Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/volcengine/ark-cli/arkcli-connectnpx skills add volcengine/ark-cli --skill arkcli-connectgit clone --depth 1 https://github.com/volcengine/ark-cliWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00062 | $0.01848 |
| Opus 5 | $0.00031 | $0.00924 |
| Sonnet 5 | $0.00012 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
arkcli-connect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli +connect
前置： 先用 Read 读 ../arkcli-shared/SKILL.md 获取共享安全规则。
把 arkcli 内嵌的 skills 同步到本机 AI Agent（Claude Code、Cursor、Gemini CLI 等）的 skills 目录。纯本地文件操作，不需要认证。
调用形态（子命令仍只有这三个）
| 调用 | 说明 |
|---|---|
arkcli +connect |
默认行为：安装到所有检测到的 agent |
arkcli +connect --path <skills-dir> |
安装到指定的本地 skills 目录（项目级 / 自定义路径），不扫描 agent、不改全局目录 |
arkcli +connect list |
只读：列出支持的 agent 与检测状态 |
arkcli +connect uninstall |
从所有 agent 删除 ownership manifest 记录且未被用户修改的 ArkCLI skills |
arkcli +connect uninstall --path <skills-dir> |
只从指定目录删除 ownership manifest 记录且未被用户修改的 ArkCLI skills |
arkcli +connect uninstall --purge-prefix |
显式破坏性清理：删除所有检测目录中的 ark- / arkcli- 前缀目录或软链 |
arkcli +connect uninstall --path <skills-dir> --purge-prefix |
只在指定目录执行显式全前缀清理 |
⚠️ 没有
+connect install/+connect setup/+connect sync/+connect remove等子命令；安装就是默认行为，不要凭直觉补 install。--path是 flag，不是子命令。
路由判断
- 用户想把 arkcli skills 装进本地 agent → 跑
arkcli +connect，建议先arkcli +connect list预检 - 用户想把 arkcli skills 装进某个 repo/project 的本地 skills 目录 → 跑
arkcli +connect --path <skills-dir>，例如arkcli +connect --path .claude/skills；--path接收具体 skills 目录，不是项目根目录 - 用户只想知道支持哪些 agent → 只跑
arkcli +connect list，不要顺手装 - 用户想清理 ArkCLI 自己安装的 skills →
arkcli +connect uninstall，仍需先确认 agent 范围；默认只删 manifest 记录且摘要未变化的 managed skills - 用户想清理 repo/project 本地 skills 目录里的 managed skills →
arkcli +connect uninstall --path <skills-dir> - 用户明确要求连历史未知条目一起全清 → 解释风险并在确认后使用
--purge-prefix；它会删除用户手工维护的同前缀目录或软链
反触发（应该路由到别处）
- 401 / 鉴权失败 / "auth login 报错" → 走
arkcli-auth，与 +connect 无关（+connect 不需要认证） - profile / base-url / region 配置问题 → 走
arkcli-config - 想生成代码示例、调用模型 → 走
arkcli-code-example/arkcli-chat
关键事实（写在 SKILL.md 内，避免 Agent 幻觉）
- 安装走 authoritative catalog update：
.arkcli-managed-skills.json记录 ArkCLI 上次写入的精确名称、产品和目录摘要；每次安装都会用当前 CLI catalog 覆盖所有同名 Skill，并删除 manifest 中已退出当前 catalog 的旧 Skill - 当前 catalog 的精确官方名称具有最高优先级：无论现有同名目录是否被 manifest 记录、摘要是否变化、是否由用户手改，都会被当前版本覆盖；需要保留自定义内容时必须复制到不同名称
- 不在当前 catalog、也未被旧 manifest 管理的其他目录或软链不会进入安装事务，即使名称带
ark-/arkcli-前缀也默认保留 - 目录摘要仍用于 provenance 和默认卸载保护，不再阻断安装升级；安装在 staging/backup 中完成并保持事务性，失败时回滚，不产生半套新旧 Skills
- 历史 BytePlus candidate 的
arkcli-managed-agent若存在于旧 manifest，会作为退出 catalog 的旧 Skill 删除；canonicalarkcli-agent作为当前官方名称安装。这是统一 catalog 规则的结果，不再需要产品特判 --path <skills-dir>是隔离安装：相对路径按当前PWD解析，绝对路径原样使用；只在该目录收敛当前 catalog 和旧 manifest，并保留其他不同名条目。它不扫描 agent、不清 legacy 私有目录、不删除byted-ark-*conflicting skills、不 patch Claude/opencode 等 harness 配置- 默认还会移除两个抢路由的第三方生成 skill：
byted-ark-seedance-skill/byted-ark-seedream-skill（按精确名匹配，不误伤其他byted-*）。原因：它们的 description 带"推荐优先"+逐字触发词，会在"生图/生视频"意图上压过arkcli +gen，且自身要独立ark-API Key，赢了路由反而失败。移除后生成类意图统一落arkcli +gen（用登录态 profile 凭证，跟视频一样能成）。日志显式打印removed N conflicting (...)，非静默。要保留它们：arkcli +connect --keep-conflicting uninstall默认只删除 ownership manifest 中记录且摘要未变化的 managed skills；只有显式--purge-prefix才恢复旧式全前缀删除- 多个 agent 共享同一个 skills 目录时，按路径自动去重，只更新一次 ownership manifest
- 多路径扫描特例：Codex 同时扫
~/.codex/skills(CODEX_HOME) 和共享的~/.agents/skills；Pi 同时扫~/.pi/agent/skills和共享的~/.agents/skills。若两处都装 arkcli，会把每个 skill 列两遍或报同名冲突。因此+connect把 Codex / Pi 的 skill 都装进共享的~/.agents/skills(与 cline/warp 去重成一份)，靠~/.codex/~/.pi/agent目录存在来检出对应 agent；legacy 私有目录只删除带旧 manifest 的 owned Skills，或与当前官方树逐字节一致的迁移副本，未知/修改过的同前缀条目保留 list只扫描本地文件系统，不写入、不联网、不需要认证- 支持的 agent 列表硬编码在二进制里，新增 agent 需要重新编译
npm installarkcli 时 postinstall 会自动跑+connect：在能打开/dev/tty的交互式终端上按 authoritative catalog 规则更新检测到的所有 agent，无需用户确认；成功时只输出唯一安装目标数、对应 Agent 名称和安全卸载命令arkcli +connect uninstall，不会逐目录展开进度明细。它不会执行--purge-prefix。CI / 非交互终端 / 拿不到/dev/tty一律静默跳过；想完全静音可设ARKCLI_SKIP_POSTINSTALL=1
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 63 lines · 62 tokens per session scan A a52b2768151e
arkcli-connect is a skill published in the GitHub repository volcengine/ark-cli (112 stars, last pushed 5d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,848 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
jobs-to-be-done
Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
scienceworld-growth-focuser
Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…