- Home
- Skills
- Social Media
- LinkedIn Content Autopilot (Official API, Guardrails, Boost Picks)
Works with the AI Agents you already use
LinkedIn Content Autopilot (Official API, Guardrails, Boost Picks)
Run a B2B LinkedIn company page with an AI agent on the official API: grounded posts, pillar rotation and funnel stages in code, safe replies, hard limits, dry-run mode, post statistics and data-driven boost picks.
$19
LinkedIn Content Autopilot (Official API, Guardrails, Boost Picks)
Example session with this skill installed
We are a 12-person data consultancy. I want an AI agent to run our LinkedIn company page on its own: one post a day and replies to comments. Write the design in DESIGN.md, including how it decides what to post and how we know which posts to boost.
- Read your context and instructions
- Compiled the linkedin content autopilot
DESIGN.md: Community Management API app, page admin consent, pinned LinkedIn-Version, token expiry alert. Four pillars (article, vendor release, open source, how we work) mapped to awareness, consideration and conversion, rotated by a scheduler from the action log. Tools refuse outside their task, allow one post per day and 40 replies, use idempotency keys, never delete, and start in dry_run for a week. Every post reads its source first, passes post_lint (UTM, length, escaping), and is logged. Daily stats snapshots feed a boost view: posts 2-14 days old with engagement at least 1.2x the page median, objective by stage, spending decided by a human.
Connects securely to your tools. The creator never sees your data.
About this skill
An unsupervised agent with publishing rights is a reputation risk with a scheduler attached. This skill keeps judgement in the model and every guardrail in the tools: what may be published, when, how often, in which format, with which links.
What your agent builds with it
- Official API setup for a company page (Community Management API, scopes, versioned REST, token expiry alerts), with the request shapes for text, image and video posts, comments, reactions and statistics.
- Content pillars grounded in sources the agent must read in the same run (your articles, your repos, confirmed vendor releases) so it never posts from memory.
- Rotation and funnel stages in code: least-recently-used pillar, awareness / consideration / conversion rules, recent-topic memory (
pillar_rotation.py). - Guardrails inside the tools: task context, one action per task, daily and weekly limits, idempotency keys, no delete tools,
live/dry_run/offmodes, full action log. - Post hygiene (
post_lint.py): emoji and stock-phrase cleanup, UTM tagging for your domain only, length, hook and hashtag checks, and LinkedIn's reserved-character escaping (unescaped, posts get silently truncated). - A playbook prompt template for replies and scheduled posts, with a boostability checklist.
- Measure and boost: daily post statistics, and boost candidates benchmarked against your own page median with the objective chosen by funnel stage (
boost_candidates.py, SQL view). The agent never spends money.
Included: SKILL.md, LinkedIn API reference, playbook template, 3 standard-library scripts, example pillars, a BigQuery view, and an eval case.
Part of the Production AI Agents series. Pair with Research-Backed Article Writer and AI Short Video Production.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Social Media.
Uses only the official LinkedIn API (no scraping or browser automation). Company pages, not personal profiles. LinkedIn products, scopes and versions change; the API reference is dated and tells you to verify. Does not create the visuals or videos itself (see the companion skills).
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago
- Software
- LinkedIn company pageapproved API app
Python 3.10+
- Optional
- BigQueryoranother SQL warehouseGoogle ADKoranother agent framework
Posting as a company page needs LinkedIn's Community Management API product on your app, which LinkedIn must approve.
Permissions
File Scopes
Bundled scripts process text and JSON locally and make no network calls.