Agent skill

Hacker News Search

by dylanfeltus in dylanfeltus/skills

Searches and monitors Hacker News stories, comments and users through the free Algolia HN Search API, with tag, points and date filters.

MITAuto-check passedProductivity & Automation

Install Hacker News Search

skills CLI
$ npx skills add dylanfeltus/skills --skill hn-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dylanfeltus/skills hn-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hn-search .claude/skills/hn-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hn-search
GitHub stars
179
Token cost
~1.7k tokens
SKILL.md length
569 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Searches and monitors Hacker News stories, comments and users through the free Algolia HN Search API, with tag, points and date filters.

  • Works in 2 steps: Build the URL → Fetch with web_fetch
  • Finding Hacker News discussions about a company, product or technology
  • SKILL.md covers When to Use, API Overview, How to Search and Response Format, plus 6 more sections
  • Reaches hn.algolia.com and news.ycombinator.com

What it does

Hacker News stories, comments and users are searched through the free Algolia HN Search API, which needs no API key. The agent builds a URL against hn.algolia.com, fetches the JSON with a web fetch tool, and chooses between two endpoints: one sorted by relevance for finding topics and one sorted by date for monitoring recent activity.

Queries can be filtered by tag, such as stories, comments, Show HN, Ask HN, front page posts, a given author or the comments on one story, and the tags combine with AND or OR. Numeric filters set minimum points or comment counts and bound results by Unix timestamps, with the agent calculating the current time before subtracting a window such as the last 24 hours. Up to 1000 results per page are allowed, and the stated rate limit is 10,000 requests per hour.

When your agent uses it

  • Finding Hacker News discussions about a company, product or technology
  • Seeing what is on the front page or trending on HN
  • Monitoring HN for new mentions of a topic
  • Looking up Show HN, Ask HN or Launch HN posts

Example prompts

  • “What did Hacker News think about the latest Rust release?”
  • “Find Show HN posts from the last week with more than 100 points.”
  • “Monitor HN for new mentions of our product name and list the newest stories.”

Requirements

  • Network access to hn.algolia.com

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Build the URL
  2. Fetch with web_fetch

What it can do on your machine

Read from SKILL.md and the folder at commit b97a48f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • hn.algolia.com
    • news.ycombinator.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hacker News Search loads about 1.7k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 569 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dylanfeltus/skills at commit b97a48f, republished under its MIT licence (© dylanfeltus). 569 words, ~1,692 tokens.

Download SKILL.mdSave it as .claude/skills/hn-search/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
hn-search
description
Search and monitor Hacker News stories, comments, and users via the free Algolia API. Use when the user asks about HN discussions, wants to find posts about a topic, or monitor HN for mentions. No API key required.

Search and monitor Hacker News stories, comments, and users via the Algolia HN Search API. No API key required.

When to Use

  • User asks about Hacker News discussions on a topic
  • User wants to find HN posts about a company, product, or technology
  • User wants to monitor HN for mentions of something
  • User asks "what's trending on HN" or "what did HN think about X"
  • User wants to find Show HN / Ask HN / Launch HN posts

API Overview

Base URL: https://hn.algolia.com/api/v1

Two search endpoints:

  • /search — Relevance-sorted (best for finding specific topics)
  • /search_by_date — Date-sorted (best for monitoring / recent activity)

Rate Limits: 10,000 requests/hour (generous, no auth needed)

Step 1: Build the URL
https://hn.algolia.com/api/v1/search?query=QUERY&tags=TAG&hitsPerPage=N&numericFilters=FILTERS
Step 2: Fetch with web_fetch

Use web_fetch to call the API. Response is JSON.

Parameters
ParameterDescriptionExample
querySearch terms (URL-encoded)query=openai+gpt
tagsFilter by type (see below)tags=story
hitsPerPageResults per page (max 1000)hitsPerPage=20
pagePage number (0-indexed)page=0
numericFiltersNumeric filters (see below)numericFilters=points>100
Tag Filters

Use tags to filter by content type:

TagDescription
storyStories only
commentComments only
show_hnShow HN posts
ask_hnAsk HN posts
front_pageCurrently on front page
author_USERNAMEPosts by a specific user
story_IDComments on a specific story

Combine tags with commas (AND) or parentheses with commas (OR):

  • tags=story,show_hn → Show HN stories (AND)
  • tags=(story,comment) → Stories OR comments
Numeric Filters
FilterDescription
points>NMinimum points/upvotes
num_comments>NMinimum comments
created_at_i>TIMESTAMPAfter Unix timestamp
created_at_i<TIMESTAMPBefore Unix timestamp

Combine with commas: numericFilters=points>100,num_comments>50

Date Ranges

To search within a time window, use Unix timestamps with created_at_i:

Calculate the current Unix timestamp first (e.g., via exec: date +%s), then subtract:

WindowSubtract from now
Last 24 hours- 86400
Last 7 days- 604800
Last 30 days- 2592000

Example: if now is 1705312200, last 7 days = numericFilters=created_at_i>1704707400

Response Format

Each hit contains:

json
{
  "objectID": "12345",
  "title": "Story Title",
  "url": "https://example.com/article",
  "author": "username",
  "points": 150,
  "num_comments": 42,
  "created_at": "2024-01-15T10:30:00Z",
  "created_at_i": 1705312200,
  "story_text": "Text for Ask HN / Show HN (HTML)",
  "_tags": ["story", "author_username", "story_12345"]
}

For comments, hits also include:

json
{
  "comment_text": "The comment body (HTML)",
  "story_id": 12345,
  "story_title": "Parent Story Title",
  "story_url": "https://example.com",
  "parent_id": 12344
}

The response wrapper includes:

json
{
  "hits": [...],
  "nbHits": 1000,
  "page": 0,
  "nbPages": 50,
  "hitsPerPage": 20
}
  • Story: https://news.ycombinator.com/item?id={objectID}
  • Comment: https://news.ycombinator.com/item?id={objectID}
  • User: https://news.ycombinator.com/user?id={author}

Step-by-Step Instructions

Searching for Stories on a Topic
  1. URL-encode the query
  2. Fetch: https://hn.algolia.com/api/v1/search?query=YOUR_QUERY&tags=story&hitsPerPage=10
  3. Parse the JSON response
  4. For each hit, present: title, points, num_comments, author, date, HN link, and original URL
Show full SKILL.md (212 more words)Show less
  1. Calculate Unix timestamp for your time window (e.g., 7 days ago)
  2. Fetch: https://hn.algolia.com/api/v1/search?query=YOUR_QUERY&tags=story&numericFilters=points>50,created_at_i>TIMESTAMP&hitsPerPage=10
  3. Sort results by points or comments for "trending"
Getting Comments on a Story
  1. Get the story's objectID from a search
  2. Fetch: https://hn.algolia.com/api/v1/search?tags=comment,story_STORYID&hitsPerPage=20
  3. Present comment_text, author, points for each
Monitoring a Topic (Show Recent Mentions)
  1. Use /search_by_date instead of /search
  2. Fetch: https://hn.algolia.com/api/v1/search_by_date?query=YOUR_QUERY&tags=(story,comment)&hitsPerPage=20
  3. Results are newest-first — useful for "what's new about X on HN"
Finding a User's Posts
  1. Fetch: https://hn.algolia.com/api/v1/search?tags=author_USERNAME,story&hitsPerPage=20
  2. For their comments: tags=author_USERNAME,comment

Output Format

Present results as a clean list:

### HN Results for "query" (N total)

1. **Story Title** (150 pts, 42 comments)
   By username · Jan 15, 2024
   🔗 https://example.com/article
   💬 https://news.ycombinator.com/item?id=12345

2. ...

For comments:

### HN Comments on "Story Title"

1. **username** (12 pts) · Jan 15, 2024
   > First ~200 chars of the comment text...
   💬 https://news.ycombinator.com/item?id=12345

Error Handling

  • Empty results: Tell the user no results were found. Suggest broadening the query or removing filters.
  • API error / timeout: Retry once. If still failing, inform the user the HN search API may be temporarily down.
  • Rate limited (429): Unlikely at 10k/hr, but if hit, wait 60 seconds and retry.
  • Malformed response: Check the URL construction — common issues are unencoded special characters in the query.

Examples

Example 1: "What's HN saying about Rust?"
Fetch: https://hn.algolia.com/api/v1/search?query=rust+programming&tags=story&hitsPerPage=5&numericFilters=points>50
Example 2: "Find Show HN posts about AI agents from the last month"
# Calculate timestamp for 30 days ago, then:
Fetch: https://hn.algolia.com/api/v1/search_by_date?query=ai+agents&tags=show_hn&numericFilters=created_at_i>TIMESTAMP&hitsPerPage=10
Example 3: "What has pg posted recently?"
Fetch: https://hn.algolia.com/api/v1/search_by_date?tags=author_pg&hitsPerPage=10

Data Source

Algolia HN Search API — Free, no authentication required. Indexes all public Hacker News content in near real-time.

© dylanfeltus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in hn-search of dylanfeltus/skills.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit b97a48f

Compare with similar skills

Hacker News Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hacker News Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hacker News Search this skilldylanfeltus/skills179—~1.7kAutomated safety check: PassMIT
9Router Web Searchdecolua/9router31k—~1kAutomated safety check: PassMIT
YouTube Channel ToolsZeroPointRepo/youtube-skills1k1 repos~3.3kAutomated safety check: PassMIT
Brave Local Place Descriptionsbrave/brave-search-skills183—~1kAutomated safety check: PassMIT
Brave Local Place Searchbrave/brave-search-skills183—~3.4kAutomated safety check: PassMIT
Hacker News Summarizerykdojo/claude-code-tips10k—~942Automated safety check: PassCustom licence

Similar skills

  • 9Router Web Search

    decolua/9router

    Runs web, news and public X searches through a 9Router gateway's search endpoint, choosing among providers such as Tavily, Exa, Brave and Perplexity.

    31k GitHub stars~1k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • YouTube Channel Tools

    ZeroPointRepo/youtube-skills

    Browses YouTube channels through TranscriptAPI: resolves handles to channel IDs, lists recent uploads and pages through a channel's videos.

    1k GitHub starsUsed in 1 repo~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Brave Local Place Descriptions

    brave/brave-search-skills

    Fetches AI-written text descriptions for local places from the Brave Search API, using place IDs returned by an earlier local search.

    183 GitHub stars~1k tokensUpdated 17 days ago
    Productivity & AutomationAuto-check passed
  • Brave Local Place Search

    brave/brave-search-skills

    Looks up businesses, points of interest, addresses and streets through the Brave Search place endpoint, returning contact details, ratings and hours in one call.

    183 GitHub stars~3.4k tokensUpdated 17 days ago
    Productivity & AutomationAuto-check passed
  • Hacker News Summarizer

    ykdojo/claude-code-tips

    Fetches Hacker News top stories, a chosen story with its comment thread and the linked article through the official APIs, then summarizes them.

    10k GitHub stars~942 tokensUpdated 15 days ago
    Writing & ContentAuto-check passed
  • Read The Damn Docs

    BuilderIO/skills

    A skill your agent uses when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs…

    4.6k GitHub stars~1.8k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from dylanfeltus/skills

All 10 skills in this repo
  • App Store Intelligence

    dylanfeltus/skills

    Looks up app details, ratings and reviews and searches the iOS and Mac App Stores through Apple's free iTunes APIs, with a web-search fallback for Google Play.

    179 GitHub stars~2k tokensUpdated 23 days ago
    Auto-check passed
  • AI Image Creative Direction

    dylanfeltus/skills

    Gives prompt templates, a model-selection guide and anti-generic rules for AI-generated visuals: hero images, feature illustrations, OG cards, icons and backgrounds.

    179 GitHub stars~2.6k tokensUpdated 23 days ago
    Auto-check passed
  • Design Token Generator

    dylanfeltus/skills

    Generates type scales, color palettes, spacing systems, WCAG contrast checks and dark mode palettes from formulas, as CSS custom properties, a Tailwind config or JSON tokens.

    179 GitHub stars~2.9k tokensUpdated 23 days ago
    Auto-check passed
  • Framer Motion (Motion) patterns for React: spring presets, staggers, layout animations, micro-interactions, scroll effects and page transitions, with performance rules.

    179 GitHub stars~3k tokensUpdated 23 days ago
    Auto-check passed
  • Privacy.com Virtual Cards

    dylanfeltus/skills

    Creates, updates, and monitors Privacy.com virtual payment cards with spending limits for an agent making controlled purchases.

    179 GitHub stars~2.2k tokensUpdated 23 days ago
    Auto-check passed
  • Looks up Product Hunt launches, products and makers through its GraphQL API: daily top posts, topic browsing and per-post details, using a free developer token.

    179 GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed

Works with

Questions about Hacker News Search

What does Hacker News Search do?

Searches and monitors Hacker News stories, comments and users through the free Algolia HN Search API, with tag, points and date filters. Hacker News stories, comments and users are searched through the free Algolia HN Search API, which needs no API key.com, fetches the JSON with a web fetch tool, and chooses between two endpoints: one sorted by relevance for finding topics and one sorted by date for monitoring recent activity.

When should I use Hacker News Search?

Hacker News Search fits situations like: finding Hacker News discussions about a company, product or technology; seeing what is on the front page or trending on HN; monitoring HN for new mentions of a topic; looking up Show HN, Ask HN or Launch HN posts.

How do I install Hacker News Search in Claude Code?

Run `npx skills add dylanfeltus/skills --skill hn-search -a claude-code`. Or copy the skill folder (hn-search in dylanfeltus/skills) into .claude/skills/hn-search in your project. Claude Code loads it when a task matches its description.

How do I install Hacker News Search in Codex?

Run `npx skills add dylanfeltus/skills --skill hn-search -a codex`. Or copy the skill folder (hn-search in dylanfeltus/skills) into .agents/skills/hn-search in your project. Codex loads it when a task matches its description.

Can I use Hacker News Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dylanfeltus/skills --skill hn-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hn-search, .gemini/skills/hn-search, .github/skills/hn-search and .opencode/skills/hn-search in your project.

What does Hacker News Search need to run?

SKILL.md names no scripts, command-line tools or credentials: Hacker News Search is instructions for the agent only. Our summary lists: Network access to hn.algolia.com.

Does Hacker News Search access the network?

SKILL.md names 2 domains. In commands or code: hn.algolia.com and news.ycombinator.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Hacker News Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hacker News Search use?

Hacker News Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hacker News Search use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hacker News Search?

Skills that share tags, products or a category with Hacker News Search: 9Router Web Search (decolua/9router, 31k stars), YouTube Channel Tools (ZeroPointRepo/youtube-skills, 1k stars), Brave Local Place Descriptions (brave/brave-search-skills, 183 stars) and Brave Local Place Search (brave/brave-search-skills, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hacker News Search?

dylanfeltus (a GitHub user) maintains it in dylanfeltus/skills, which has 179 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 17, 2026.

Source: dylanfeltus/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.