How do I install the Linkedin Post Research skill?

Run npx skillmds@latest add robomotionio/linkedin-post-research in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Linkedin Post Research safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Linkedin Post Research?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Linkedin Post Research free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Linkedin Post Research?

robomotionio (@robomotionio) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Linkedin Post Research by robomotionio

Name: Linkedin Post Research
Author: robomotionio

Linkedin Post Research

Search LinkedIn posts by keyword, sorted by engagement or date, returning author, post text, reaction/comment/share counts, URL, and date. Use to research what people say about a topic, find high-engagement content, spot thought leaders, or seed a warm-lead pipeline. Apify actor primary with a keyless web-search degrade.

robomotionio 796d97d 4 files · 10.3 KB Updated Sep 17, 2026

File contents

LinkedIn Post Research

Search public LinkedIn posts for one or more keywords. Primary path is an Apify posts-search actor (cookieless, full engagement metrics); degrades to a keyless web search over public linkedin.com/posts URLs (titles/URLs only, no engagement counts).

When to use

"What are people saying about [topic] on LinkedIn?" / "search LinkedIn posts."
"Find high-engagement posts on [topic]" / "who's posting about [topic]?"
Feeds linkedin-commenter-extractor (posts -> commenters) and kol-discovery.

How to run

Python 3 stdlib only — no install:

python3 ${SKILL_DIR}/scripts/post_search.py \
  --keywords "rpa,workflow automation" \
  --max-items 50 --sort-by relevance --output json

Flag	Default	Meaning
`--keywords`	(required)	Comma-separated search keywords.
`--max-items`	`50`	Cap per keyword.
`--sort-by`	`relevance`	`relevance` (engagement) or `date_posted`.
`--actor`	apimaestro posts-search	Override the Apify actor id.
`--output`	`json`	`json` / `csv` / `summary`.

Results are deduped across keywords by activity_id and sorted. The agent then judges relevance and picks the posts worth acting on.

Outputs

Per post: {author, author_headline, author_profile_url, keyword, reactions, comments, shares, date, post_preview, full_text, url, activity_id, hashtags, is_repost, source}. source is apify (full metrics) or serp-degrade (URL/title only).

Credentials / env

env.required: none — the keyless serp degrade always works (Robomotion Proxy is platform-provided in production).
env.optional: APIFY_API_TOKEN — if set → cookieless Apify posts-search actor with full engagement metrics; else → keyless public site:linkedin.com/posts search (the default; no reaction/comment counts, prints a fidelity warning).

Notes & edge cases

Engagement counts and activity_id are only reliable via Apify (or web-automation against the logged-in app); the serp fallback returns titles/URLs only — fidelity is flagged in source and on stderr.
Too-specific keywords return zero results — broaden and retry.
Apify path costs ~credits per ~50 posts; note before running at volume.
The bundled degrade uses DuckDuckGo HTML; in a Robomotion flow this maps to robomotion-serp Search behind the platform proxy.

---name: linkedin-post-researchdescription: Search LinkedIn posts by keyword, sorted by engagement or date, returning author, post text, reaction/comment/share counts, URL, and date. Use to research what people say about a topic, find high-engagement content, spot thought leaders, or seed a warm-lead pipeline. Apify actor primary with a keyless web-search degrade.---# LinkedIn Post ResearchSearch public LinkedIn posts for one or more keywords. Primary path is an **Apifyposts-search actor** (cookieless, full engagement metrics); degrades to a **keyless websearch** over public `linkedin.com/posts` URLs (titles/URLs only, no engagement counts).## When to use- "What are people saying about [topic] on LinkedIn?" / "search LinkedIn posts."- "Find high-engagement posts on [topic]" / "who's posting about [topic]?"- Feeds `linkedin-commenter-extractor` (posts -> commenters) and `kol-discovery`.## How to runPython 3 stdlib only — no install:```bashpython3 ${SKILL_DIR}/scripts/post_search.py \ --keywords "rpa,workflow automation" \ --max-items 50 --sort-by relevance --output json```| Flag | Default | Meaning ||---|---|---|| `--keywords` | (required) | Comma-separated search keywords. || `--max-items` | `50` | Cap per keyword. || `--sort-by` | `relevance` | `relevance` (engagement) or `date_posted`. || `--actor` | apimaestro posts-search | Override the Apify actor id. || `--output` | `json` | `json` / `csv` / `summary`. |Results are deduped across keywords by `activity_id` and sorted. The agent then judgesrelevance and picks the posts worth acting on.## OutputsPer post: `{author, author_headline, author_profile_url, keyword, reactions, comments,shares, date, post_preview, full_text, url, activity_id, hashtags, is_repost, source}`.`source` is `apify` (full metrics) or `serp-degrade` (URL/title only).## Credentials / env- `env.required`: **none** — the keyless serp degrade always works (Robomotion Proxy is platform-provided in production).- `env.optional`: `APIFY_API_TOKEN` — **if set → cookieless Apify posts-search actor with full engagement metrics; else → keyless public `site:linkedin.com/posts` search** (the default; no reaction/comment counts, prints a fidelity warning).## Notes & edge cases- Engagement counts and `activity_id` are only reliable via Apify (or web-automation against the logged-in app); the serp fallback returns titles/URLs only — fidelity is flagged in `source` and on stderr.- Too-specific keywords return zero results — broaden and retry.- Apify path costs ~credits per ~50 posts; note before running at volume.- The bundled degrade uses DuckDuckGo HTML; in a Robomotion flow this maps to `robomotion-serp` Search behind the platform proxy.

Frequently asked questions