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 anneheartrecord/charles-skill --skill x-hotspot-radargit clone --depth 1 https://github.com/anneheartrecord/charles-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/anneheartrecord/charles-skill/x-hotspot-radar)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/x-hotspot-radar"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/x-hotspot-radar/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/anneheartrecord/charles-skill/x-hotspot-radar"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/x-hotspot-radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00216 | $0.01740 |
| Opus 5 | $0.00108 | $0.00870 |
| Sonnet 5 | $0.00043 | $0.00348 |
| Haiku 4.5 | $0.00022 | $0.00174 |
Grade A, and why
x-hotspot-radar 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X 热点雷达(热点 → 落地推文)
把「今天有什么值得蹭的热点」变成一条符合用户文风、去过 AI 味、配好图、可直接发布的推文草稿。
本 skill 只做编排:热点扫描 + 五重过滤 + 流程串联。文风、去 AI 味、配图、发布都调用下面列出的已有系统,严禁在本 skill 里重新发明这些环节。
依赖的已有系统(糊在流水线上)
| 环节 | 调用什么 | 位置 |
|---|---|---|
| 文风(所有写作) | 写作系统三件套 + 镇库范文 | ~/.agent-harness/writing/writing-style*.md |
| 开头诊断 | dbs-hook |
已装 skill |
| 发布前共鸣诊断 | dbs-resonate |
已装 skill |
| 去 AI 味 | de-ai-flavor(观点文走 A-E) |
已装 skill |
| 正文配图 | ian-xiaohei-illustrations(观点/隐喻)、guizang-material-illustration(机制/数据图) |
已装 skill |
| 封面 | cover-image |
已装 skill |
| 发布 | 同仓 x-post(dry-run + 确认) |
同仓 skill |
账号定位(过滤热点的基准,可被用户运营手册覆盖)
用户 @Charles77xixi 的稀缺交叉地带:真写代码、真用 Agent、真拿钱在市场交过学费。三个反复问题(选题只服务这三条):AI 真落地、钱真打理、路真自己选。不做纯 AI 工具搬运、纯新闻评论、MBTI/情绪流水账(历史数据验证这些 0 涨粉)。若用户运营目录有 账号运营手册.md/选题库.md,以其为准。
工作流程
第 1 步:扫热点
按账号定位分领域扫,来源:
python3 <skill目录>/scripts/scan_hotspots.py --topics ai,investing,career
脚本用给定关键词生成一批 WebSearch/WebFetch 查询建议(HN、各大 AI 厂商发布、GitHub Trending、财经要闻)。agent 拿建议后实际执行 WebSearch/WebFetch 抓当天热点。可选:配了 cookie(X_AUTH_TOKEN/X_CT0)时,用同仓 x-content-review/scripts/fetch_x_pulse.py --user <对标账号> --profile 看对标账号最近在讲什么。
也支持用户直接丢链接/截图进来,跳过扫描。
第 2 步:五重过滤(排掉不值得做的)
对每个候选热点过五关,任一不过就淘汰:
- 相关性:落在三个反复问题(AI 落地/钱/路)里吗?蹭不上定位的再热也不做。
- 稀缺角度:用户有没有别人没有的一手视角(真实代码/真实持仓/真实踩坑)?只有转述没有增量 → 淘汰(历史数据:纯新闻评论 0 涨粉)。
- 时效:热点还在窗口内吗?过气的不做。
- 信任增益:发出来能不能让人更信用户(露出判断/证据)?纯蹭流量不增信 → 降级。
- 可持续:能不能接到已有系列、沉淀成资产?一次性消耗 → 降级。
输出候选热点表:热点 + 过滤结论 + 推荐做/不做。
第 3 步:出角度和结构提纲,等用户拍板(硬性分步)
按全局写作规范三步走的第一步:给 2-3 个角度选项 + 每个的编号结构提纲。停下等用户选,不直接铺全文(除非用户说「直接出全文」)。
第 4 步:写开头段落做风格校准,等用户反馈
先读写作系统三件套,按用户文风写开头段(具体场景/一笔账/一次真实取舍切入,绝不抽象开场)。用 dbs-hook 自检开头。停下等用户反馈。
第 5 步:铺全文
按镇库范文的编号说理骨架铺全文(短推是压缩版):具体开场 + 反共识判断 + emoji 编号观点 + 每节落判断 + 极致具体 + 坦诚暴露。守写作系统硬禁忌(不用引号强调、不用破折号、连接词胶水≤1、结尾不用反问钩子)。
第 6 步:去 AI 味
走 de-ai-flavor(观点文按 A-E 五条强制动作)。这一步不可省——热点稿最容易带 AI 味。
第 7 步:配图(可选,用户要就做)
- 观点/隐喻类插图 →
ian-xiaohei-illustrations - 机制/概念拆解/数据图 →
guizang-material-illustration - 需要封面(thread 首图)→
cover-image(文案走好奇/共鸣钩子,不塞关键词)
What ships with it
3 files 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.
- 11d ago First seen · 95 lines · 216 tokens per session scan A 3cfecb23f14d
x-hotspot-radar is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 216 tokens to every session and 1,740 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.