Agent skill

Codebuddy Ide MCP Upgrade

by TencentCloudBase in TencentCloudBase/CloudBase-AI-Toolkit

升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP…

MITAuto-check passedAgent Workflows

Install Codebuddy Ide MCP Upgrade

skills CLI
$ npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill codebuddy-ide-mcp-upgrade -a claude-code

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

GitHub CLI
$ gh skill install TencentCloudBase/CloudBase-AI-Toolkit codebuddy-ide-mcp-upgrade --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/TencentCloudBase/CloudBase-AI-Toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codebuddy-ide-mcp-upgrade .claude/skills/codebuddy-ide-mcp-upgrade && 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
codebuddy-ide-mcp-upgrade
GitHub stars
1.1k
Token cost
~3k tokens
SKILL.md length
764 words
Files
2 (incl. scripts)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP…

  • Works in 6 steps: 解包拿到线上基线(第一步必做) → 构建新 bundle → 生成新配置 → …
  • Tasks that involve MCP servers
  • SKILL.md covers When to use, 集成结构(先读,别猜), Steps and MCP 发版时的强制同步项(防漂移), plus 4 more sections
  • Runs JavaScript scripts from its folder; calls node and npm

What it does

Codebuddy Ide MCP Upgrade is an agent skill from TencentCloudBase/CloudBase-AI-Toolkit. 升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP 发版要同步什么」时使用。覆盖:解包定位内置 bundle 与内嵌配置、重新构建 mcp bundle、生成新的工具白名单与系统提示词、安全注入 IDE 并备份、用 MCP 协议验证工具清单、人工端到端验收、一键回滚。

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/codebuddy-ide-mcp-upgrade”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 解包拿到线上基线(第一步必做)
  2. 构建新 bundle
  3. 生成新配置
  4. 注入 IDE(先 dry-run)
  5. 验证
  6. 回滚

What it can do on your machine

Read from SKILL.md and the folder at commit ea2c202. 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

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Codebuddy Ide MCP Upgrade loads about 3k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~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); the scripts in this folder are not scanned.

SKILL.md

The full file from TencentCloudBase/CloudBase-AI-Toolkit at commit ea2c202, republished under its MIT licence (© TencentCloudBase). 764 words, ~2,965 tokens.

Download SKILL.mdSave it as .claude/skills/codebuddy-ide-mcp-upgrade/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
codebuddy-ide-mcp-upgrade
description
升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP 发版要同步什么」时使用。覆盖:解包定位内置 bundle 与内嵌配置、重新构建 mcp bundle、生成新的工具白名单与系统提示词、安全注入 IDE 并备份、用 MCP 协议验证工具清单、人工端到端验收、一键回滚。
description_zh
升级 CodeBuddy IDE 内置 CloudBase MCP
description_en
Upgrade the CloudBase MCP bundled inside CodeBuddy IDE
disable
false
agent_created
true

codebuddy-ide-mcp-upgrade

When to use

  • 需要把 CloudBase MCP 新版本推进 CodeBuddy IDE 的内置集成
  • 线上反馈「IDE 里集成的 CloudBase 功能不足」(大概率是白名单过期,不是 MCP 能力不够)
  • 需要修改 IDE 内置的 toolWhiteList / systemPrompt / attatchPrompt
  • 需要定位「IDE 里的 MCP 到底装的哪个版本、能用哪些工具」

集成结构(先读,别猜)

CodeBuddy IDE 的内置 CloudBase MCP 由 genie 扩展承载,改一处不生效,必须同时改两个文件:

文件内容等价来源
Contents/Resources/app/extensions/genie/integration-mcp/tcb/index.cjsMCP Server bundle仓库 mcp/dist/cli.cjs 改名
Contents/Resources/app/extensions/genie/out/extension/index.js内嵌的 tcb 集成配置(webpack module,ir.exports=JSON.parse('{...}'))无仓库对版,需就地解包

默认 IDE 路径:/Applications/CodeBuddy CN.app。同目录还有 anydev、eop、lighthouse 三个集成,别改错。

加载与启动契约:

js
// TcbIntegration
mcpServer: {
  path: path.join("integration-mcp", "tcb", "index.cjs"),
  envMapper: (r) => ({ TENCENTCLOUD_SECRETID: r.tmp_secret_id,
                       TENCENTCLOUD_SECRETKEY: r.tmp_secret_key,
                       TENCENTCLOUD_SESSIONTOKEN: r.token }),
  toolWhiteList: config.toolWhiteList,
}
// StdioClientTransport
{ command: process.execPath, args: [mcpPath],
  env: { ...envMapper(), INTEGRATION_IDE: "CodeBuddy",
         ELECTRON_RUN_AS_NODE: "1", WORKSPACE_FOLDER_PATHS } }

不传任何命令行参数(--cloud-mode / --integration-ide 都没用),凭据全靠环境变量,MCP 侧 mcp/src/auth.ts 直接读 TENCENTCLOUD_SECRETID/SECRETKEY。

Steps

1. 解包拿到线上基线(第一步必做)

配置内嵌在 21MB 的 out/extension/index.js 里,用 JSON.parse('...') 包着,必须按 JS 字符串语义 eval 才能解析:

js
const i = s.indexOf('"id":"tcb"');
const st = s.lastIndexOf("JSON.parse('", i) + 12;
let cursor = st, cfg;
for (;;) {
  cursor = s.indexOf("')", cursor + 1);
  try { cfg = JSON.parse(eval("'" + s.slice(st, cursor) + "'")); break; } catch {}
}

拿到后先数一遍白名单,并和仓库 scripts/tools.json 比对。九成问题出在这里:白名单停留在旧版本,里面全是已被 MCP 改名的死条目。

2. 构建新 bundle
bash
cd <repo>/mcp && npm run build:webpack   # 产物 dist/cli.cjs,约 4.6 MiB

只跑 build:webpack,不要跑 npm run build(会触发 prebuild 的 rm -rf dist,可能被 safe-delete hook 拦截)。

3. 生成新配置

白名单真源是 scripts/tools.json,不要手写清单。配置改动落在:

  • toolWhiteList ← tools.json 全部工具名(全量,不要裁剪,理由见「白名单裁剪的前提已不存在」)
  • systemPrompt.login / .logout、userPrompt.*、attatchPrompt.* ← 提示词
  • 其余字段(id、displayName、description、descriptionMap、types、ruleZipUrl、loginOnlyChinese、loginType、toolTimeout)保持原值
3.1 写提示词前必须知道的两件事

(1)PG 模式 = Supabase 同构,不是「多了一种数据库」

判定为 PG 环境后,认证、存储、权限、迁移四项全部改道:

能力层SupabaseCloudBase PG 模式工具
数据库PostgresPostgreSQLqueryPgDatabase / managePgDatabase
Schema 变更MigrationapplyMigration(须带 migrationVersion)managePgDatabase
行级授权RLS PoliciesRLSmanagePgDatabase + rls-patterns.md
存储Storage Bucketspgstore(与 legacy COS 是两套系统)queryPgStorage(不是 queryStorage)
认证anon/service key应用认证(publishable key / API key)queryAppAuth / manageAppAuth

PG 环境里引导错路径(用 NoSQL/MySQL 工具,或用 queryStorage 而非 queryPgStorage)是最高频的跑偏方式。

(2)提示词看配重,不看总长

  • 总长不是问题:systemPrompt.login 约 10.6k 字符 ≈ 3.5k token,在 Tool Search + 长上下文下不构成负担。为「看起来短」删引导 = 丢掉关键分叉点的判断质量。
  • 要看常量 vs 变量的配比。实测一次改版的占比:
    • 静态索引(rule 文件路径清单 + 控制台 URL 清单)占 28.8%,但模型随时可查、规则文件里本来就有完整版(提示词自己都写着 "see platform rule for full list");
    • 真正决定走向的分支变量(如 PG 主线)只占 6.6%,且散落在互不相邻的章节,需要模型自行拼接 —— 这是「提示词写了但模型没照做」的典型成因。
  • 改法:
    1. 下沉常量索引(可省 ~23%),腾出的空间上提变量主线;
    2. 分支判定后紧跟一张「改道表」,把散落约束收敛成一处;
    3. 「三选一」式的并列列表,若各分支会改变后续多项决策,应改写成「两条主线」各自自包含。

改完提示词用这个脚本量化配重,别靠感觉:

bash
node -e '
const s=require("fs").readFileSync("config/prompts/systemPrompt.login.md","utf8"),L=s.split("\n");
let c="(开头)",a={[c]:0},o=[c];
for(const l of L){if(/^## /.test(l)){c=l.slice(3);if(!(c in a)){a[c]=0;o.push(c)}continue}
if(/^### /.test(l)){c=l.slice(4);if(!(c in a)){a[c]=0;o.push(c)}continue}a[c]+=l.length+1}
for(const k of o)console.log(String(a[k]).padStart(6),(a[k]/s.length*100).toFixed(1).padStart(5)+"%  ",k.slice(0,50))'
4. 注入 IDE(先 dry-run)
bash
node scripts/apply-to-ide.mjs --dry-run   # 只看差异
node scripts/apply-to-ide.mjs             # 备份到 backup/<时间戳>/ 后写入
node scripts/patch-tool-timeout.mjs --timeout 300000   # 接通 toolTimeout(见 Pitfalls)

写配置的替换逻辑:生成紧凑 JSON(JSON.stringify(cfg),无裸换行),再按 JS 单引号字符串转义(先 \\ 再 '),替换 JSON.parse('...') 区间。转义顺序错了会破坏 JS 字符串。

边界语义(踩过坑,勿改错):start = raw 起点(slice(0, start) 里已包含 JSON.parse('),end = ') 之后。所以替换时只能拼 escaped raw + '),绝不能再拼一次 JSON.parse('。

5. 验证
bash
node scripts/verify-ide-config.mjs   # 从 IDE 回读配置,逐字段比对
node scripts/verify-bundle.mjs       # 按 IDE 方式启动 bundle,拉 tools/list

verify-bundle.mjs 复刻 IDE 的启动参数(stdio + INTEGRATION_IDE=CodeBuddy + ELECTRON_RUN_AS_NODE=1 + 临时密钥占位值),比对三件事:暴露的工具是否全在白名单内、白名单是否有悬空条目、PG 工具是否注册。

6. 回滚
bash
node scripts/rollback-ide.mjs --latest

MCP 发版时的强制同步项(防漂移)

白名单漂移是「IDE 里 CloudBase 功能不足」的唯一根因,不是 MCP 能力问题。线上实测:21 条白名单里 12 条是已被 MCP 删除或改名的死条目,用户实际只能用 9 个。

因此 MCP 每次发版(工具增删改名)都必须重新生成 IDE 侧白名单,否则新版本 MCP 发得再勤,IDE 里还是老的。

发版 checklist:

  1. scripts/tools.json 是否已更新(工具清单真源)
  2. 用 scripts/build-config.mjs 重新生成 IDE 配置,产出新 toolWhiteList
  3. 检查新增/改名的工具是否在提示词里有对应引导 —— 提示词里引用已删除的工具名会导致模型调用不存在的工具
  4. 把新配置同步给 IDE 侧(或直接执行本 skill 的 Steps 打进本机 IDE 验证)
  5. 在交付文档里记录「本次新增了哪些工具」,便于 IDE 侧理解变更

建议把这个 checklist 挂到 MCP 发版流程里(release workflow 或发版 checklist 文档),不要靠人工记忆。 靠人记的后果就是这次的 12 条死条目。

白名单裁剪的前提已不存在
  • CodeBuddy 已支持 Tool Search:MCP 工具按需检索,不再全量塞进上下文;MCP server 配置层也支持 defer_loading。
  • 当初给 tcb 加 toolWhiteList 的唯一理由就是省上下文,这个前提现在没了。
  • 结论:白名单回归「安全边界」单一职责,按 tools.json 全量生成。继续裁剪的唯一后果就是随 MCP 发版漂移成死条目。
  • ⚠️ 判断「IDE 是否支持 Tool Search」时不要 grep genie 的 out/extension/index.js —— 那里搜不到 ToolSearch 字符串(实测 0 命中)。Tool Search 属 Agent CLI 内核层,证据在 CLI 进程参数(--tools 白名单含 ToolSearch)和 mcp-config 的 defer_loading 里。

Pitfalls

  • 白名单过滤在 IDE 侧,不在 bundle 内。 只换 bundle 不换白名单 = 新工具被静默过滤,用户侧零变化。这是最容易踩的坑。
  • 写入后必须完全退出并重启 IDE 才生效,运行中的进程已把旧 bundle 加载进内存。
  • 解包时配置字符串里可能含 ') 序列,必须用「eval + JSON.parse 能否成功」来判断结束位置,不能用第一个 ')。
  • 定位 tcb 块必须用 "id":"tcb" 做锚点。 全文 toolWhiteList 出现 13 次,用 toolWhiteList 搜会抓到 eop(EdgeOne)的配置块——症状是解出来的 raw 只有 1,015 字符(正常应 ~16,000)。
  • 插件类工具(如 msg-push)不在 DEFAULT_PLUGINS 里,白名单写了也不会注册,需注入 CLOUDBASE_MCP_PLUGINS_ENABLED=msg-push。白名单 40 条、实际暴露 38 条是正常现象,不是 bug。
⚠️ 头号陷阱:JSON 回读全绿 ≠ 文件可用

曾发生的事故:替换时重复拼接 JSON.parse(' 前缀,生成 JSON.parse('JSON.parse('{...}'),第二个 ' 提前闭合字符串,整文件 SyntaxError。但 verify 脚本的 JSON 字段比对全部显示 ✅ —— 因为定位用 lastIndexOf("JSON.parse('"),恰好命中了第二个前缀,照样能解析出正确 JSON。

铁律:改动这种大打包产物后,必须对整文件做真实编译:

js
import vm from "node:vm";
try { new vm.Script(source, { filename: "index.js" }); }
catch (e) { /* 立即回滚备份 */ }
  • 写入脚本要内置编译校验 + 失败自动回滚
  • verify 脚本的结构/语法检查必须硬阻断 exit 1,只打印 ❌ 而不改变退出码等于没有检查
  • 交付前再独立跑一次 node --check <file>,不要只信自己的脚本
  • 反向测试:拿一个已知损坏的备份喂给 verify,确认它真的报失败(否则检测是摆设)
已知 IDE 侧缺陷:toolTimeout 未接通,实际只有 60 秒
  • TcbIntegration 的配置对象没有 toolTimeout 字段(EopIntegration 传了)
  • callTool 用 this.config.toolTimeout → undefined
  • MCP SDK:const Sn = sn?.timeout ?? DEFAULT_REQUEST_TIMEOUT_MSEC,而 DEFAULT_REQUEST_TIMEOUT_MSEC = 6e4
  • ⇒ 配置 JSON 里写的 "toolTimeout":120000 从未生效,实际 60 秒就掐断 PG applyMigration / CloudRun 部署

修复(scripts/patch-tool-timeout.mjs):

  • Patch A:给 TcbIntegration 配置对象补 toolTimeout:hn.toolTimeout(锚点 attatchPrompt:hn.attatchPrompt,loginOnlyChinese:hn.loginOnlyChinese},全文唯一 1 处)
  • Patch B:把配置值从 120000 提到 300000
Show full SKILL.md (285 more words)Show less
白名单可以放心多留位(源码实证)
js
((ir?.tools) || []).filter((ir) => this.config.mcpServer.toolWhiteList.includes(ir.name))

遍历的是 server 实际返回的 tools/list,白名单只做 includes 判定。多出的条目静默跳过、不报错、不产生悬空工具。所以白名单按 tools.json 全量下发是安全的,插件后续启用也无需再改配置。

  • mcp/src/server.ts 用 ide === "CodeBuddy" 判定 logging capability,大小写敏感;IDE 传的正是 "CodeBuddy",别改成小写。
  • 老版本 bundle 用旧的 MySQL / 云函数 / 存储工具名(executeReadOnlySQL、createFunction、uploadFiles、writeSecurityRule 等),新 bundle 里这些名字已全部消失,提示词里如果还在引用就会引导模型调用不存在的工具。

Verification

交付前必须同时满足:

  1. 独立跑 node --check "<genie>/out/extension/index.js" 通过(最关键,能抓住回读校验掩盖的语法错误)
  2. apply-to-ide.mjs 输出「语法有效」+「回读校验通过」
  3. verify-ide-config.mjs 结构完整性三项 ✅ + 七个字段 ✅,echo $? 为 0
  4. verify-bundle.mjs 显示「所有暴露的工具都在白名单内」且 PG 三件套(queryPgDatabase / managePgDatabase / queryPgStorage)已注册
  5. verify-ide-config.mjs 反向测试:喂已知损坏文件必须 exit 1
  6. 重启 IDE 后完成下方的人工端到端验收(E1–E10)
人工端到端验收用例(自动化证明不了的那一层)

脚本只能证明「bundle 与配置文件本身是对的」,证明不了 IDE 加载后用户真的能用。重启后逐项跑:

#用例预期
E1完全退出后重启 IDE集成面板正常渲染,无 SyntaxError、genie 扩展不报错
E2集成面板连接 CloudBase登录成功,显示环境信息
E3让 Agent 列出可用的 CloudBase 工具数量与新白名单一致(不是旧版数量)
E4PG 环境让 Agent 建表走 managePgDatabase 的 applyMigration,提示词先引导读 postgresql-development-cloudbase 规则
E5执行一条只读 SQL走 queryMysqlDatabase(不再是 executeReadOnlySQL)
E6部署一个 Node.js 云函数走 manageFunctions(不再是 createFunction)
E7PG 模式下访问存储走 queryPgStorage 而非 queryStorage
E8查看/修改安全规则走 queryPermissions / managePermissions(不再是 writeSecurityRule)
E9PG 执行耗时 >1 分钟的迁移不中断,5 分钟超时生效(验证 toolTimeout 修复)
E10正常对话观察上下文占用工具全量放开后无明显膨胀(验证 Tool Search 结论)

验证时的两个坑:

  • tcb 临时密钥会过期:日志表现为 Authorization cache loaded for tcb, tempKey expires at: <过去时间>,必须在集成面板重新登录,MCP 才起来。
  • MCP 进程按需启动:tcb 的 MCP Server 只有集成面板连上后才拉起,IDE 刚启动时日志里没有 tcb 的 tools/list 属正常,别据此判定 bundle 没生效。

日志位置:~/Library/Application Support/CodeBuddy CN/logs/<时间戳>/window1/exthost/Tencent-Cloud.coding-copilot/腾讯云代码助手.log(搜 [Integration] / tcb)。

MCP 服务端质量的合格基线(顺带可测)

如果要顺带评估 MCP 工具层本身,这几项是实测通过的基线,达不到说明有回归:

  • 只读承诺:queryPgDatabase(action=sql) 必须拦截 DELETE / UPDATE / DROP / 多语句注入,且返回带 nextActions 的可执行建议
  • confirm 闸门:managePgDatabase(execute)、manageFunctions(deleteFunction) 缺 confirm 时必须拒绝
  • 负向路径零崩溃:不存在的函数名 / 集合 / envId / topic 都返回结构化错误或正常语义,不出裸 stack trace
  • 能力边界明示:PG 环境下 queryPermissions 应返回「不支持 PostgreSQL 类型环境」,而不是假装成功

首次实操的完整交付物(文档 + 配置 + 脚本)模板在 CloudBase-MCP 仓库的 specs/cb-ide-mcp-upgrade/(worktree chore/cb-ide-mcp-upgrade)。

交付前的一致性自查(易漏)

凡「改配置 + 再打独立 patch」的两步流程,patch 改的标量必须回流到配置生成脚本。

实例:本任务里 toolTimeout 先从 120000 提到 300000 是靠 patch-tool-timeout.mjs 单独 patch 的,而 build-config.mjs 生成的 tcb-config.new.json 里仍是 120000。交付物自带旧值,IDE 侧直接拿配置去用就会退回两分钟。

自查项:

  1. 对比「交付配置 JSON 的标量值」与「IDE 内实际生效值」,逐项相等
  2. 白名单条数、各提示词长度、所有标量字段都要对,不能只看回读脚本报绿
  3. 文档里的数值表格(变更项、建议项)与配置源保持一致

交付文档的可读性(易被忽略)

Markdown 交付物不要放在点开头的隐藏目录下。git worktree 常用 .worktrees/<name>/,预览器常因安全策略拒绝加载隐藏目录资源,表现是「文件能读到、点击却打不开/报错」。

交付前做两件事:

  1. 把文档产物镜像到非隐藏路径(本次用 ~/Projects/cb-ide-mcp-upgrade/),present_files 指向该路径
  2. 生成自包含 HTML 版,present_files 第一个传它(HTML 会同时开预览面板 + 列 artifact card,最稳)

渲染脚本在本 skill 的 scripts/render-html.mjs,依赖 marked:

bash
mkdir -p /tmp/mdrender && cd /tmp/mdrender
echo '{"name":"mdrender","private":true}' > package.json
npm install marked
NODE_PATH=/tmp/mdrender/node_modules node <skill>/scripts/render-html.mjs \
  "<交付目录>/README.md" "<交付目录>/README.html" "文档标题"

注意:npm install 别在 ~/.workbuddy/binaries/node/workspace 里跑——没有 package.json 时 npm 会向上找到 ~/node_modules 并因 ENOTEMPTY 失败。装到带 package.json 的临时目录最省事。

产物自带侧边目录导航(从 h2/h3 生成)、表格与代码高亮样式、@media print 打印规则(可直接导出 PDF 交给外部团队)。

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

Files

SKILL.md and 1 other file (scripts) in skills/codebuddy-ide-mcp-upgrade of TencentCloudBase/CloudBase-AI-Toolkit.

  • SKILL.md
  • scripts/render-html.mjs

Open the folder on GitHubat commit ea2c202

Compare with similar skills

Codebuddy Ide MCP Upgrade 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.

Codebuddy Ide MCP Upgrade compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codebuddy Ide MCP Upgrade this skillTencentCloudBase/CloudBase-AI-Toolkit1.1k—~3kAutomated safety check: PassMIT
Migrate To CodexHaohao-end/openagent8071 repos~2kAutomated safety check: PassApache-2.0
Openai DocsHaohao-end/openagent807—~1.7kAutomated safety check: PassApache-2.0
Use Gfs MCPGuepard-Corp/gfs158—~4kAutomated safety check: PassMIT
Ogham Recallogham-mcp/ogham-mcp115—~1kAutomated safety check: PassMIT
Memmesh CLIThinkfleetAI/memmesh419—~855Automated safety check: PassApache-2.0

Similar skills

  • Migrate To Codex

    Haohao-end/openagent

    Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

    807 GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • Openai Docs

    Haohao-end/openagent

    A skill your agent uses when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or…

    807 GitHub stars~1.7k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Use Gfs MCP

    Guepard-Corp/gfs

    GFS MCP Server for AI agent integration. An agent skill from Guepard-Corp/gfs.

    158 GitHub stars~4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Ogham Recall

    ogham-mcp/ogham-mcp

    Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Memmesh CLI

    ThinkfleetAI/memmesh

    MemMesh CLI + local MCP server — the zero-infra, no-API-key path to the same engine as the hosted SDK.

    419 GitHub stars~855 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Monte Carlo Storage Cost Analysis

    sickn33/agentic-awesome-skills

    Analyze a warehouse for stale, unused, or redundant tables via the analyzestoragecosts MCP tool.

    47k GitHub starsUsed in 1 repo~2.3k tokens
    Agent WorkflowsAuto-check passed

More from TencentCloudBase/CloudBase-AI-Toolkit

All 49 skills in this repo
  • AI Model Nodejs

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses for Node.js backend AI via @cloudbase/node-sdk (=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration.

    1.1k GitHub starsUsed in 3 repos~5k tokens
    Auto-check passed
  • HTTP API Cloudbase

    TencentCloudBase/CloudBase-AI-Toolkit

    CloudBase official HTTP API client guide. An agent skill from TencentCloudBase/CloudBase-AI-Toolkit.

    1.1k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed
  • Cloud API Recipe Authoring

    TencentCloudBase/CloudBase-AI-Toolkit

    Author or revise a cloud-api-operations recipe (config/source/skills/cloud-api-operations/references/recipes/).

    1.1k GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Manage Local Skills

    TencentCloudBase/CloudBase-AI-Toolkit

    Analyze, standardize, validate, and sync locally maintained skills into agent skill directories with a skills CLI-aligned workflow.

    1.1k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Cloudbase Agent Python

    TencentCloudBase/CloudBase-AI-Toolkit

    Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming +…

    1.1k GitHub starsUsed in 2 repos~2.9k tokens
    Auto-check: notes
  • Cloudbase

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects — Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android…

    1.1k GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed

Questions about Codebuddy Ide MCP Upgrade

What does Codebuddy Ide MCP Upgrade do?

升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP…. Codebuddy Ide MCP Upgrade is an agent skill from TencentCloudBase/CloudBase-AI-Toolkit.

When should I use Codebuddy Ide MCP Upgrade?

Codebuddy Ide MCP Upgrade fits situations like: tasks that involve MCP servers.

How do I install Codebuddy Ide MCP Upgrade in Claude Code?

Run `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill codebuddy-ide-mcp-upgrade -a claude-code`. Or copy the skill folder (skills/codebuddy-ide-mcp-upgrade in TencentCloudBase/CloudBase-AI-Toolkit) into .claude/skills/codebuddy-ide-mcp-upgrade in your project. Claude Code loads it when a task matches its description.

How do I install Codebuddy Ide MCP Upgrade in Codex?

Run `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill codebuddy-ide-mcp-upgrade -a codex`. Or copy the skill folder (skills/codebuddy-ide-mcp-upgrade in TencentCloudBase/CloudBase-AI-Toolkit) into .agents/skills/codebuddy-ide-mcp-upgrade in your project. Codex loads it when a task matches its description.

Can I use Codebuddy Ide MCP Upgrade 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 TencentCloudBase/CloudBase-AI-Toolkit --skill codebuddy-ide-mcp-upgrade -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codebuddy-ide-mcp-upgrade, .gemini/skills/codebuddy-ide-mcp-upgrade, .github/skills/codebuddy-ide-mcp-upgrade and .opencode/skills/codebuddy-ide-mcp-upgrade in your project.

What does Codebuddy Ide MCP Upgrade need to run?

Going by SKILL.md and its folder, Codebuddy Ide MCP Upgrade needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npm). Our summary lists: Node.js.

Does Codebuddy Ide MCP Upgrade access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Codebuddy Ide MCP Upgrade 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codebuddy Ide MCP Upgrade use?

Codebuddy Ide MCP Upgrade 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 Codebuddy Ide MCP Upgrade use?

About 3k tokens (SKILL.md is roughly 12k 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 Codebuddy Ide MCP Upgrade?

Skills that share tags, products or a category with Codebuddy Ide MCP Upgrade: Migrate To Codex (Haohao-end/openagent, 807 stars), Openai Docs (Haohao-end/openagent, 807 stars), Use Gfs MCP (Guepard-Corp/gfs, 158 stars) and Ogham Recall (ogham-mcp/ogham-mcp, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codebuddy Ide MCP Upgrade?

TencentCloudBase (a GitHub organization) maintains it in TencentCloudBase/CloudBase-AI-Toolkit, which has 1,132 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 6, 2026.

Source: TencentCloudBase/CloudBase-AI-Toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.