← 返回 Skills 市场
vprudnikoff

LinkedIn Skill

作者 Vlad Prudnikov · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
736
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install linkedin-skill
功能描述
LinkedIn automation skill — search people and companies, fetch profiles, send messages and InMails, manage connections, create posts, react, comment. Support...
使用说明 (SKILL.md)

LinkedIn Skill

You have access to linkedin – a CLI tool for LinkedIn automation. Use it to fetch profiles, search people and companies, send messages, manage connections, create posts, react, comment, and more.

Each command sends a request to Linked API, which runs a real cloud browser to perform the action on LinkedIn. Operations are not instant – expect 30 seconds to several minutes depending on complexity.

If linkedin is not available, install it:

npm install -g @linkedapi/linkedin-cli

Authentication

If a command fails with exit code 2 (authentication error), ask the user to set up their account:

  1. Go to app.linkedapi.io and sign up or log in
  2. Connect their LinkedIn account
  3. Copy the Linked API Token and Identification Token from the dashboard

Once the user provides the tokens, run:

linkedin setup --linked-api-token=TOKEN --identification-token=TOKEN

Global Flags

Always use --json and -q for machine-readable output:

linkedin \x3Ccommand> --json -q
Flag Description
--json Structured JSON output
--quiet / -q Suppress stderr progress messages
--fields name,url,... Select specific fields in output
--no-color Disable colors
--account "Name" Use a specific account for this command

Output Format

Success:

{"success": true, "data": {"name": "John Doe", "headline": "Engineer"}}

Error:

{"success": false, "error": {"type": "personNotFound", "message": "Person not found"}}

Exit code 0 means the API call succeeded – always check the success field for the action outcome. Non-zero exit codes indicate infrastructure errors:

Exit Code Meaning
0 Success (check success field – action may have returned an error like "person not found")
1 General/unexpected error
2 Missing or invalid tokens
3 Subscription/plan required
4 LinkedIn account issue
5 Invalid arguments
6 Rate limited
7 Network error
8 Workflow timeout (workflowId returned for recovery)

Commands

Fetch a Person Profile

linkedin person fetch \x3Curl> [flags] --json -q

Optional flags to include additional data:

  • --experience – work history
  • --education – education history
  • --skills – skills list
  • --languages – languages
  • --posts – recent posts (with --posts-limit N, --posts-since TIMESTAMP)
  • --comments – recent comments (with --comments-limit N, --comments-since TIMESTAMP)
  • --reactions – recent reactions (with --reactions-limit N, --reactions-since TIMESTAMP)

Only request additional data when needed – each flag increases execution time.

# Basic profile
linkedin person fetch https://www.linkedin.com/in/username --json -q

# With experience and education
linkedin person fetch https://www.linkedin.com/in/username --experience --education --json -q

# With last 5 posts
linkedin person fetch https://www.linkedin.com/in/username --posts --posts-limit 5 --json -q

Search People

linkedin person search [flags] --json -q
Flag Description
--term Search keyword or phrase
--limit Max results
--first-name Filter by first name
--last-name Filter by last name
--position Filter by job position
--locations Comma-separated locations
--industries Comma-separated industries
--current-companies Comma-separated current company names
--previous-companies Comma-separated previous company names
--schools Comma-separated school names
linkedin person search --term "product manager" --locations "San Francisco" --json -q
linkedin person search --current-companies "Google" --position "Engineer" --limit 20 --json -q

Fetch a Company

linkedin company fetch \x3Curl> [flags] --json -q

Optional flags:

  • --employees – include employees
  • --dms – include decision makers
  • --posts – include company posts

Employee filters (require --employees):

Flag Description
--employees-limit Max employees to retrieve
--employees-first-name Filter by first name
--employees-last-name Filter by last name
--employees-position Filter by position
--employees-locations Comma-separated locations
--employees-industries Comma-separated industries
--employees-schools Comma-separated school names
Flag Description
--dms-limit Max decision makers to retrieve (requires --dms)
--posts-limit Max posts to retrieve (requires --posts)
--posts-since Posts since ISO timestamp (requires --posts)
# Basic company info
linkedin company fetch https://www.linkedin.com/company/name --json -q

# With employees filtered by position
linkedin company fetch https://www.linkedin.com/company/name --employees --employees-position "Engineer" --json -q

# With decision makers and posts
linkedin company fetch https://www.linkedin.com/company/name --dms --posts --posts-limit 10 --json -q

Search Companies

linkedin company search [flags] --json -q
Flag Description
--term Search keyword
--limit Max results
--sizes Comma-separated sizes: 1-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+
--locations Comma-separated locations
--industries Comma-separated industries
linkedin company search --term "fintech" --sizes "11-50,51-200" --json -q

Send a Message

linkedin message send \x3Cperson-url> '\x3Ctext>' --json -q

Text up to 1900 characters. Wrap the message in single quotes to avoid shell interpretation issues.

linkedin message send https://www.linkedin.com/in/username 'Hey, loved your latest post!' --json -q

Get Conversation

linkedin message get \x3Cperson-url> [--since TIMESTAMP] --json -q

The first call for a conversation triggers a background sync and may take longer. Subsequent calls are faster.

linkedin message get https://www.linkedin.com/in/username --json -q
linkedin message get https://www.linkedin.com/in/username --since 2024-01-15T10:30:00Z --json -q

Connection Management

Check connection status

linkedin connection status \x3Curl> --json -q

Send connection request

linkedin connection send \x3Curl> [--note 'text'] [--email [email protected]] --json -q

List connections

linkedin connection list [flags] --json -q
Flag Description
--limit Max connections to return
--since Only connections made since ISO timestamp (only works when no filter flags are used)
--first-name Filter by first name
--last-name Filter by last name
--position Filter by job position
--locations Comma-separated locations
--industries Comma-separated industries
--current-companies Comma-separated current company names
--previous-companies Comma-separated previous company names
--schools Comma-separated school names
linkedin connection list --limit 50 --json -q
linkedin connection list --current-companies "Google" --position "Engineer" --json -q
linkedin connection list --since 2024-01-01T00:00:00Z --json -q

List pending outgoing requests

linkedin connection pending --json -q

Withdraw a pending request

linkedin connection withdraw \x3Curl> [--no-unfollow] --json -q

By default, withdrawing also unfollows the person. Use --no-unfollow to keep following.

Remove a connection

linkedin connection remove \x3Curl> --json -q

Posts

Fetch a post

linkedin post fetch \x3Curl> [flags] --json -q
Flag Description
--comments Include comments
--reactions Include reactions
--comments-limit Max comments to retrieve (requires --comments)
--comments-sort Sort order: mostRelevant or mostRecent (requires --comments)
--comments-replies Include replies to comments (requires --comments)
--reactions-limit Max reactions to retrieve (requires --reactions)
linkedin post fetch https://www.linkedin.com/posts/username_activity-123 --json -q

# With comments sorted by most recent, including replies
linkedin post fetch https://www.linkedin.com/posts/username_activity-123 \
  --comments --comments-sort mostRecent --comments-replies --json -q

Create a post

linkedin post create '\x3Ctext>' [flags] --json -q
Flag Description
--company-url Post on behalf of a company page (requires admin access)
--attachments Attachment as url:type or url:type:name. Types: image, video, document. Can be specified multiple times.

Attachment limits: up to 9 images, or 1 video, or 1 document. Cannot mix types.

linkedin post create 'Excited to share our latest update!' --json -q

# With a document
linkedin post create 'Our Q4 report' \
  --attachments "https://example.com/report.pdf:document:Q4 Report" --json -q

# Post as a company
linkedin post create 'Company announcement' \
  --company-url https://www.linkedin.com/company/name --json -q

React to a post

linkedin post react \x3Curl> --type \x3Creaction> [--company-url \x3Curl>] --json -q

Reaction types: like, love, support, celebrate, insightful, funny.

linkedin post react https://www.linkedin.com/posts/username_activity-123 --type like --json -q

# React on behalf of a company
linkedin post react https://www.linkedin.com/posts/username_activity-123 --type celebrate \
  --company-url https://www.linkedin.com/company/name --json -q

Comment on a post

linkedin post comment \x3Curl> '\x3Ctext>' [--company-url \x3Curl>] --json -q

Text up to 1000 characters.

linkedin post comment https://www.linkedin.com/posts/username_activity-123 'Great insights!' --json -q

# Comment on behalf of a company
linkedin post comment https://www.linkedin.com/posts/username_activity-123 'Well said!' \
  --company-url https://www.linkedin.com/company/name --json -q

Statistics

# Social Selling Index
linkedin stats ssi --json -q

# Performance analytics (profile views, post impressions, search appearances)
linkedin stats performance --json -q

# API usage for a date range
linkedin stats usage --start 2024-01-01T00:00:00Z --end 2024-01-31T00:00:00Z --json -q

Sales Navigator

Requires a LinkedIn Sales Navigator subscription. Uses hashed URLs for person/company lookups.

Fetch person

linkedin navigator person fetch \x3Chashed-url> --json -q

Search people

linkedin navigator person search [flags] --json -q
Flag Description
--term Search keyword or phrase
--limit Max results
--first-name Filter by first name
--last-name Filter by last name
--position Filter by job position
--locations Comma-separated locations
--industries Comma-separated industries
--current-companies Comma-separated current company names
--previous-companies Comma-separated previous company names
--schools Comma-separated school names
--years-of-experience Comma-separated ranges: lessThanOne, oneToTwo, threeToFive, sixToTen, moreThanTen
linkedin navigator person search --term "VP Marketing" --locations "United States" --json -q
linkedin navigator person search --years-of-experience "moreThanTen" --position "CEO" --json -q

Fetch company

linkedin navigator company fetch \x3Chashed-url> [flags] --json -q

Optional flags:

  • --employees – include employees
  • --dms – include decision makers

Employee filters (require --employees):

Flag Description
--employees-limit Max employees to retrieve
--employees-first-name Filter by first name
--employees-last-name Filter by last name
--employees-positions Comma-separated positions
--employees-locations Comma-separated locations
--employees-industries Comma-separated industries
--employees-schools Comma-separated school names
--employees-years-of-experience Comma-separated experience ranges
--dms-limit Max decision makers to retrieve (requires --dms)
linkedin navigator company fetch https://www.linkedin.com/sales/company/97ural --employees --dms --json -q
linkedin navigator company fetch https://www.linkedin.com/sales/company/97ural \
  --employees --employees-positions "Engineer,Designer" --employees-locations "Europe" --json -q

Search companies

linkedin navigator company search [flags] --json -q
Flag Description
--term Search keyword
--limit Max results
--sizes Comma-separated sizes: 1-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+
--locations Comma-separated locations
--industries Comma-separated industries
--revenue-min Min annual revenue in M USD: 0, 0.5, 1, 2.5, 5, 10, 20, 50, 100, 500, 1000
--revenue-max Max annual revenue in M USD: 0.5, 1, 2.5, 5, 10, 20, 50, 100, 500, 1000, 1000+
linkedin navigator company search --term "fintech" --sizes "11-50,51-200" --json -q
linkedin navigator company search --revenue-min 10 --revenue-max 100 --locations "United States" --json -q

Send InMail

linkedin navigator message send \x3Cperson-url> '\x3Ctext>' --subject '\x3Csubject>' --json -q

Text up to 1900 characters. Subject up to 80 characters.

linkedin navigator message send https://www.linkedin.com/in/username \
  'Would love to chat about API integrations' --subject 'Partnership Opportunity' --json -q

Get Sales Navigator conversation

linkedin navigator message get \x3Cperson-url> [--since TIMESTAMP] --json -q

Custom Workflows

Execute a custom workflow definition from a file, stdin, or inline:

# From file
linkedin workflow run --file workflow.json --json -q

# From stdin
cat workflow.json | linkedin workflow run --json -q

# Inline
echo '{"actions":[...]}' | linkedin workflow run --json -q

Check workflow status or wait for completion:

linkedin workflow status \x3Cid> --json -q
linkedin workflow status \x3Cid> --wait --json -q

See Building Workflows for the workflow JSON schema.

Account Management

linkedin account list                            # List accounts (* = active)
linkedin account switch "Name"                   # Switch active account
linkedin account rename "Name" --name "New Name" # Rename account
linkedin reset                                   # Remove active account
linkedin reset --all                             # Remove all accounts

Important Behavior

  • Sequential execution. All operations for an account run one at a time. Multiple requests queue up.
  • Not instant. A real browser navigates LinkedIn – expect 30 seconds to several minutes per operation.
  • Timestamps in UTC. All dates and times are in UTC.
  • Single quotes for text arguments. Use single quotes around message text, post text, and comments to avoid shell interpretation issues with special characters.
  • Action limits. Per-account limits are configurable on the platform. A limitExceeded error means the limit was reached.
  • URL normalization. All LinkedIn URLs in responses are normalized to https://www.linkedin.com/... format without trailing slashes.
  • Null fields. Fields that are unavailable are returned as null or [], not omitted.
安全使用建议
This skill's instructions are plausible for a LinkedIn automation tool, but the package/source is not declared in the registry and metadata doesn't match the SKILL.md. Before installing or providing any tokens: 1) Verify the npm package and its publisher (inspect the package page and GitHub repo, read code and recent commits); 2) Confirm what the 'Linked API Token' and 'Identification Token' actually are, what scopes they grant, and that they are revocable; 3) Prefer using a throwaway/test LinkedIn account when trying it first; 4) Avoid pasting your LinkedIn password — only provide tokens from the provider's dashboard if you trust them; 5) If you don't want a third party to act on your account, do not install/use this tool. If you need help checking the npm package or finding the provider's privacy/security docs, ask and include the package URL or publisher info.
功能分析
Type: OpenClaw Skill Name: linkedin-skill Version: 1.0.0 The skill instructs the agent to install an external npm package (`@linkedapi/linkedin-cli`) via `npm install -g` in `SKILL.md`. This introduces a supply chain risk, as the integrity of the external package cannot be guaranteed by the skill bundle itself. Additionally, the skill requires the user to provide sensitive API tokens (`Linked API Token`, `Identification Token`) for authentication with an external service (`app.linkedapi.io`), which the agent is then instructed to use. While the instructions do not show explicit malicious intent (e.g., no prompt injection to steal data or subvert the agent), the reliance on an external executable and the handling of sensitive credentials constitute meaningful high-risk behaviors, classifying it as suspicious rather than benign.
能力评估
Purpose & Capability
The skill claims LinkedIn automation (search, fetch, message, post, etc.) which plausibly requires a CLI or API tokens, but the registry metadata lists no required binaries, no primary credential, and no install instructions. SKILL.md explicitly requires a `linkedin` CLI (npm package @linkedapi/linkedin-cli) and tokens from app.linkedapi.io; that mismatch is inconsistent and unexplained.
Instruction Scope
The runtime instructions are narrowly scoped to LinkedIn actions and include explicit CLI commands and flags. They do not instruct reading arbitrary system files. However they require the user/agent to capture and provide two tokens (Linked API Token and Identification Token) from a third party dashboard — these are sensitive and the instructions do not describe token scopes or how tokens are stored/used beyond running `linkedin setup`.
Install Mechanism
There is no install spec in the registry, but SKILL.md tells users to run `npm install -g @linkedapi/linkedin-cli`. Installing a global npm package from an unknown publisher (no homepage/source provided in the registry) can execute arbitrary code on the host. The skill also describes a third‑party cloud browser performing actions, which increases the trust surface because external infrastructure will act on your account.
Credentials
The skill metadata lists no required environment variables or credentials, yet the instructions require the user to obtain and provide two tokens from app.linkedapi.io (Linked API Token and Identification Token). Those tokens could grant broad access to the user's LinkedIn account via the third party; their absence from declared requirements is a red flag. The skill also performs sensitive operations (sending messages, managing connections) which justify needing tokens, but the lack of transparency about token scope and storage is problematic.
Persistence & Privilege
The skill is not marked always:true and does not request system‑wide configuration changes in the registry. It does instruct running `linkedin setup`, which will persist tokens locally for the CLI — normal for this type of tool. Autonomous model invocation is allowed by default (disable-model-invocation=false); combined with sensitive tokens this increases blast radius, but that is platform default and not by itself proof of malice.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkedin-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkedin-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the LinkedIn automation skill. - Automate LinkedIn actions via CLI: search people/companies, fetch profiles, send messages and InMails, manage connections, create posts, comment, and react. - Sales Navigator support included. - Flexible search and filter options for people, companies, and connections. - Cloud browser ensures real, non-instant interactions (actions may take 30 seconds to minutes). - Machine-readable JSON outputs and robust error reporting by exit codes. - Simple authentication required via Linked API tokens.
元数据
Slug linkedin-skill
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

LinkedIn Skill 是什么?

LinkedIn automation skill — search people and companies, fetch profiles, send messages and InMails, manage connections, create posts, react, comment. Support... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 736 次。

如何安装 LinkedIn Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkedin-skill」即可一键安装,无需额外配置。

LinkedIn Skill 是免费的吗?

是的,LinkedIn Skill 完全免费(开源免费),可自由下载、安装和使用。

LinkedIn Skill 支持哪些平台?

LinkedIn Skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 LinkedIn Skill?

由 Vlad Prudnikov(@vprudnikoff)开发并维护,当前版本 v1.0.0。

💬 留言讨论