计、错误处理、传输层选择与测试，让 AI 助手连接外部能力
subagent-driven-developmentjnMetaCode/superpowers-zh8.3k
jnMetaCode/superpowers-zh8.3ksubagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用
using-superpowersjnMetaCode/superpowers-zh8.3k
jnMetaCode/superpowers-zh8.3kusing-superpowers
在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具
workflow-runnerjnMetaCode/superpowers-zh8.3k
jnMetaCode/superpowers-zh8.3kworkflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
yao-board
YaoApp/yao8.1k
YaoApp/yao8.1kyao-board
Kanban board and task query expert. ALWAYS invoke this skill when the user asks about boards, tasks, task status, or project progress. Do not guess task state — use this skill first.
yao-decisionYaoApp/yao8.1k
YaoApp/yao8.1kyao-decision
Typed decision expert. ALWAYS invoke this skill when you need structured classification, scoring, or probability estimation — routing tickets, grading content, detecting intent, or any task requiring typed answers with calibrated confidence.
yao-processYaoApp/yao8.1k
YaoApp/yao8.1kyao-process
Yao process execution expert. ALWAYS invoke this skill when the user needs to call a Yao process, query data models, run scripts, or check process permissions. Do not call processes without checking this skill first.
yao-webYaoApp/yao8.1k
YaoApp/yao8.1kyao-web
Web information retrieval expert. ALWAYS invoke this skill when the user needs to search the web, fetch a URL, or access real-time information beyond training data. Do not guess or use stale knowledge — use this skill first.
agent-team
anbeime/skill7.7k
anbeime/skill7.7kagent-team
产品经理与项目管理专家在应对复杂项目时，使用此技能可动态组建包含“执行、指挥、评审”的专属AI团队。实时查看多智能体辩论与决策全过程，共享统一上下文记忆，一键完成从会议决策到系统构建的全流程高效协同！
companion-skillanbeime/skill7.7k
anbeime/skill7.7kcompanion-skill
软件开发工程师与综合办公文员在长时间独自执行后台任务或处理繁琐工作时，当需要情绪陪伴与互动反馈，请使用此技能。小跃虚拟伴侣会在任务期间主动陪聊，智能生成专属生活照片并通过飞书发送温暖消息，为你提供全天候的情绪价值与贴心陪伴。
obsidian-skills-integratedanbeime/skill7.7k
anbeime/skill7.7kobsidian-skills-integrated
内容创作者与技术写作员在让AI撰写Obsidian笔记时，使用此官方技能可精准处理双链、Callout及Bases数据库语法，一键生成格式零破坏的Canvas画布与专业笔记，彻底解决AI破坏专属格式的痛点。
ontoly-software-graphanbeime/skill7.7k
anbeime/skill7.7kontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for architecture review, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source-file search.
skill-templateanbeime/skill7.7k
anbeime/skill7.7kskill-template
技能创建模板。复制此目录并修改 SKILL.md 即可创建新技能。请将所有 <占位符> 替换为实际内容。
hermes-ephemeral-delegation
Gentleman-Programming/gentle-ai7.6k
Gentleman-Programming/gentle-ai7.6khermes-ephemeral-delegation
Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegate_task for a named reason.
rdd-advisory-transportGentleman-Programming/gentle-ai7.6k
Gentleman-Programming/gentle-ai7.6krdd-advisory-transport
Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisory reviewer transport contract.
skill-creatorGentleman-Programming/gentle-ai7.6k
Gentleman-Programming/gentle-ai7.6kskill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
skill-improverGentleman-Programming/gentle-ai7.6k
Gentleman-Programming/gentle-ai7.6kskill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
skill-registryGentleman-Programming/gentle-ai7.6k
Gentleman-Programming/gentle-ai7.6kskill-registry
Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.
refly
refly-ai/refly7.5k
refly-ai/refly7.5krefly
Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly, skill, workflow, run skill, create skill, automation, pipeline. Requires: @refly/cli installed and authenticated.
audit-context-building
trailofbits/skills7.5k
trailofbits/skills7.5kaudit-context-building
Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.
devcontainer-setuptrailofbits/skills7.5k
trailofbits/skills7.5kdevcontainer-setup
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.