# Send Linkedin - automation to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "inkedin-automation-that-really-works", "name": "Linkedin - automation", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/red777777/inkedin-automation-that-really-works", "canonicalUrl": "https://clawhub.ai/red777777/inkedin-automation-that-really-works", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/inkedin-automation-that-really-works", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=inkedin-automation-that-really-works", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/cc-webhook.py", "scripts/linkedin.py", "scripts/requirements.txt", "scripts/lib/actions.py", "scripts/lib/analytics.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/inkedin-automation-that-really-works" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/inkedin-automation-that-really-works", "downloadUrl": "https://openagent3.xyz/downloads/inkedin-automation-that-really-works", "agentUrl": "https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent", "manifestUrl": "https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent.json", "briefUrl": "https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent.md" } } ``` ## Documentation ### LinkedIn Automation Author: Community Contributors ⚠️ DISCLAIMER — PERSONAL USE ONLY This skill is provided for personal, non-commercial use only. It automates your own LinkedIn account for personal productivity and engagement. Do NOT use this skill for spam, mass outreach, scraping other users' data, or any commercial automation service. Use responsibly and in accordance with LinkedIn's User Agreement. The author assumes no liability for misuse or account restrictions. Automate LinkedIn interactions via headless Playwright browser with a persistent session. ### Prerequisites Python 3.10+ with Playwright installed (pip install playwright && playwright install chromium) A logged-in LinkedIn browser session (persistent Chromium profile) Adjust paths in scripts/lib/browser.py to match your setup ### Commands CLI={baseDir}/scripts/linkedin.py # Check if session is valid python3 $CLI check-session # Read feed python3 $CLI feed --count 5 # Create a post (text only) python3 $CLI post --text "Hello world" # Create a post with image (handles LinkedIn's image editor modal automatically) python3 $CLI post --text "Hello world" --image /path/to/image.png # Comment on a post (supports @Mentions — see below) python3 $CLI comment --url "https://linkedin.com/feed/update/..." --text "Great insight @Betina Weiler!" # Edit a comment (match by text fragment) python3 $CLI edit-comment --url "https://..." --match "old text" --text "new text" # Delete a comment python3 $CLI delete-comment --url "https://..." --match "text to identify" # Repost with thoughts python3 $CLI repost --url "https://..." --thoughts "My take..." # Engagement analytics for recent posts python3 $CLI analytics --count 10 # Profile-level stats (followers, views) python3 $CLI profile-stats # Monitor your likes for new ones (for comment suggestions) python3 $CLI scan-likes --count 15 # Scrape someone's activity python3 $CLI activity --profile-url "https://linkedin.com/in/someone/" --count 5 All commands output JSON. Enable debug logging: LINKEDIN_DEBUG=1. ### @Mentions Comments support @FirstName LastName syntax. The skill: Types @FirstName → waits for typeahead dropdown Progressively types last name letter by letter if needed Clicks the match only if first+last name both match Falls back to plain text if person not found (returns mention_failed warning) Check mentions in the JSON result to see if mentions succeeded. ### Like Monitor The scan-likes command checks your recent likes/reactions activity and returns any new likes since the last check. State is persisted to avoid duplicate alerts. Ideal for cron/heartbeat integration: # In HEARTBEAT.md or cron job: python3 $CLI scan-likes → if new likes found → suggest comment for each ### ⚠️ Golden Rule NEVER post, comment, repost, edit, or delete anything without EXPLICIT user approval. Always show the user exactly what will be posted and get a clear "yes" before executing. Read-only actions (feed, analytics, check-session, scan-likes) are safe to run freely. ### Content Calendar (Scheduled Publishing) Full approval-based publishing workflow with auto-posting. See references/content-calendar.md for setup. Webhook (scripts/cc-webhook.py): Receives approve/edit/skip from a frontend UI Auto-apply: Simple edits ("old text -> new text") applied instantly by webhook Agent processing: Complex edits flagged for AI-powered text rewriting Auto-post: Approved posts past their scheduled time are posted automatically via cron Image strategy: Real photos + AI-generated story overlays (not stock photos) # Start the webhook (or install as systemd service) python3 scripts/cc-webhook.py # Env vars for config: # CC_DATA_FILE=/path/to/cc-data.json # CC_ACTIONS_FILE=/path/to/actions.json # CC_WEBHOOK_PORT=8401 ### Content Strategy & Engagement references/content-strategy.md — Hook formulas, post structure, posting times, hashtag strategy, 4-1-1 rule references/engagement.md — Algorithm signals, comment quality formula, rate limits, weekly routine references/dom-patterns.md — Known LinkedIn DOM patterns for troubleshooting references/content-calendar.md — Content calendar setup, data format, webhook API ### Rate Limits ActionDaily MaxWeekly MaxPosts2–310–15Comments20–30—Likes100—Connection requests30100 ### Setup Install dependencies: pip install playwright && playwright install chromium Configure browser profile path in scripts/lib/browser.py (or set LINKEDIN_BROWSER_PROFILE env var) Log in to LinkedIn manually once (the session persists) Run python3 scripts/linkedin.py check-session to verify Learn your voice: Run python3 scripts/linkedin.py learn-profile — this scans your recent posts and comments to learn your tone, topics, language, and style. The agent uses this profile when suggesting comments/posts so they sound like you, not like a generic bot. ### Voice & Style On first setup, learn-profile analyzes your content and saves a style profile (~/.linkedin-style.json) containing: Language (de/en/mixed) Tone (casual / professional / professional-friendly) Emoji usage (heavy / moderate / minimal) Top hashtags you use Sample posts and comments for voice reference The agent should ALWAYS read this profile (get-style) before drafting any comment or post suggestion. Never impose a foreign voice — match the user's natural style. ### Post Age Warning CRITICAL: Before suggesting a comment on any post, check how old the post is: < 2 weeks: Safe to comment > 2 weeks: Warn the user explicitly ("⚠️ This post is X weeks old — commenting on old posts can look like bot behavior. Still want to?") > 1 month: Strongly discourage unless there's a specific reason Commenting on old posts makes it look like you're mining someone's history with a bot. Always flag post age. ### Troubleshooting Session expired: Log in again via browser profile Selectors broken: LinkedIn updates UI frequently — check references/dom-patterns.md and update scripts/lib/selectors.py Debug screenshots: Saved to /tmp/linkedin_debug_*.png on failure ## Trust - Source: tencent - Verification: Indexed source record - Publisher: red777777 - Version: 1.0.1 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:11.935Z - Expires at: 2026-04-30T16:43:11.935Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/inkedin-automation-that-really-works) - [Send to Agent page](https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent) - [JSON manifest](https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent.json) - [Markdown brief](https://openagent3.xyz/skills/inkedin-automation-that-really-works/agent.md) - [Download page](https://openagent3.xyz/downloads/inkedin-automation-that-really-works)