Linkedin Skills
LinkedIn automation skills for AI agents – sales, social selling, data extraction, and more.
Linked-API · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Linked-API/linkedin-skills技能说明
linkedin-skills
A collection of LinkedIn skills for AI agents (Claude Code, Codex, Cursor, Windsurf), powered by
LinkedIn CLI (@linkedapi/linkedin-cli) and
Linked API.
Install
One command — detects your installed agents, asks what to install and where, and sets up the prerequisites for you:
npx @linkedapi/skills
Or just hand this to your AI agent:
Read https://linkedapi.io/skills/install.md and follow it.
For a single skill, hand over its own runbook instead — e.g.
https://linkedapi.io/skills/linkedin/install.md or
https://linkedapi.io/skills/linkedin-growth/install.md.
Non-interactive (agents / CI)
# Inspect the environment first (machine-readable)
npx @linkedapi/skills detect --json
# Install one skill in one command
npx @linkedapi/skills add linkedin --yes
# Install specific skills into specific agents
npx @linkedapi/skills add linkedin linkedin-growth \
--agent claude-code --agent codex --scope project --yes --json
Other commands: list, update, remove, doctor (all support --json). See
npx @linkedapi/skills --help.
Exit codes & readiness
add separates two things so a caller never mistakes "needs setup" for "install failed"
(the agent-facing install runbook at linkedapi.io/skills/install.md spells this out for AI agents):
- Exit code reflects only whether the install itself succeeded (files placed +
dependencies installed).
0= installed.1= a real install failure.2= bad arguments. - Readiness is reported in the JSON, not the exit code. Each skill carries
ok(installed) andready(fully configured and usable now). When a skill installed fine but still needs setup — e.g. LinkedIn tokens not connected yet — you get exit 0 withready: falseand apendinglist describing what's left. Always parse the JSON; do not treat a readiness gap as a failure.
{ "success": tr