New: 98,000+ 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

Support

by hAcKlyc in hAcKlyc/MyAgents

MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent 网络/协作空间等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。

AGPL-3.0Auto-check passed

Install Support

skills CLI
$ npx skills add hAcKlyc/MyAgents --skill support -a claude-code

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

GitHub CLI
$ gh skill install hAcKlyc/MyAgents support --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/hAcKlyc/MyAgents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bundled-agents/myagents_helper/.claude/skills/support .claude/skills/support && 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
support
GitHub stars
918
Token cost
~1.9k tokens
SKILL.md length
468 words
Files
16 (incl. scripts, references)
Skills in repo
15
Repo updated
First seen
Licence
AGPL-3.0

At a glance

MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent 网络/协作空间等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。

  • Works in 8 steps: 建立正确预期 → 建立诊断信封 → 选择诊断域 → …
  • SKILL.md covers 总原则, Step 0 - 建立正确预期, Step 1 - 建立诊断信封 and Step 2 - 选择诊断域, plus 6 more sections
  • Runs JavaScript scripts from its folder; calls gh, rg and node

What it does

Support is an agent skill from hAcKlyc/MyAgents. MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent 网络/协作空间等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。 先用 /myagents-docs 确认正确产品预期，再以本地状态、CLI、日志和必要 probe 分类、修复、验证；确认产品缺陷或功能建议后， 在用户确认下形成并提交脱敏 Issue。普通“是什么/怎么用/入口在哪”不使用本 skill，直接使用 /myagents-docs。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `references/agent-channel-plugin.md`, `references/agent-network.md` and `references/attachments.md`).

It works with Model Context Protocol. The repository describes itself as: MyAgents - 优雅、易用的 Agent 桌面端 ，一站式 Agent 工作台与任务中心. The licence is AGPL-3.0.

Example prompts

  • “小助理诊断/问题反馈”
  • “是什么/怎么用/入口在哪”
  • “Use the support skill to myagent 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent…”
  • “/support”

Requirements

  • Node.js

Workflow steps

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

  1. 建立正确预期
  2. 建立诊断信封
  3. 选择诊断域
  4. 被动证据与 active probe
  5. 建立时间线和故障边界
  6. 分类
  7. 修复与验证
  8. Issue 或建议升级

What it can do on your machine

Read from SKILL.md and the folder at commit 71fc0ff. 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 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • rg
    • node

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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

Support loads about 1.9k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 468 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

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 hAcKlyc/MyAgents at commit 71fc0ff, republished under its AGPL-3.0 licence (© hAcKlyc). 468 words, ~1,864 tokens.

Download SKILL.mdSave it as .claude/skills/support/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
support
description
MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent 网络/协作空间等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。 先用 `/myagents-docs` 确认正确产品预期，再以本地状态、CLI、日志和必要 probe 分类、修复、验证；确认产品缺陷或功能建议后， 在用户确认下形成并提交脱敏 Issue。普通“是什么/怎么用/入口在哪”不使用本 skill，直接使用 `/myagents-docs`。

MyAgents Support

Support 的职责是解释“为什么实际行为没有符合正确预期”，并把问题推进到恢复或可执行的产品反馈。它不拥有产品百科；产品行为基线来自 /myagents-docs，当前实例状态来自 CLI/UI，发生过程来自本地证据。

总原则

  1. 先理解用户目标，再比较预期与实际；不要把不会用直接升级成事故。
  2. 先被动证据，后 active probe；先局部恢复，后破坏性重置。
  3. 配置修复优先走 /myagents-cli，不直接改 config.json 或内部 store。
  4. 不读取 credential store。状态通过脱敏 CLI/API 获取，日志和报告中的 Key、Token、Secret、Webhook query、home 用户名都要脱敏。
  5. 修复后必须重走触发原问题的路径验证，不能只跑一个总状态命令。
  6. 区分已确认、根因假设和已排除；证据不足时不装作确定。

Step 0 - 建立正确预期

先写清四件事：

  • 用户想完成什么
  • 用户实际做了什么
  • 正确情况下应该看到什么
  • 现在实际看到什么

涉及产品语义时，加载 /myagents-docs 的相关 reference，确认前置条件、作用域、生效时机、成功标志和限制。若发现只是功能理解或正常门控，回到产品使用指导，不继续扫日志。

白屏、明确 crash、数据错位等无需争议的异常可以直接进入取证，但报告仍要补齐 expected/actual。

Step 1 - 建立诊断信封

只收集与问题有关的最小现场：

  • MyAgents 版本、OS、问题发生时间窗口
  • 触发入口：Chat、Launcher、悬浮窗、Task、Goal、IM、Agent 网络、协作空间等；跨设备时记录双方版本与设备
  • Workspace、Session ID、Task/Goal/Issue ID（如适用）
  • Provider、Model、Runtime、runtimeSource（如适用）
  • 是否稳定复现、影响一个对象还是所有对象

常用只读基线：

bash
myagents status --json
myagents version
rg '\[boot\]' ./logs/unified-*.log | node .claude/skills/support/scripts/redact-log-output.mjs | tail -5

不必每次机械运行全部命令。前端已经注入 Terminal Reason / Runtime Diagnostics 时先利用它，再补缺失字段。某条命令或日志不存在，记录原因并继续，不要卡死。

Step 2 - 选择诊断域

一次先读最相关的 reference；只有证据跨域时才追加。

主诉读取
DSH/Codex/Claude Code 不工作、终端能用但 MyAgents 不行、runtime/model/permission 异常references/runtime.md
跨设备 Agent 发现/调用/回传失败、@ Agent 不完整、Session state/watch/取消观察异常references/agent-network.md
Provider 登录/验证/模型失败，MCP 启动、OAuth、握手或工具列表异常references/provider-mcp.md
Telegram/钉钉/飞书/微信/QQ Agent 不在线、不收发消息，OpenClaw Plugin 异常references/agent-channel-plugin.md
Task/定时/Cron 未执行或状态异常，Goal 不续跑/无法暂停/错误终态，Record/Session Inbox 异常references/automation.md
录音、离线转写、说话人、播放、语音模型或附件 speech job 异常references/recording-speech.md
协作空间登录、Goal/Issue、Registered Agent、Delivery、claim、共享工具/官方市场、附件或 quota 异常references/cloud-space.md
图片/音频/PDF 等工具产物生成但不显示，IM 媒体未发出references/attachments.md
工作区文件树、搜索、预览、@ 文件、拖拽、CRUD、watcher 异常references/workspace-files.md
AI 不回复、Sidecar 重启、pre-warm、历史恢复、回溯/分叉、Session 状态异常references/session-sidecar.md
网络/代理、Provider 可达性、npm 拉包、终端与 Runtime env 差异references/proxy-env.md
白屏、整页渲染错误、悬浮窗/桌宠打不开或卡在连接references/frontend-render.md
功能入口不存在、实验室开关、CLI 工具或 Runtime/Space 入口看不到references/feature-gates.md

Step 3 - 被动证据与 active probe

优先被动读取：

  • status、version
  • 对应对象的 list/show/get/view --json
  • 当前登录/验证/运行状态的脱敏接口
  • 最近时间窗口内的统一日志

active probe 会连接外部服务、启动进程、消耗请求、弹浏览器或实际执行任务。先区分两类授权：

  • Provider verify、MCP test、Runtime diagnose：在用户已经要求诊断对应问题时，可以在说明目的和影响后执行。
  • OAuth start、Task/Cron run-now、Channel 登录、Plugin/Skill 安装，以及任何写操作或 Cloud/IM/GitHub mutation：会改变状态、启动真实工作或影响外部系统，必须先展示具体对象与影响，并取得用户明确确认。

写命令只有在精确 leaf help 明确支持时才使用 --dry-run。不支持 preview 的命令不能通过添加无效 flag 假装已经预览。

统一日志不是凭据安全接口。禁止用裸 rg / grep 把完整日志行直接送入模型上下文；所有日志命令都必须先通过 .claude/skills/support/scripts/redact-log-output.mjs，让 URL、认证字段、常见 Token、长编码串和 home 用户名在工具输出前被替换。第三方 Plugin/npm 输出默认只保留时间、组件、错误类别和已脱敏消息；确需扩大上下文时仍使用同一过滤器并缩小时间窗口。

Step 4 - 建立时间线和故障边界

按问题入口还原实际链路，而不是套用一张“所有功能都经过 Sidecar”的总图：

text
用户动作 / Scheduler / Channel / Cloud Delivery
  → 对应产品 owner 接收
  → Session Runtime 或本地 Rust 能力执行
  → 持久状态 / UI / Channel / Cloud 返回结果

先按时间、Workspace、Session/Task/Goal/Issue ID、Runtime/Provider 收窄，再看上下游。常见主线关键词：

bash
rg -n "ERROR|WARN|auth error|401|403|429|terminal_reason|AppErrorBoundary|external-session|runtime_diagnostics|runtimeSource|managed-codex|codex-sub|anthropic-sub|grok-auth|xai-sub|task-scheduler|\[task\]|\[Goal\]|\[space\]|bridge|tool-attachment|cmd_workspace" ./logs/unified-*.log | node .claude/skills/support/scripts/redact-log-output.mjs | tail -200

[CronTask]、cron_runs 等旧名字仍可能出现在兼容路径，但不能再把它们当作 Task Scheduler 的唯一主线。

Step 5 - 分类

类型判断依据行动
使用理解行为符合 docs，用户误解入口、作用域、生效时机或限制解释产品行为，必要时用 CLI 代为完成
配置错误当前配置与用户目标或合法值域明确不符用 /myagents-cli 修复并同路径验证
环境问题网络、代理、PATH、Runtime 安装、registry、OAuth 外部状态异常给出具体恢复，必要时执行已说明的 probe
实验门控功能默认关闭或需要人工开启解释设置入口，不绕过可见门控
临时运行异常重启窗口、瞬时网络/限流或可恢复进程状态，重试后恢复说明证据和恢复结果，不夸大为产品 Bug
产品 Bug前置条件满足且稳定偏离产品契约，配置/环境无法解释明确影响、证据和 workaround，进入 Issue 升级
证据不足问题真实但无法在当前证据下归类收集最小复现；仍不足则以 unknown defect 报告，不伪造根因

Step 6 - 修复与验证

修复前确认对象、预期变化和副作用。删除、覆盖、重置登录、撤销 OAuth、移除 Channel/Plugin/Skill、云端 mutation 必须得到用户确认。

修复后：

  1. 读取权威状态，确认写入真的落地。
  2. 重走用户原来的入口和步骤。
  3. 对比原始 expected/actual，确认症状消失且没有产生相邻回归。
  4. 告诉用户实际改了什么、现在状态、是否需要新消息/新 Session 生效。

产品二进制 Bug 无法在安装实例中根治时，不通过反复清缓存、删历史或重置账号掩盖；给出最小风险 workaround 并升级。

Step 7 - Issue 或建议升级

确认产品 Bug 或用户希望提交功能建议后：

  1. 用 /myagents-docs 检查它是否已有能力、正常限制或已知使用路径。
  2. 生成下面的脱敏标题与报告，路径优先写相对路径或 <HOME>，先展示给用户。
  3. 按下面的渠道发现选择建议入口，向用户说明目标社区/仓库。取得向该渠道发送脱敏关键词的授权后，搜索相似 Issue；没有搜索能力或用户不授权就明确未搜索。
  4. 根据搜索结果更新报告并展示。用户确认最终报告与提交目标后执行提交；已有明确授权仍有效，不重复询问同一个决定。
  5. 成功后返回可点击链接；不能或不应提交时交付可直接粘贴的 Markdown。
Show full SKILL.md (178 more words)Show less
渠道发现与提交

MyAgents Space 从 0.5.0 起正式提供官方社区 Issue 反馈。先运行 gh --version 检测本机工具；这是本地检测，不需要安装或登录。

当前能力推荐入口与下一步
gh 可运行优先建议 GitHub 仓库 hAcKlyc/MyAgents。用 gh auth status 检查可用性（不显示 token）；未认证时提示 GitHub 登录，也可按用户选择转 Space，不把“装了 gh”当成已登录。
没有可用 gh，Space 已登录用 myagents space list --json 读取当前成员空间，选择 data.items[] 中 spaceKind=official 的官方社区，使用返回的实际 slug（当前通常是 myagents）。推荐提交到这里。
Space 未登录或需要重新认证提供 [登录 MyAgents Space](myagents://open/v1/spaces)，用户点击会打开/聚焦 Space Tab 的登录入口；登录后重新运行 space list 再继续。

space list 是经应用提供的脱敏状态接口；不要读取 Space credential 文件。只有 NOT_AUTHENTICATED / SPACE_REAUTH_REQUIRED 等明确认证错误才能判断需登录。网络、门控或权限错误保留具体原因，不误报退出登录；官方社区未出现在列表中时引导用户在 Space 检查成员状态，不猜 slug 或新建同名社区。尊重用户明确指定的渠道；不要求用户为了反馈安装 gh。

渠道确认与对外授权到位后，使用精确 help 核对参数：

  • GitHub：gh issue list --repo hAcKlyc/MyAgents --state open --search '<脱敏关键词>'；确认报告后 gh issue create --repo hAcKlyc/MyAgents --title '<标题>' --body-file issue.md。
  • Space：先 myagents space whoami --space <返回的slug> --json 核对身份，再 myagents space issue list --space <slug> --q '<脱敏关键词>' --json 查相似反馈。普通小助理 Session 应为 User；不通过注册 Agent、显式 token 或身份降级绕过拒绝。确认报告后 myagents space issue create --space <slug> --title '<标题>' --body-file issue.md --json。报告文件保存于当前工作区；不指定 assignee；如需归入 BUGFIX/功能建议 Goal，先用 space goal list 取得真实 active Goal ID，否则省略 --goal 进入 Inbox。

成功必须根据命令返回结果判断，不把超时/失败说成已提交或盲目重复创建。GitHub 返回其实际 Issue URL；Space 用返回的真实 id 生成 [查看反馈](myagents://open/v1/spaces/<slug>/issues/<issueId>)，不能把界面的 #12 等展示编号替代 Issue ID。也可提供 [官方社区反馈列表](myagents://open/v1/spaces/official/issues)。这些链接只导航，不触发搜索、上传或创建。

markdown
## 功能与用户目标
...

## 环境与影响范围
- MyAgents version / OS：...
- 入口 / Workspace / Runtime：...
- 影响一个对象还是全部对象：...

## 正确预期
...

## 实际结果
...

## 最小复现
1. ...
2. ...

## 关键证据（已脱敏）
...

## 分析
- 已确认：...
- 根因假设：...
- 已排除：...

## 临时绕过与严重程度
...

功能建议应强调用户目标、当前阻力和期望结果，不把未经评估的具体实现方案写成唯一答案。

安全边界

  • 不读取 ~/.myagents/credentials/、Space token、Claude/Codex 等供应商 credential home、Agent 网络私钥或系统 Keychain；停用集成留下的凭据同样受保护。
  • 不要求用户把 API Key/Token 发进持久对话；引导使用产品受保护输入入口。
  • 不直接编辑 Session、Project、Task、Goal、Space 内部 store。
  • 不把完整日志、用户文件内容、大 base64 或可识别个人路径放进 Issue。
  • 未经确认不提交 GitHub Issue、不发 Cloud/IM 消息、不改变外部账号状态。

© hAcKlyc, AGPL-3.0. 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 15 other files (scripts, references) in bundled-agents/myagents_helper/.claude/skills/support of hAcKlyc/MyAgents.

  • SKILL.md
  • references/agent-channel-plugin.md
  • references/agent-network.md
  • references/attachments.md
  • references/automation.md
  • references/cloud-space.md
  • references/feature-gates.md
  • references/frontend-render.md
  • references/provider-mcp.md
  • references/proxy-env.md
  • references/recording-speech.md
  • references/runtime.md
  • references/session-sidecar.md
  • references/workspace-files.md
  • scripts/redact-log-core.mjs
  • scripts/redact-log-output.mjs

Open the folder on GitHubat commit 71fc0ff

Compare with similar skills

Support 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.

Support compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Support this skillhAcKlyc/MyAgents918—~1.9kAutomated safety check: PassAGPL-3.0
MCP Server Builderanthropics/skills180k64 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-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.4k6 repos~3.2kAutomated safety check: NotesApache-2.0

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 64 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.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Figma use_figma Plugin API Rules

    warpdotdev/warp

    Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed

  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.4k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes

  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

More from hAcKlyc/MyAgents

All 15 skills in this repo

  • Hatch Pet

    hAcKlyc/MyAgents

    Create, repair, validate, visually QA, and package MyAgents/Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual…

    918 GitHub starsUsed in 2 repos~9.5k tokens
    Auto-check passed

  • Download Anything

    hAcKlyc/MyAgents

    Find and download virtually any digital resource from the internet — ebooks, academic papers, movies, TV shows, music, software, images, fonts, courses, and more.

    918 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Myagents Memory Gardener

    hAcKlyc/MyAgents

    仅当系统或用户明确指定完整名称 myagents-memory-gardener 时使用； 不要根据任务语义或相似表述自行触发。

    918 GitHub stars~425 tokensUpdated yesterday
    Auto-check passed

  • Myagents Memory Molt

    hAcKlyc/MyAgents

    仅当系统或用户明确指定完整名称 myagents-memory-molt 时使用； 不要根据任务语义或相似表述自行触发。

    918 GitHub stars~546 tokensUpdated yesterday
    Auto-check passed

  • Prompt Writer

    hAcKlyc/MyAgents

    Methodology for writing or improving prompts and system prompts that drive any LLM.

    918 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Myagents Task Automation

    hAcKlyc/MyAgents

    让 Agent 建立 MyAgents Task 的完整产品心智模型，并创建、验证和治理需要持久追踪、独立 Session 或未来触发的工作：理解 Task 与立即执行/Record/Goal 的边界，以及 once/scheduled/recurring、Session routing、结束条件和 command Detector。用户提到创建…

    918 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Support

What does Support do?

MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Agent 网络/协作空间等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。. Support is an agent skill from hAcKlyc/MyAgents.

How do I install Support in Claude Code?

Run `npx skills add hAcKlyc/MyAgents --skill support -a claude-code`. Or copy the skill folder (bundled-agents/myagents_helper/.claude/skills/support in hAcKlyc/MyAgents) into .claude/skills/support in your project. Claude Code loads it when a task matches its description.

How do I install Support in Codex?

Run `npx skills add hAcKlyc/MyAgents --skill support -a codex`. Or copy the skill folder (bundled-agents/myagents_helper/.claude/skills/support in hAcKlyc/MyAgents) into .agents/skills/support in your project. Codex loads it when a task matches its description.

Can I use Support 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 hAcKlyc/MyAgents --skill support -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/support, .gemini/skills/support, .github/skills/support and .opencode/skills/support in your project.

What does Support need to run?

Going by SKILL.md and its folder, Support needs JavaScript for the scripts in its folder and the command-line tools its instructions call (gh, rg and node). Our summary lists: Node.js.

Does Support access the network?

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

Is Support 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 Support use?

Support is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Support use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Support?

Skills that share tags, products or a category with Support: 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, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Support?

hAcKlyc (a GitHub user) maintains it in hAcKlyc/MyAgents, which has 918 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

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