Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add FTShare-Lab/FTShare-skill --skill semantic-search-newsgit clone --depth 1 https://github.com/FTShare-Lab/FTShare-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ftshare-lab/ftshare-skill/semantic-search-news)<a href="https://agentmods.dev/skills/ftshare-lab/ftshare-skill/semantic-search-news"><img src="https://agentmods.dev/badge/skills/ftshare-lab/ftshare-skill/semantic-search-news/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ftshare-lab/ftshare-skill/semantic-search-news"><img src="https://agentmods.dev/badge/skills/ftshare-lab/ftshare-skill/semantic-search-news.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01303 |
| Opus 5 | $0.00020 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
semantic-search-news scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
语义搜索新闻
1. 接口描述
| 项目 | 说明 |
|---|---|
| 接口名称 | 语义搜索新闻 |
| 外部接口 | GET /api/v3/market/data/semantic-search-news |
| 请求方式 | GET |
| 适用场景 | 根据搜索文字进行语义搜索，返回相关新闻列表；数据仅支持查询当年、最近半个月内的新闻 |
2. 请求参数
| 参数名 | 类型 | 是否必填 | 描述 | 取值示例 | 备注 |
|---|---|---|---|---|---|
| query | string | 是 | 搜索文字 | 人工智能 | - |
| limit | int | 否 | 返回条数 | 10 | 默认 10 |
| year | int | 否 | 年份 | 2026 | 仅支持当年；数据仅保留最近半个月，用于限定搜索范围 |
| start_time | string | 否 | 开始时间（含） | 2026-03-01T00:00:00+08:00 | ISO 8601 格式，用于限定搜索时间范围；无时区时按东八区解释 |
| end_time | string | 否 | 结束时间（含） | 2026-03-15T23:59:59+08:00 | ISO 8601 格式，用于限定搜索时间范围；无时区时按东八区解释 |
3. 响应说明
返回 SearchResult 数组，按相关度排序。
[
{
"news_id": 556106924001595392,
"source_site": "21经济网_要闻",
"article_url": "https://...",
"publish_time": "2026-03-15T21:00:00",
"fetch_time": "2026-03-15T21:19:49",
"title": "越是AI，越需人文",
"media_name": "21世纪经济",
"summary": null,
"content": "...",
"is_truncated": 0,
"is_reviewed": 1,
"score": 0.6933832764625549
}
]
SearchResult 结构
| 字段名 | 类型 | 是否可为空 | 说明 |
|---|---|---|---|
| news_id | long | 否 | 新闻 ID |
| source_site | string | 否 | 来源站点 |
| article_url | string | 是 | 文章链接 |
| publish_time | string | 是 | 发布时间，ISO 8601 格式 |
| fetch_time | string | 否 | 抓取时间，ISO 8601 格式 |
| title | string | 是 | 标题 |
| media_name | string | 是 | 媒体名称 |
| summary | string | 是 | 摘要 |
| content | string | 否 | 正文内容 |
| is_truncated | int | 否 | 是否被截断：0=否 1=是 |
| is_reviewed | int | 否 | 是否已审核：0=否 1=是 |
| score | float | 否 | 搜索匹配分数 |
4. 用法
通过主目录 run.py 调用（必填 --query，可选 --limit、--year、--start_time、--end_time）：
python <RUN_PY> semantic-search-news --query 人工智能
python <RUN_PY> semantic-search-news --query 人工智能 --limit 10 --year 2026
python <RUN_PY> semantic-search-news --query 人工智能 --limit 10 --year 2026 --start_time 2026-03-01T00:00:00+08:00 --end_time 2026-03-15T23:59:59+08:00
<RUN_PY> 为主 SKILL.md 同级的 run.py 绝对路径。脚本输出 JSON；本接口无需额外请求头。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 99 lines · 40 tokens per session scan A b19b099d1489
semantic-search-news is a skill published in the GitHub repository FTShare-Lab/FTShare-skill (63 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,303 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
defeatbeta-earnings-analysis
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on beat/miss analysis, key metrics, updated estimates, and revised thesis. Includes 1-3 summary tables and 8-12 charts. Use when…
ci-cd-pipeline
Design and implement CI/CD pipelines for automated testing and deployment.
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
obsidian
Obsidian vault management — create notes, backlinks, tags, and Dataview queries via file operations.
code-review
Systematic code review SOP covering correctness, security, performance, and maintainability — plus GitHub PR review workflow (diff, inline comments, approve via gh/REST).
debugging
Systematic bug investigation process — reproduce, isolate, root cause, fix, verify.