CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hn-summarize

Fetch and summarize Hacker News / hckrnews.com top stories, articles, and their comment threads. Use when asked to summarize HN front-page stories, a specific HN story plus its discussion, or "the top N from hckrnews".

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body: every code block is runnable, the critical gotchas (don't scrape the JS site, Algolia points are null, dedupe old headlines with numericFilters) are surfaced concisely, and fallbacks for paywalled or blocked articles are provided. The main improvement would be a complete executable snippet for extracting readable article text and light response validation.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it opens with the one non-obvious fact (hckrnews.com is JS-rendered, "do not scrape it") and then delivers runnable commands with terse, high-value notes ("Algolia's per-comment points field is now always null"). No padding or explanations of concepts Claude already knows — matches anchor 5.

5 / 5

Actionability

Sections 1-3 are copy-paste ready with real URLs and complete pipelines, and section 4's Wayback lookup is executable. It falls short of anchor 5 because the article-text extraction itself is loosely assembled ("strip tags with sed ... or grep for the key sentences") rather than a complete example, leaving a minor gap for one of the skill's core outputs.

4 / 5

Workflow Clarity

The numbered sections form a coherent sequence (top stories -> find story -> comment tree -> article -> summary format) with decision points ("Pick the objectID with the highest points/comments") and an error-recovery path (paywalled/JS-heavy -> Wayback; blocked host -> proxy). No validation of API responses is included (e.g., empty hits or missing 'text' fields), which keeps it at anchor 4 rather than 5, though the read-only nature of the task means the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

This is a compact, single-purpose skill (~75 lines) with clear section headers and no bundle files; all content is appropriately inlined since splitting it out would add navigation cost without benefit. Under the simple-skill guidance, well-organized sections with no external references warrant anchor 5; there is no content that clearly belongs in a separate file.

5 / 5

Total

18

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities in third person, covers natural trigger phrasings including synonyms (HN, Hacker News, hckrnews), and explicitly answers both what it does and when to use it. The only room for improvement is enumerating the sub-actions (fetch stories, search, pull comment trees, summarize linked articles) more granularly.

DimensionReasoningScore

Specificity

Concrete actions are stated — "Fetch and summarize" — applied to specific objects ("top stories, articles, and their comment threads"), with minor gaps in coverage (e.g., summarizing linked articles is implied rather than broken out). It sits above anchor 3 (only 1-2 actions, not comprehensive) because the enumerated targets give broad scope, but below anchor 5 (multiple distinct concrete actions, fully comprehensive) since only two verbs carry the whole description.

4 / 5

Completeness

Both what ("Fetch and summarize Hacker News ... top stories, articles, and their comment threads") and when ("Use when asked to summarize HN front-page stories, a specific HN story plus its discussion, or 'the top N from hckrnews'") are explicitly stated with concrete trigger phrases. This matches anchor 5; anchor 4 would require the 'when' clause to be less explicit or specific.

5 / 5

Trigger Term Quality

Natural terms users would say are well covered: "Hacker News", "HN", "hckrnews.com", "front-page stories", "summarize", and "the top N from hckrnews" — including synonyms (HN / Hacker News / hckrnews). This matches anchor 5's comprehensive synonym coverage; anchor 4 would require missing common variations, which is not the case here.

5 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (HN/hckrnews summarization) with distinct, unambiguous triggers that no general-purpose or file-format skill would claim. Minimal conflict risk; matches anchor 5 rather than anchor 4 (minor overlap with closely related skills), as no plausible competing skill shares these triggers.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ykdojo/claude-code-tips

Path

skills/hn-summarize/SKILL.md

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.