菜单
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jackwener/OpenCLI --skill opencli-usage命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.
基于 SOC 职业分类
| name | opencli-usage |
| description | Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?". |
| allowed-tools | Bash(opencli:*), Read |
OpenCLI turns any website, Electron desktop app, or external CLI into a uniform opencli <site> <command> surface that agents can drive without screen-scraping. This skill is the orientation layer — once you know what you want to do, load one of the specialized skills below.
opencli <site> <command> [...]. Built-in adapters live in clis/, user adapters in ~/.opencli/clis/. Each is backed by a strategy (PUBLIC | COOKIE | INTERCEPT | UI | LOCAL) that tells you whether a Chrome session is needed.opencli browser * subcommands (open, state, click, type, select, find, extract, network, …) for ad-hoc interaction and scraping when no adapter covers the task. See opencli-browser.opencli browser <session> bind attaches the Chrome tab the user already opened/logged into to that browser session. Follow-up commands use . See before using it; bound sessions still block tab mutation.opencli browser <session> ...opencli-browseropencli gh, opencli docker, opencli vercel, etc. Managed via opencli external install <name> (auto-install from external-clis.yaml) or opencli external register <name> (bring your own).# npm global
npm install -g @jackwener/opencli # binary: opencli, requires Node >= 21
opencli doctor # run before browser-dependent work (see below)
# From source
git clone git@github.com:jackwener/OpenCLI.git
cd OpenCLI && npm install
npx tsx src/main.ts <command> # same surface, no global install
opencli doctor prints a structured DoctorReport — daemon status, extension connection, version checks, and a live browser connectivity probe. Scope is narrow: it diagnoses the browser bridge (daemon + extension + Chrome wiring). PUBLIC / LOCAL adapters, opencli list, validate, verify, plugin commands, and external-CLI passthrough don't need it to be green — only COOKIE / INTERCEPT / UI adapters and the opencli browser * subcommands do. Flag: -v (verbose).
Strategy tag on opencli list | What it needs |
|---|---|
PUBLIC | Nothing — pure HTTP, no browser. |
COOKIE | Chrome logged into the target site + OpenCLI extension installed from the Chrome Web Store. Command captures the credential from your live session — no re-login. |
INTERCEPT | Same as COOKIE, plus opencli opens an automation window to capture a signed request. |
UI | Same as COOKIE, full DOM interaction. |
LOCAL | No browser; talks to a local/dev endpoint. |
Electron desktop apps (cursor, codex, chatwise, discord-app, doubao-app, antigravity, chatgpt-app) route through CDP against the running app — same cookie-less flow as a logged-in browser. Make sure the app is running before invoking.
opencli list # table, grouped by site
opencli list -f json # machine-readable; pipe to jq or your agent
opencli list | grep -i twitter # find commands for a specific site
opencli <site> --help # see that site's commands + flags
opencli <site> <command> --help # see positional args and command-specific flags
Do not hard-code adapter lists — there are 100+ sites and the count moves every week. opencli list -f json is the source of truth; it emits one entry per command with {site, name, aliases, description, strategy, browser, args, columns, ...}. For an agent, that is always better than grepping a doc.
Before falling back to raw opencli browser commands on high-change authenticated sites, check whether a site adapter already exposes the workflow. For example, ChatGPT web has higher-level commands for conversation reads and Deep Research result extraction; discover the current surface with opencli chatgpt --help or opencli list -f json.
| flag | effect |
|---|---|
-f, --format <fmt> | table (default in TTY) · yaml (default in non-TTY) · json · plain · md · csv. Pass explicitly when you want a specific shape; agents almost always want -f json. |
-v, --verbose | Debug logs + stack traces on failure; also sets OPENCLI_VERBOSE=1 for the process. |
Command-specific flags (--limit, --tab, --filter, …) are not universal — consult <site> <command> --help.
json — pretty-printed, 2-space indent. Default choice for agents.plain — prints a single primary field for chat-style commands (response/content/text/value). Useful for piping to another tool.yaml — fallback when output is not a TTY and -f is not explicit.table — color-coded, site-grouped; meant for humans.md, csv — straightforward tabular dumps.A few commands override the default via cmd.defaultFormat (e.g. chat commands default to plain), so don't assume without reading --help.
| variable | default | purpose |
|---|---|---|
OPENCLI_BROWSER_CONNECT_TIMEOUT | 45 | Seconds to wait for the browser bridge. |
OPENCLI_BROWSER_COMMAND_TIMEOUT | 60 | Per-command timeout. |
OPENCLI_CDP_ENDPOINT | — | Manual CDP endpoint override (dev / remote Chrome / Electron). |
OPENCLI_CACHE_DIR | ~/.opencli/cache | Network capture + browser-state cache. |
OPENCLI_WINDOW | command-specific | foreground or background browser window mode. |
OPENCLI_VERBOSE | false | Verbose logging (also triggered by -v). |
When an adapter command fails because the site changed (selectors drifted, API rotated, response schema shifted), re-run with --trace retain-on-failure. The error envelope includes a trace block pointing at summary.md; patch only the adapterSourcePath from that summary and retry. Max 3 repair rounds. The full flow is in opencli-autofix.
Two-path storage:
~/.opencli/clis/<site>/<command>.js — no build step, hot-available, not visible in the public package.clis/<site>/<command>.js — for upstream contribution; requires build.Scaffolding & verification:
opencli browser init <site>/<command> # generates a skeleton
opencli validate [target] # semantic checks on the loaded registry (description, domain, pipeline step names, func|pipeline|_lazy presence, arg duplicates) — no network, no browser
opencli verify [target] [--smoke] # run the command with synthetic args
opencli browser verify <site>/<command> # end-to-end smoke inside the bridge
Adapters import only @jackwener/opencli/registry and @jackwener/opencli/errors. columns must align 1:1 (in name and order) with keys of the object returned by func. For the full workflow see opencli-adapter-author.
Plugins are third-party extensions pulled from git, separate from the main adapter registry:
opencli plugin install github:user/repo # install
opencli plugin list [-f json] # see installed
opencli plugin update [name] | --all # keep current
opencli plugin uninstall <name>
opencli plugin create <name> # scaffold a new plugin
Wraps external command-line tools so you can discover + invoke them through the same opencli … entrypoint:
opencli external install gh # auto-install via brew/apt/npm per external-clis.yaml
opencli external register my-tool \
--binary my-tool \
--install "npm i -g my-tool" \
--desc "My internal CLI"
opencli external list
opencli gh pr list --limit 5 # passthrough; stdio is inherited, exit code propagated
opencli docker ps
Built-in entries live in src/external-clis.yaml; user overrides and additions in ~/.opencli/external-clis.yaml. Commonly shipped: gh, docker, vercel, lark-cli, longbridge, dws, wecom-cli, obsidian, ntn, tg(tg-cli), discord(discord-cli), wx(wx-cli).
Some official CLIs use shell-script installers instead of a shell-free package-manager command. Entries without an install config, such as ntn, must be installed manually from their homepage before passthrough use.
opencli completion bash # also: zsh, fish
# -> script on stdout; source or save per your shell's convention
| If you're about to… | Load this skill |
|---|---|
| Drive a live browser ad-hoc (no adapter available, or prototyping) | opencli-browser |
| Write a new adapter, or add a command to an existing site | opencli-adapter-author |
| Fix a broken adapter after a command failure | opencli-autofix |
| Route a search / lookup / research request to the right adapter | smart-search |
The following were removed in the PR #1094 consolidation — don't try to invoke them:
opencli explore <url> — superseded by opencli browser network + opencli browser find for live API discovery, and by the opencli-adapter-author workflow for capture.opencli record <url> — removed; manual capture now lives in opencli browser network --detail.opencli web read / opencli desktop * as top-level groups — folded into their respective adapters (opencli web read still exists as the web adapter's read command, but there is no standalone web / desktop top-level group command).opencli list -f json at the start of a task instead.PUBLIC and LOCAL don't. Check the strategy field.fetch — --trace retain-on-failure gives you the browser evidence and adapter source path. Do that first.