本文へ移動
cccskills
無料GitHub で公開

linkedin-post-research

Search LinkedIn posts by keywords, sorted by engagement or date. Use when researching what people are saying about a topic on LinkedIn, finding high-engagement content, identifying thought leaders, or discovering warm leads through post engagement. Returns author, post text, reactions, comments, shares, post URL, and date. No LinkedIn cookies or login required.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md5.1 KB
  • scripts/search_posts.py11.0 KB
  • skill.meta.json267 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

LinkedIn Post Research

Search LinkedIn for posts matching keywords via Apify. Returns posts sorted by engagement or date, with author info, full text, reaction counts, and direct URLs.

No LinkedIn cookies. No login. Just keywords in, posts out.

When to Auto-Load

Load this skill when:

  • User says "search LinkedIn posts", "what are people saying about X on LinkedIn", "find LinkedIn content about"
  • User wants to find high-engagement posts on a topic
  • User wants to identify who's posting about a specific topic (thought leader discovery)
  • User wants to find posts to extract commenters from (warm lead pipeline)

Prerequisites

Apify API Token

Required for searching LinkedIn posts. Set in .env:

APIFY_API_TOKEN=your_token_here

No LinkedIn cookies, login, or session tokens needed. That's the only setup.


How It Works

  1. Takes one or more keywords
  2. Calls the apimaestro/linkedin-posts-search-scraper-no-cookies Apify actor
  3. Returns posts with author, text, engagement metrics, date, and URL
  4. Deduplicates across keywords by activity_id
  5. Sorts by engagement (total reactions) descending, or by date

Quick Start

# Single keyword search
python3 skills/capabilities/linkedin-post-research/scripts/search_posts.py \
  --keyword "AI sourcing" --max-items 20

# Multiple keywords
python3 skills/capabilities/linkedin-post-research/scripts/search_posts.py \
  --keyword "AI sourcing" --keyword "recruiting automation" --max-items 30

# Sort by date (most recent first)
python3 skills/capabilities/linkedin-post-research/scripts/search_posts.py \
  --keyword "AI agents" --sort-by date_posted --max-items 20

# Output as CSV
python3 skills/capabilities/linkedin-post-research/scripts/search_posts.py \
  --keyword "AI agents" --output csv --output-file results.csv

# Summary table
python3 skills/capabilities/linkedin-post-research/scripts/search_posts.py \
  --keyword "AI agents" --output summary

CLI Reference

FlagDefaultDescription
--keyword, -krequiredKeyword to search (can be repeated for multiple keywords)
--max-items50Max posts to return per keyword
--sort-byrelevanceSort order: relevance or date_posted
--output, -ojsonOutput format: json, csv, summary
--output-filestdoutWrite output to file
--tokenenv varApify API token (overrides APIFY_API_TOKEN env var)
--timeout120Max seconds to wait for Apify run

Apify Actor Details

Actor: apimaestro/linkedin-posts-search-scraper-no-cookies

API call:

curl -X POST "https://api.apify.com/v2/acts/apimaestro~linkedin-posts-search-scraper-no-cookies/runs?token=$APIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "keyword": "AI agents",
    "maxItems": 50,
    "sortBy": "date_posted"
  }'

Polling for results:

# Check run status
curl "https://api.apify.com/v2/acts/apimaestro~linkedin-posts-search-scraper-no-cookies/runs/{RUN_ID}?token=$APIFY_API_TOKEN"

# When status is SUCCEEDED, fetch results
curl "https://api.apify.com/v2/datasets/{DATASET_ID}/items?token=$APIFY_API_TOKEN"

Output Schema

{
  "author": "Jane Smith",
  "author_headline": "VP of Sales at Acme Corp",
  "author_profile_url": "https://www.linkedin.com/in/janesmith",
  "keyword": "AI sourcing",
  "reactions": 142,
  "comments": 28,
  "shares": 12,
  "reactions_by_type": {"LIKE": 100, "EMPATHY": 30, "PRAISE": 12},
  "date": "2026-04-01",
  "post_preview": "First 200 chars of the post text...",
  "full_text": "Complete post text...",
  "url": "https://www.linkedin.com/posts/...",
  "activity_id": "7447040447966826496",
  "hashtags": ["#AI", "#sales"],
  "is_repost": false,
  "content_type": "text"
}

Output Columns (CSV)

ColumnDescription
authorPost author name
author_headlineAuthor's LinkedIn headline
author_profile_urlAuthor's LinkedIn profile URL
keywordWhich search keyword matched
reactionsTotal reaction count
commentsComment count
sharesShare count
datePost date (YYYY-MM-DD)
post_previewFirst ~200 characters
urlDirect link to the LinkedIn post
activity_idUnique post identifier
hashtagsComma-separated hashtags

Cost

Apify charges per compute usage. ~50 posts costs approximately $0.01-0.05 depending on the actor's pricing tier. The script prints cost info after each run.

Error Handling

ErrorFix
APIFY_API_TOKEN not setAsk user to add it to .env
Apify run fails or times outRetry once. If still fails, try a broader keyword.
0 resultsKeyword may be too specific. Try broader terms.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

gooseworks-ai のスキルをすべて見る

このスキルの問題を報告する