threads-keyword-search
Searches Threads posts by keyword or hashtag and returns matching posts with engagement metrics, extracted from SSR-embedded JSON
Install / Use
npx skills add browser-act/skills --skill threads-keyword-searchInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
OperationsSupported Platforms
Tags
Our assessment of threads-keyword-search
threads-keyword-search scores 91/100 on our quality scale, 261st of 745 Operations skills we index (top 36%).
Its SKILL.md is 6.5 KB long, well organised into 15 sections with 1 code example: a thorough specification that gives an agent plenty to work with.
With 6,001 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 3 months ago, so threads-keyword-search is actively maintained.
- Our last check on 2026-10-28 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
threads-keyword-search compared with similar skills
All 4 of these similar skills score higher than threads-keyword-search; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| threads-keyword-search (this skill)by browser-act | 91 | 6.0k | 3mo ago | SKILL.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 149.0k | 6d ago | SKILL.md |
Frequently asked questions
- How do I install threads-keyword-search?
- Run
npx skills add browser-act/skills --skill threads-keyword-search. The install tabs above show the steps for each supported agent. - Which AI agents does threads-keyword-search work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is threads-keyword-search safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is threads-keyword-search still maintained?
- The repository was last updated about 3 months ago, so threads-keyword-search is actively maintained.
Skill content
View source on GitHubname: threads-keyword-search description: "Searches Threads posts by keyword or hashtag and returns matching posts with engagement metrics, extracted from SSR-embedded JSON. Use when user asks to search Threads posts, find Threads content by topic, scrape Threads search results, collect Threads posts about a keyword, monitor Threads hashtag activity, pull Threads posts mentioning a term, gather Threads content by hashtag, search for posts on Threads, extract Threads search feed, get trending posts on Threads, find Threads discussions about a subject, or fetch recent or top Threads posts by keyword."
Threads — Keyword & Hashtag Search
keyword + sort filter → list of matching posts with engagement metrics
Language
All process output to user (progress updates, process notifications) follows the user's language.
Objective
Search Threads for posts matching a keyword or hashtag and extract the results from SSR-embedded JSON, with support for top/recent sort ordering.
Prerequisites
- A browser is open and connected via browser-act
- No login required for public search results (unauthenticated: typically 17-18 results per query, no pagination)
Pre-execution Checks
1. Tool Readiness
If browser-act has been confirmed available in the current session → skip this step.
Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
Capability Components
This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page. JS code is encapsulated in Python files under the
scripts/directory, invoked viaeval "$(python scripts/xxx.py {params})".$(...)is bash syntax; it is recommended to use the bash tool for execution.
SSR: Extract keyword search results
Navigate to the search page with the keyword and sort filter, then extract all results embedded in the initial HTML:
navigate https://www.threads.com/search/?q={keyword}&serp_type={filter}{keyword}: URL-encoded search term or hashtag (e.g.,AIor%23AIfor#AI){filter}:top(default, most relevant) orrecent(chronologically newest)
wait stableeval "$(python scripts/extract-search-results.py '{keyword}' --filter {filter})"
Output example:
{
"keyword": "AI",
"filter": "top",
"posts": [
{
"id": "3936653356768062022", // post internal ID (pk)
"code": "DZyvcdEl-W1", // post short code for URL
"url": "https://www.threads.com/@flower_popy/post/DZyvcdEl-W1",
"text": "AI is changing everything...", // post text content, null if no caption
"taken_at": 1781926571, // Unix timestamp of post creation
"like_count": 34, // number of likes
"reply_count": 6, // number of direct replies
"repost_count": 0, // number of reposts
"quote_count": 0, // number of quote posts
"is_reply": false, // true if this post is a reply
"media_type": 19, // 1=photo, 2=video, 8=carousel, 19=text-only
"has_media": false, // true if post contains image/video/carousel
"user": {
"pk": "14803522782",
"username": "flower_popy",
"full_name": "Flower",
"is_verified": false
}
}
],
"count": 17,
"page_info": {
"end_cursor": null,
"has_next_page": false,
"has_previous_page": false,
"start_cursor": null
}
}
Error handling: If error: true is returned, check that the search page loaded correctly by verifying the URL contains the query parameter. If searchResults not found, the page may have failed to render SSR data — retry navigate and wait stable once. If count: 0, no posts matched the keyword.
SSR: Hashtag search
Hashtag search uses the same URL pattern. Prefix keyword with #:
navigate https://www.threads.com/search/?q=%23{hashtag}&serp_type={filter}- Example:
%23AIfor#AI
- Example:
wait stableeval "$(python scripts/extract-search-results.py '#AI' --filter top)"
The # prefix in the keyword argument is for labeling only; the URL encoding %23 is what Threads uses to identify hashtag searches.
Enum Parameters
[DOM] filter — values: top (most relevant/popular posts), recent (newest posts first). Set via --filter argument and serp_type URL parameter.
Pagination
Pagination is not available for unauthenticated access on the search endpoint (has_next_page: false is returned regardless of result volume). Results are limited to approximately 17-18 posts per query without login. For broader coverage, run multiple searches with related keywords.
Success Criteria
result.count >= 1 and result.posts[0].id != null and result.posts[0].user.username != null
Known Limitations
- Unauthenticated access: no pagination; approximately 17-18 results per keyword
- Date filtering is not supported as a URL parameter; filter by
taken_at(Unix timestamp) client-side after extraction - Private account posts may appear in search results but their full content may be restricted
- Search index may not include very new posts (lag of minutes to hours)
Execution Efficiency
- Batch orchestration: Write a bash script to loop keywords serially within a single session. Add 1-2 second intervals between searches. For higher throughput, distribute keywords across multiple parallel browser sessions.
- Test before batch execution: Test with 1-2 keywords first before running full batch.
- Reduce redundant pre-operations: Each keyword requires a fresh
navigateto the search URL — the search parameters are baked into the URL. - Error resumption: Save results per keyword; on failure, resume from the breakpoint.
Experience Notes
Path: {working-directory}/browser-act-skill-forge-memories/threads-scraper-threads-keyword-search.memory.md
Before execution: If the file exists, read it first — it records unexpected situations encountered during past executions; adjust strategy order accordingly.
After execution: If an unexpected situation is encountered (strategy became ineffective, page redesigned, anti-scraping upgraded, better path discovered), append a line:
{YYYY-MM-DD}: {what happened} → {conclusion}
Normal execution does not write to the file. Do not record what keywords were used or how many results were returned — those are task outputs, not experience.
Related Skills
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
149.0kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
