New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Knowledge Extension Ecosystem

by echoVic in echoVic/blade-code

覆盖 Blade 的 MCP、插件、Skills、自定义命令、Hooks 与 LSP 扩展边界及其 Session 集成关系。进入条件：新增扩展来源、调整 Workspace 扩展发现、排查插件资源未生效、 修改扩展资源快照或判断扩展职责归属。不包含：内置工具执行管线（见 ../tool-and-automation-platform/）、Workspace Trust 与通用配置合并（见…

MITAuto-check passedAgent Workflows

Install Knowledge Extension Ecosystem

skills CLI
$ npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install echoVic/blade-code knowledge-extension-ecosystem --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.trae/knowledges/extension-ecosystem .claude/skills/knowledge-extension-ecosystem && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-extension-ecosystem
GitHub stars
180
Token cost
~1.3k tokens
SKILL.md length
252 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

覆盖 Blade 的 MCP、插件、Skills、自定义命令、Hooks 与 LSP 扩展边界及其 Session 集成关系。进入条件：新增扩展来源、调整 Workspace 扩展发现、排查插件资源未生效、 修改扩展资源快照或判断扩展职责归属。不包含：内置工具执行管线（见 ../tool-and-automation-platform/）、Workspace Trust 与通用配置合并（见…

  • Tasks that involve MCP servers
  • SKILL.md covers Module Structure, Gotchas, Architecture and Decisions, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Knowledge Extension Ecosystem is an agent skill from echoVic/blade-code. 覆盖 Blade 的 MCP、插件、Skills、自定义命令、Hooks 与 LSP 扩展边界及其 Session 集成关系。进入条件：新增扩展来源、调整 Workspace 扩展发现、排查插件资源未生效、 修改扩展资源快照或判断扩展职责归属。不包含：内置工具执行管线（见 ../tool-and-automation-platform/）、Workspace Trust 与通用配置合并（见 ../workspace-policy-and-shared-foundations/）。关键词：extension ecosystem、 MCP、plugin、SkillRegistry、CustomCommandRegistry、HookManager、LspSessionManager。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/knowledge-extension-ecosystem”

What it can do on your machine

Read from SKILL.md and the folder at commit 30f8684. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Extension Ecosystem loads about 1.3k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 252 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from echoVic/blade-code at commit 30f8684, republished under its MIT licence (© echoVic). 252 words, ~1,306 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-extension-ecosystem/SKILL.md (or your agent's skills folder).
name
knowledge-extension-ecosystem
description
覆盖 Blade 的 MCP、插件、Skills、自定义命令、Hooks 与 LSP 扩展边界及其 Session 集成关系。进入条件：新增扩展来源、调整 Workspace 扩展发现、排查插件资源未生效、 修改扩展资源快照或判断扩展职责归属。不包含：内置工具执行管线（见 ../tool-and-automation-platform/）、Workspace Trust 与通用配置合并（见 ../workspace-policy-and-shared-foundations/）。关键词：extension ecosystem、 MCP、plugin、SkillRegistry、CustomCommandRegistry、HookManager、LspSessionManager。

Module Structure

扩展生态先在 source project 上发现配置与资源，再由 Workspace 级注册表完成插件整合， 最后冻结为 Session 私有视图；MCP 和 LSP 还会在 Session 初始化时创建独立连接与进程。

Directory Layout
  • packages/cli/src/mcp/ — MCP transport、目录、交互、恢复、OAuth 与异步任务
  • packages/cli/src/plugins/ — 插件发现、装载及向其他扩展点的资源注入
  • packages/cli/src/skills/ — Skill 元数据发现、正文延迟加载与注册表
  • packages/cli/src/slash-commands/custom/ — Markdown 自定义命令解析和执行
  • packages/cli/src/hooks/ — Hook 配置、匹配、信任与多种执行后端
  • packages/cli/src/lsp/ — Session 级语言服务器客户端和语义查询
  • .blade/ — 仓库内项目级 Skills、命令与配置资源
Key Entry Points
  • resolveWorkspaceAgentResources() in packages/cli/src/agent/resources/WorkspaceAgentResources.ts — 初始化并缓存 Workspace 扩展注册表
  • snapshotWorkspaceAgentResources() in packages/cli/src/agent/resources/WorkspaceAgentResources.ts — 创建 Session 持有的扩展资源快照
  • resolveWorkspaceMcpConfig() in packages/cli/src/mcp/resolveWorkspaceMcpConfig.ts — 合并当前 Session 的 MCP 来源
  • resolveWorkspaceLspResources() in packages/cli/src/lsp/WorkspaceLspResources.ts — 解析并冻结当前 Session 的 LSP 配置
  • SessionRuntime.initialize() in packages/cli/src/agent/runtime/SessionRuntime.ts — 绑定 Hooks 并创建 Session 私有 MCP/LSP 运行时

Gotchas

  • Workspace Trust 只决定项目扩展资源能否被发现，配置型 Hook 还必须通过独立的精确摘要信任；信任 workspace 不等于信任其中的命令、Prompt 或 HTTP Hook(packages/cli/src/skills/SkillRegistry.ts, packages/cli/src/hooks/HookTrustService.ts)
  • source project 是 MCP/LSP/插件配置身份，execution workspace 是 worktree 中实际执行工具和启动 LSP 的路径；将两者混用会让 MCP 默认 cwd、MCP roots 或 LSP 文件边界指向错误 checkout(packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/mcp/resolveWorkspaceMcpConfig.ts, packages/cli/src/lsp/LspSessionManager.ts)
  • 插件刷新先清空再整批重注入 Workspace 注册表，但已创建 Session 使用 Skills、命令、Hooks 和 LSP 的快照，不应被刷新中的可变对象追改(packages/cli/src/plugins/PluginIntegrator.ts, packages/cli/src/agent/resources/WorkspaceAgentResources.ts)
  • 插件整合阶段只登记 MCP/LSP 定义数量，不建立连接；实际 MCP client 和 LSP process 都延迟到精确 Session 中创建(packages/cli/src/plugins/PluginIntegrator.ts, packages/cli/src/agent/runtime/SessionRuntime.ts)
  • MCP、LSP、Skills 和命令均按 workspace 或 Session 隔离，不能以无参数全局单例作为多项目调用的权威来源(packages/cli/src/mcp/McpRegistry.ts, packages/cli/src/skills/SkillRegistry.ts, packages/cli/src/slash-commands/custom/CustomCommandRegistry.ts)

Architecture

  • 扩展资源主链路是“Workspace 发现与插件整合 → Session 快照 → 工具/Prompt/事件适配”；该边界让项目切换和插件刷新不改变正在运行的模型回合(packages/cli/src/agent/resources/WorkspaceAgentResources.ts, packages/cli/src/agent/runtime/SessionRuntime.ts)
  • 插件是扩展聚合入口，可同时提供命令、Skills、Agents、Hooks、MCP 和 LSP；其中命令、Skills、Agents 注入 Workspace 注册表，Hooks 整批交换配置，MCP/LSP 由 Session 重新解析(packages/cli/src/plugins/PluginIntegrator.ts, packages/cli/src/plugins/PluginLoader.ts)
  • Skills 与自定义命令都以 Markdown 为载体，但 Skills 将元数据暴露给模型并延迟加载正文，自定义命令会在发现时加载正文并在调用前展开参数、Shell 和文件引用(packages/cli/src/skills/SkillLoader.ts, packages/cli/src/slash-commands/custom/CustomCommandExecutor.ts)
  • Hooks 是扩展域的行为拦截层，横跨工具准入、权限、会话、Agent 停止、压缩和 MCP Elicitation；它不拥有这些领域的主状态(packages/cli/src/hooks/types/HookTypes.ts, packages/cli/src/tools/execution/ToolExecutionHooks.ts)
  • MCP 工具和 LSP 工具都进入统一 ToolRegistry，但前者是外部 Execute 工具与动态目录，后者是仅在 Session 有可用服务器时注册的 ReadOnly 语义查询工具(packages/cli/src/mcp/createMcpTool.ts, packages/cli/src/tools/builtin/index.ts)

Decisions

  • 运行时资源在 Session 创建时做深拷贝快照，是为了阻止后续 workspace refresh、项目切换或插件刷新改变活动 Session 已暴露给模型的能力集合(packages/cli/src/skills/SkillRegistry.ts, packages/cli/src/slash-commands/custom/CustomCommandRegistry.ts, git:f6a82242)
  • 扩展点统一经过 Workspace Trust 后再读取项目级可执行资源，同时保留用户级资源可用性；Hooks 额外按内容摘要授权，避免“信任路径”永久授权后续修改(packages/cli/src/security/WorkspaceTrustService.ts, packages/cli/src/hooks/HookTrustService.ts, git:a172a7c0)
  • MCP 与 LSP 放在独立 Session 生命周期而非进程全局生命周期，以隔离并行 Session 的连接、目录、诊断、环境和清理责任(packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/mcp/McpRegistry.ts, packages/cli/src/lsp/LspSessionManager.ts)

Patterns

  • 插件资源使用 plugin:<plugin-name>:<resource> 或稳定 provider 名称避免跨插件冲突；短名只在唯一时才可解析(packages/cli/src/plugins/namespacing.ts, packages/cli/src/skills/SkillRegistry.ts, packages/cli/src/slash-commands/custom/CustomCommandRegistry.ts)
  • 外部扩展产生的 schema、日志、结果、指令和配置都在进入模型或 UI 前做大小、类型和安全投影，不能直接透传协议对象(packages/cli/src/mcp/McpToolResult.ts, packages/cli/src/hooks/schemas/HookSchemas.ts, packages/cli/src/config/lspSettings.ts)

Child Knowledge Nodes

  • ./mcp-protocol-runtime/SKILL.md — 进入条件：修改 MCP transport、动态目录、OAuth、Elicitation、Sampling、Tasks、结果安全或连接恢复
  • ./plugin-lifecycle-and-marketplace/SKILL.md — 进入条件：修改插件发现、安装、来源策略、兼容性、命名空间或资源注入
  • ./skills-and-custom-commands/SKILL.md — 进入条件：修改 SKILL.md/命令 Markdown 解析、覆盖优先级、延迟加载、Session 快照或调用入口
  • ./hooks-and-behavior-interception/SKILL.md — 进入条件：修改 Hook 事件、匹配、执行顺序、信任摘要、错误策略或跨领域拦截行为
  • ./lsp-code-intelligence/SKILL.md — 进入条件：修改 LSP 配置、进程代际、文档同步、诊断回注、语义查询或子 Session 继承

© echoVic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .trae/knowledges/extension-ecosystem of echoVic/blade-code.

Open the folder on GitHubat commit 30f8684

Compare with similar skills

Knowledge Extension Ecosystem next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Extension Ecosystem compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Extension Ecosystem this skillechoVic/blade-code180—~1.3kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from echoVic/blade-code

All 38 skills in this repo

  • Base64 Parser

    echoVic/blade-code

    Base64 编解码工具，支持编码/解码文本、JSON、二进制文件，自动检测格式，支持批量处理. An agent skill from echoVic/blade-code.

    180 GitHub stars~545 tokensUpdated 10 days ago
    Auto-check: notes

  • Code Review

    echoVic/blade-code

    Review frontend code for best practices, bugs, and improvements.

    180 GitHub stars~377 tokensUpdated 10 days ago
    Auto-check: notes

  • GitHub Explorer

    echoVic/blade-code

    Explore and summarize popular GitHub projects. An agent skill from echoVic/blade-code.

    180 GitHub stars~434 tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Extension Ecosystem Lsp Code Intelligence

    echoVic/blade-code

    覆盖 Session 级 LSP 配置快照、stdio 进程、文档同步、语义查询、诊断回注、崩溃恢复 和子 Session 继承。进入条件：新增语言服务器、修改 LSP 工具、排查诊断缺失/重复、 处理 worktree 或 ACP 差异、修复进程泄漏或 transport 代际问题。不包含：VS Code 扩展桥接（见…

    180 GitHub stars~1.9k tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Extension Ecosystem Skills And Custom Commands

    echoVic/blade-code

    覆盖 SkillRegistry、SKILL.md 延迟加载、自定义命令 Markdown 解析、来源覆盖、插件 命名空间、Session 快照和模型/用户调用入口。进入条件：新增 Skill 或命令字段、调整 发现优先级、调试 /command 或 Skill 工具、修改 Prompt 元数据或消费者集成。不包含： 插件安装生命周期（见…

    180 GitHub stars~2.1k tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Integration And Workflow Tool Adapters

    echoVic/blade-code

    Covers 领域能力如何包装成内置工具、getBuiltinTools 的 Session 依赖注入、ToolSearch 延迟激活，以及 Goal/Task/Team/Plan/Skill/LSP/MCP/Web/Config/Worktree 适配边界。

    180 GitHub stars~2.1k tokensUpdated 10 days ago
    Auto-check passed

Works with

Categories

Questions about Knowledge Extension Ecosystem

What does Knowledge Extension Ecosystem do?

覆盖 Blade 的 MCP、插件、Skills、自定义命令、Hooks 与 LSP 扩展边界及其 Session 集成关系。进入条件：新增扩展来源、调整 Workspace 扩展发现、排查插件资源未生效、 修改扩展资源快照或判断扩展职责归属。不包含：内置工具执行管线（见 ../tool-and-automation-platform/）、Workspace Trust 与通用配置合并（见…. Knowledge Extension Ecosystem is an agent skill from echoVic/blade-code.

When should I use Knowledge Extension Ecosystem?

Knowledge Extension Ecosystem fits situations like: tasks that involve MCP servers.

How do I install Knowledge Extension Ecosystem in Claude Code?

Run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem -a claude-code`. Or copy the skill folder (.trae/knowledges/extension-ecosystem in echoVic/blade-code) into .claude/skills/knowledge-extension-ecosystem in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Extension Ecosystem in Codex?

Run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem -a codex`. Or copy the skill folder (.trae/knowledges/extension-ecosystem in echoVic/blade-code) into .agents/skills/knowledge-extension-ecosystem in your project. Codex loads it when a task matches its description.

Can I use Knowledge Extension Ecosystem in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-extension-ecosystem, .gemini/skills/knowledge-extension-ecosystem, .github/skills/knowledge-extension-ecosystem and .opencode/skills/knowledge-extension-ecosystem in your project.

What does Knowledge Extension Ecosystem need to run?

SKILL.md names no scripts, command-line tools or credentials: Knowledge Extension Ecosystem is instructions for the agent only.

Does Knowledge Extension Ecosystem access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Extension Ecosystem safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Extension Ecosystem use?

Knowledge Extension Ecosystem is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Extension Ecosystem use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Knowledge Extension Ecosystem?

Skills that share tags, products or a category with Knowledge Extension Ecosystem: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Extension Ecosystem?

echoVic (a GitHub user) maintains it in echoVic/blade-code, which has 180 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 27, 2026.

Source: echoVic/blade-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.