--- name: scout-dx.hugen.tokyo description: scout-dx.hugen.tokyo provides a collection of search and discovery skills targeting developer-oriented sources: Hacker News, GitLab, Product Hunt, Stack Overflow, Dev.to, Lobste.rs, PyPI, the x402 Bazaar API directory, and a multi-source AI-synthesized research report endpoint. Each skill issues a single-shot query against its respective source and returns structured metadata. No real-time streaming, financial data, or write operations are supported. host: scout-dx.hugen.tokyo --- # scout-dx.hugen.tokyo scout-dx.hugen.tokyo is a developer intelligence aggregation host serving agents that need to discover, compare, or research technical topics across multiple community and registry sources. It covers link aggregators (HN, Lobste.rs), code and package registries (GitLab, PyPI), community content (Dev.to, Stack Overflow), product discovery (Product Hunt), x402 API discovery, and a paid multi-source synthesis report. It is distinct from general web search hosts in that every skill targets a specific, structured developer or academic source rather than the open web. ## When to use this host Use scout-dx.hugen.tokyo when an agent needs structured discovery across specific developer sources: HN, Lobste.rs, Stack Overflow, Dev.to, GitLab, PyPI, Product Hunt, or the x402 Bazaar. The fetch-scout-research-report skill is the right choice when a single synthesized brief across many sources is needed at once, at a cost of $0.25 USDC per call. Do not use this host for: general open-web search (use a Bing, Google, or Brave Search API instead); GitHub repository search (use the GitHub Search API directly); real-time or streaming content; financial or token price data; fetching a specific item by ID (use the source's native API); or bulk dependency audits across many packages. All skills are single-shot paginated queries with no write, execute, or streaming capability. ## Capabilities ### Developer Link Aggregators Searches curated tech news and discussion communities to surface relevant stories, scores, and community signals for a given keyword or topic. - **`search-hacker-news`** — Searches Hacker News stories, comments, and polls via Algolia and returns titles, URLs, points, comment counts, authors, and dates for matching items. - **`search-lobsters`** — Searches Lobste.rs, a curated tech link aggregator, and returns matching stories with scores, comment counts, authors, tags, and timestamps. ### Technical Q&A and Blog Content Finds structured Q&A threads on Stack Overflow and technical blog posts on Dev.to, including engagement metrics useful for ranking or filtering results. - **`search-stackoverflow-questions`** — Searches Stack Overflow (or any StackExchange site) by keyword and returns questions with scores, answer counts, view counts, tags, and author metadata. - **`search-devto-articles`** — Searches Dev.to (Forem) for technical articles and blog posts, returning title, description, author, reactions, comments, reading time, tags, and publication date. ### Code and Package Registries Discovers public GitLab repositories and resolves Python package metadata on PyPI, providing activity signals, version info, and licensing details. - **`search-gitlab-projects`** — Searches GitLab.com public projects and returns name, description, stars, forks, topics, default branch, and last activity date for each result. - **`search-pypi-packages`** — Looks up Python packages on PyPI by name, trying hyphenated, underscored, and py-prefixed variants, and returns version, summary, license, author, and links. ### Product and API Discovery Finds launched products on Product Hunt and x402-enabled micropayment APIs in the x402 Bazaar directory, returning structured metadata for evaluation. - **`search-product-hunt`** — Searches Product Hunt by topic slug or keywords and returns product name, tagline, description, votes, comments, topics, makers, and URLs sorted by votes or newest. - **`search-x402-bazaar`** — Searches the x402 Bazaar CDP Discovery directory for AI-agent APIs with micropayment access, returning resource URLs, prices, networks, and relevance scores. ### Multi-Source Research Synthesis Issues a single query across 14 developer and academic sources in parallel and returns an AI-synthesized report with summary, key findings, sentiment, and recommendations. - **`fetch-scout-research-report`** — Searches 14 developer and academic sources in parallel (HN, GitHub, npm, PyPI, ArXiv, etc.) and returns an AI-synthesized intelligence report with summary, key findings, sentiment, trends, and recommendations. ## Workflows ### Python Library Due Diligence *Use when an agent needs to evaluate a Python library by combining registry metadata with community discussion and Q&A signals.* 1. **`search-pypi-packages`** — Resolve the package name to its current version, license, author, and homepage links on PyPI. 2. **`search-stackoverflow-questions`** — Find Stack Overflow threads about the package to surface common issues, usage patterns, and community familiarity. 3. **`search-hacker-news`** — Search HN for discussions or Show HN posts about the library to gauge developer sentiment and adoption signals. ### Technical Topic Research Brief *Use when an agent needs a comprehensive view of a technical topic by first pulling a synthesized report and then supplementing with targeted community signals.* 1. **`fetch-scout-research-report`** — Retrieve an AI-synthesized intelligence report covering 14 developer and academic sources for the topic. 2. **`search-hacker-news`** — Supplement with recent HN stories and comments to capture community reactions not yet reflected in the synthesis. 3. **`search-devto-articles`** — Find practitioner blog posts on Dev.to to surface tutorials, opinions, and real-world usage examples. ### x402 API Discovery and Vetting *Use when an agent needs to find a paid x402 API for a capability and then assess community awareness or prior discussion of that API or its provider.* 1. **`search-x402-bazaar`** — Search the x402 Bazaar directory for APIs matching the desired capability, returning resource URLs, prices, and networks. 2. **`search-hacker-news`** — Search HN for mentions of the discovered API or its provider to assess community trust and prior discussion. 3. **`search-product-hunt`** — Check Product Hunt for any launch page associated with the API or its parent product to review votes and maker information. ## Skill reference ### `search-hacker-news` **Scout HN Feed** — Searches Hacker News stories, comments, and polls via Algolia and returns titles, URLs, points, comment counts, authors, and dates for matching items. *Use when:* Use when an agent needs to discover or analyze Hacker News content by keyword, optionally filtered by content type (story, comment, poll, show_hn, ask_hn) and sorted by relevance or date. *Not for:* Do not use for real-time streaming of new HN posts; this is a single-shot search query. Not suitable for fetching a specific HN item by ID — use the HN API directly for that. **Inputs:** - `q` (string, required) — Search query string to match against Hacker News content. - `sort` (string) — Sort order for results: 'relevance' (default) or 'date' for chronological ordering. - `per_page` (integer) — Number of results to return, between 1 and 50. Defaults to 10. - `tag` (string) — Filter results by content type. One of: story, comment, poll, show_hn, ask_hn. **Returns:** Returns success=true with a data array of up to 50 HN items (id, title, url, hn_url, author, points, comments, date, type) plus source, query, count, and elapsed_ms metadata. **Example:** `GET https://scout-dx.hugen.tokyo/scout/hn?q=AI+agents&sort=relevance&per_page=10&tag=story` --- ### `search-gitlab-projects` **GitLab Project Search** — Searches GitLab.com public projects and returns name, description, stars, forks, topics, default branch, and last activity date for each result. *Use when:* Use when an agent needs to discover or analyze public GitLab-hosted repositories by keyword, especially for enterprise OSS or projects not mirrored on GitHub, and requires activity signals like stars, forks, and last activity date. *Not for:* Do not use for GitHub-hosted repositories; use a GitHub search API instead. Not suitable for private GitLab repositories or real-time commit-level activity streaming. **Inputs:** - `q` (string, required) — Search query string for GitLab projects. - `per_page` (integer) — Number of results to return per page. Minimum 1, maximum 20, default 10. - `sort` (string) — Sort order for results. One of: stars, updated, name. Default is stars. **Returns:** Returns success=true and a data array of up to 20 GitLab project objects, each with id, name, full_name, description, url, stars, forks, topics, default_branch, last_activity, and created timestamps. **Example:** `GET https://scout-dx.hugen.tokyo/scout/gitlab?q=kubernetes&per_page=5&sort=stars` --- ### `search-product-hunt` **Scout Product Hunt Search** — Searches Product Hunt by topic slug or keywords and returns product name, tagline, description, votes, comments, topics, makers, and URLs sorted by votes or newest. *Use when:* Use when an agent needs to discover Product Hunt products or launches for a given topic, keyword, or category, and requires structured data including vote counts, maker info, and direct Product Hunt links. *Not for:* Do not use for real-time trending feeds or streaming price/rank data; this is a single-shot search returning up to 20 results per call. **Inputs:** - `q` (string, required) — Topic slug or keywords to search on Product Hunt. - `order` (string) — Sort order for results. Allowed values: VOTES, NEWEST. Defaults to VOTES. - `per_page` (integer) — Number of results to return, between 1 and 20. Defaults to 10. **Returns:** Returns success=true and a data array of up to 10 product objects, each with id, name, tagline, description, ph_url, website, votes, comments, date, topics array, makers array, and thumbnail URL. **Example:** `GET https://scout-dx.hugen.tokyo/scout/ph?q=developer-tools&order=VOTES&per_page=10` --- ### `fetch-scout-research-report` **Scout Research Report** — Searches 14 developer and academic sources in parallel (HN, GitHub, npm, PyPI, ArXiv, etc.) and returns an AI-synthesized intelligence report with summary, key findings, sentiment, trends, and recommendations. *Use when:* Use when an agent needs a multi-source research brief on a technical topic, library, framework, or market trend — especially when raw search results plus an AI synthesis layer are both required in a single call. *Not for:* Do not use for real-time price feeds, financial market data, or general web search; this endpoint targets developer/academic sources only and costs $0.25 USDC per call. **Inputs:** - `query` (string, required) — Research query string, max 500 characters. - `per_page` (integer) — Number of results to fetch per source. Integer between 1 and 20, default 5. - `focus` (string) — Analysis focus: 'technical' (architecture, patterns), 'market' (adoption, competition), or 'sentiment' (community opinions). Default is 'technical'. **Returns:** Returns a synthesis object with summary, key_findings array, sentiment, trends, and recommendations, plus a raw_results object with per-source hits; in the sample, 12 of 14 sources succeeded yielding 43 total results. **Example:** `{"query": "AI agent frameworks", "per_page": 5, "focus": "technical"}` --- ### `search-stackoverflow-questions` **StackScout – Stack Overflow Search** — Searches Stack Overflow (or any StackExchange site) by keyword and returns questions with scores, answer counts, view counts, tags, and author metadata. *Use when:* Use when an agent needs to find existing Stack Overflow Q&A threads relevant to a programming problem, error message, or technical concept, and requires structured metadata like vote scores, answer counts, and tags to rank or filter results. *Not for:* Do not use for real-time code execution, fetching full answer body text, or searching non-StackExchange sources; use a general web search or code-execution API instead. **Inputs:** - `q` (string, required) — Search query string to match against Stack Overflow questions. - `per_page` (integer) — Number of results to return per page. Minimum 1, maximum 50. Defaults to 10. - `sort` (string) — Sort order for results. One of: relevance, votes, activity, creation. Defaults to relevance. - `site` (string) — StackExchange site to search. Defaults to stackoverflow. **Returns:** Returns success=true with a data array of up to 50 question objects each containing id, title, url, score, answers, views, is_answered, tags, author, author_reputation, and date, plus source, query, count, and elapsed_ms fields. **Example:** `GET https://scout-dx.hugen.tokyo/scout/stackoverflow?q=async+await&per_page=10&sort=votes&site=stackoverflow` --- ### `search-x402-bazaar` **Scout X402 Bazaar Search** — Searches the x402 Bazaar CDP Discovery directory for AI-agent APIs with micropayment access, returning resource URLs, prices, networks, and relevance scores. *Use when:* Use when an agent needs to discover x402-enabled HTTP APIs by keyword — for example, to find paid endpoints for weather, search, browser automation, or blockchain tools available on Base or Solana. *Not for:* Do not use to call or invoke a discovered API; this skill only returns metadata about available x402 resources. Do not use for real-time price feeds or token swaps. **Inputs:** - `q` (string, required) — Search query matched against API URL and description in the x402 Bazaar directory. - `per_page` (integer) — Number of results to return, between 1 and 50. Defaults to 10. **Returns:** Returns success=true with a data array of up to 10 x402 API entries (resource URL, description, price, network, relevance_score), plus source, query, count, and elapsed_ms fields. **Example:** `GET https://scout-dx.hugen.tokyo/scout/x402?q=browser&per_page=10` --- ### `search-devto-articles` **Dev.to Article Search** — Searches Dev.to (Forem) for technical articles and blog posts, returning title, description, author, reactions, comments, reading time, tags, and publication date. *Use when:* Use when an agent needs to find technical blog posts or community articles on Dev.to matching a keyword or topic, and requires engagement metrics (reactions, comments) and metadata to evaluate relevance. *Not for:* Do not use for real-time news or general web search; use a news or web search API instead. Not suitable for fetching a specific article by ID or URL. **Inputs:** - `q` (string, required) — Search query string to match against Dev.to articles. - `per_page` (integer) — Number of results to return per page. Minimum 1, maximum 30, default 10. - `sort` (string) — Sort order for results. One of: relevance, latest, top. Defaults to relevance. **Returns:** Returns success=true and a data array of up to 30 article objects, each with id, title, description, URL, author name/username, reaction count, comment count, reading time in minutes, tags, and publication date. **Example:** `GET https://scout-dx.hugen.tokyo/scout/devto?q=typescript&per_page=5&sort=top` --- ### `search-lobsters` **Lobsters Scout API** — Searches Lobste.rs, a curated tech link aggregator, and returns matching stories with scores, comment counts, authors, tags, and timestamps. *Use when:* Use when the user or agent needs curated tech news or discussion links from Lobste.rs matching a keyword or topic, optionally sorted by hotness or recency. *Not for:* Do not use for broad web search or Hacker News results; use a general search or HN-specific API instead. Not suitable for real-time streaming feeds — this is a single paginated query. **Inputs:** - `q` (string, required) — Search query string to match against Lobste.rs stories. - `per_page` (integer) — Number of results to return per page. Minimum 1, maximum 25, default 10. - `sort` (string) — Sort order for results. Accepted values: 'hot' (default) or 'newest'. **Returns:** Returns success=true with a data array of up to 25 Lobste.rs stories (id, title, url, lobsters_url, score, comments, author, tags, date), plus source, query, count, and elapsed_ms metadata. **Example:** `GET https://scout-dx.hugen.tokyo/scout/lobsters?q=rust&per_page=10&sort=hot` --- ### `search-pypi-packages` **PyPI Scout** — Looks up Python packages on PyPI by name, trying hyphenated, underscored, and py-prefixed variants, and returns version, summary, license, author, and links. *Use when:* Use when an agent needs to resolve a Python package name to its PyPI metadata — version, license, homepage, repository, author, Python requirements, or release history. *Not for:* Do not use for searching npm, RubyGems, or other package registries. Not suitable for bulk dependency audits across many packages — each call costs $0.005 and covers one query. **Inputs:** - `q` (string, required) — Package name or approximate name to look up on PyPI. The API tries hyphenated, underscored, and py-prefixed variants automatically. - `per_page` (integer) — Number of results to return, between 1 and 20. Defaults to 5. **Returns:** Returns success=true with a data array of package objects each containing name, version, summary, license, author, pypi_url, homepage, requires_python, release_count, and latest_upload, plus source, count, and elapsed_ms. **Example:** `GET https://scout-dx.hugen.tokyo/scout/pypi?q=fastapi&per_page=5` ---