CtrlK
BlogDocsLog inGet started
Tessl Logo

aihot

查询 AIHOT 的中文 AI 资讯、精选、当前热点和日报。用户询问今天或最近的 AI 新闻、AI 圈动态、大模型或产品发布、OpenAI/Anthropic/Google 最新消息、AI 论文、AI 日报、AIHOT 精选、当前最热事件,或需要同步当前全部精选时使用。必须通过 aihot.virxact.com 的匿名只读 API 获取当前数据,不凭训练记忆回答新闻;不需要 API Key 或 MCP server。

76

Quality

96%

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

92%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 well-engineered routing skill body: concrete request paths, a clear sequenced workflow with explicit fallbacks, and clean one-level-deep references to real bundle files. The only weakness is minor — several rationale sentences justify rules rather than state them, adding modest length beyond strict actionability.

Suggestions

Tighten the rationale sentences in the routing rules (e.g. the 'why' behind the empty-selected→all fallback and the /latest caching caveat) to state the rule and leave the justification to references/api.md.

Consider moving the detailed 72-hour timeline/narrowing algorithm (lines 54, 60) fully into references/api.md since it is already duplicated there, keeping SKILL.md to the routing decision.

DimensionReasoningScore

Conciseness

Dense, assumes Claude's competence (no explanations of APIs/JSON/news concepts), and almost every line is an actionable routing rule; a few multi-sentence rationale blocks (e.g. the empty-selected→all fallback justification and the /latest caching caveat) explain why rather than just what and could be trimmed slightly.

4 / 5

Actionability

Provides copy-paste-ready request paths in the intent→request routing table (e.g. `/api/v1/items?mode=selected&window=24h&limit=10`), exact parameter contracts, and a concrete markdown output template covering the common briefing case.

5 / 5

Workflow Clarity

The five-step core workflow is clearly sequenced, with explicit feedback loops (empty selected→retry `mode=all`, ETag/304 reuse, cursor-error handling) and a defined error-degradation path via references/errors.md; the read-only nature means the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

The body is a focused overview that defers full parameter/field/pagination detail to references/api.md, error handling to references/errors.md, and the sync state machine to references/sync.md — all real one-level-deep files, clearly signaled with markdown links at the points they are needed.

5 / 5

Total

19

/

20

Passed

Description

100%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 high-quality third-person description that pairs concrete data-retrieval actions with an exhaustive set of natural Chinese trigger phrases and an explicit use-when clause. It cleanly separates what the skill does from when to invoke it and is anchored to a distinct branded data source.

DimensionReasoningScore

Specificity

Lists multiple concrete retrieval actions across the full data surface — 「查询...资讯、精选、当前热点和日报」and「同步当前全部精选」— with comprehensive coverage of every AIHOT data type rather than a single generic verb.

5 / 5

Completeness

Explicitly answers both what (query AIHOT Chinese AI news/selected/hot-topics/dailies via anonymous read-only API, not training memory) and when (「用户询问...时使用」) with concrete trigger phrases; also notes no API Key/MCP needed.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and named entities a user would actually say: 「今天或最近的 AI 新闻」「AI 圈动态」「大模型或产品发布」「OpenAI/Anthropic/Google 最新消息」「AI 论文」「AI 日报」「当前最热事件」.

5 / 5

Distinctiveness Conflict Risk

Tightly bound to the AIHOT brand and its specific data products, with triggers tied to named sources (OpenAI/Anthropic/Google) and AIHOT-specific concepts (精选, 日报, hot-topics), giving a clear niche with minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
KKKKhazix/khazix-skills
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.