hackernews-frontpage
Scrape the Hacker News front page (titles, points, comment counts).
33
28%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./browser-skills/hackernews-frontpage/SKILL.mdQuality
Discovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is highly specific about what it does—scraping Hacker News front page data including titles, points, and comment counts—and occupies a clear niche. However, it completely lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. Adding trigger guidance and common user phrasings would significantly improve its effectiveness.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks about Hacker News, HN top stories, trending tech news, or wants to scrape news.ycombinator.com.'
Include common keyword variations such as 'HN', 'news.ycombinator.com', 'top stories', 'trending posts' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scrape, titles, points, comment counts, and names the specific source (Hacker News front page). | 3 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores at the lower end. | 1 / 3 |
Trigger Term Quality | Includes natural keywords like 'Hacker News', 'scrape', 'front page', 'titles', 'points', 'comment counts', but misses common variations like 'HN', 'top stories', 'news aggregator', or 'web scraping'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Hacker News front page scraping; unlikely to conflict with other skills due to the narrow, well-defined scope. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a README explaining what a tool does rather than teaching Claude how to scrape Hacker News. It lacks any executable code, concrete selectors, or actionable scraping instructions. The 'Why this is the reference skill' section is entirely meta-commentary that wastes tokens without helping Claude perform the task.
Suggestions
Add executable scraping code with concrete CSS selectors (e.g., `tr.athing`, `.score`, `.subtext a:last-child`) so Claude can actually perform the scraping task.
Remove the 'Why this is the reference skill' section entirely—it's meta-context about project architecture that doesn't help Claude scrape HN.
Transform 'How it works' from a description of tool behavior into actionable steps Claude should follow, including error handling for missing fields or changed HTML structure.
Add a concrete example of the expected JSON output schema and include validation steps (e.g., verify count equals 30, check for null URLs).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes significant unnecessary explanation: 'Why this is the reference skill' section explains meta-context Claude doesn't need, 'How it works' restates what the code does conceptually without adding actionable value, and phrases like 'smallest interesting browser-skill' are padding. The description of HN's HTML structure and test philosophy wastes tokens. | 1 / 3 |
Actionability | There is no executable code, no concrete scraping logic, no selectors, no parsing code, and no actual implementation. The skill describes what happens at a high level ('parses each story row') but provides zero copy-paste-ready code or commands beyond a CLI invocation stub with placeholder output. | 1 / 3 |
Workflow Clarity | The 'How it works' section lists 4 steps but they are descriptive rather than instructional—they describe what the tool does, not what Claude should do. There are no validation checkpoints, no error handling guidance, and no feedback loops for when selectors break (despite acknowledging this risk). | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections (Usage, How it works, Why this is the reference skill), which provides some structure. However, it references `script.test.ts` and bundle components without providing them or linking to them, and there are no bundle files to support the references. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- garrytan/gstack
- Commit
070722a
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.