Borrowing it
Nothing to install: this file belongs to puppylpg/puppylpg.github.io. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/puppylpg/puppylpg.github.io/master/.agents/skills/ai-trends-report/SKILL.mdgit clone --depth 1 https://github.com/puppylpg/puppylpg.github.ioWrote 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/puppylpg/puppylpg.github.io/ai-trends-report)<a href="https://agentmods.dev/skills/puppylpg/puppylpg.github.io/ai-trends-report"><img src="https://agentmods.dev/badge/skills/puppylpg/puppylpg.github.io/ai-trends-report/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/puppylpg/puppylpg.github.io/ai-trends-report"><img src="https://agentmods.dev/badge/skills/puppylpg/puppylpg.github.io/ai-trends-report.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 | $0.00121 | $0.03235 |
| Opus 5 | $0.00060 | $0.01618 |
| Sonnet 5 | $0.00024 | $0.00647 |
| Haiku 4.5 | $0.00012 | $0.00324 |
Grade A, and why
ai-trends-report scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
确认站点启动，并用 `curl --noproxy '*' -fsS "http://127.0.0.1:4000${ARTICLE_URL}"` 验证目标页面可访问，避免本机 HTTP/SOCKS 代理错误接管 localhost。若当前执行环境会在脚本退出时回收后台进程，则改为在持久终端会话中前台运行 `bundle exec jekyll serve --host 0.0.0.0 --port 4000 --livereload` How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Trends 博客报告
把来源页面的当前数据快照生成项目内 _ai/ 博客文章。不要沿用旧报告的图表数量、模型排名、数字或结论。
默认行为
- 默认来源：
https://llm-stats.com/ai-trends；仅当用户明确给出新网址时替换。 - 正式产物只有 Jekyll Markdown 和站内 PNG 图表，不生成 PDF 或独立 HTML。
- 默认目标为
_ai/，分类为[ai, trends]。 - 用户明确要求发布到 Tech 时，目标改为
_posts/，分类为[tech, trends]，构建命令增加--target tech。 - 生成文章并完成本地预览后等待用户确认。未经再次明确授权，不执行
git commit或git push。 - 全程遵循项目根目录
AGENTS.md，尤其是文章同步、frontmatter、预览、发布和清理要求。
文章硬性要求
- 先给结论和理由：正文第一个一级标题必须是“整体趋势总结”。每条趋势判断紧跟“判断依据”，用跨图数字或对比说明为什么得到这个结论；不要把总结放到文章末尾。
- 方法与局限前置：在整体总结和逐期差异之后写“方法与局限”，交代时间快照、数据口径、相关与因果、来源边界，再进入读图方法和单图正文。
- 逐期差异单列并前置：若存在上一期报告，在“整体趋势总结”之后、“方法与局限”之前写“与上一期相比”一级章节。明确对比基线，分别说明可核对的数值变化、图表增删和指标口径切换；不可直接比较的指标不得硬算升降。
- 术语附英文全称：术语表不能只写中文或缩写；同时给出可核对的英文全称，例如
GPQA（Graduate-Level Google-Proof Q&A Benchmark）。 - 每组先写小结：每个来源 section 的中文标题下立即给出“本组结论”，先概括整组共同趋势，再介绍组内各图。
- 每图列关键点：每张图除了“怎么看”和“图表显示”，还必须列 1–6 条“关键模型 / 数据点”，通常精选 2–4 条模型名与精确 metric；聚合图则列国家、组织、时间、门槛或相关系数等可直接核对的数据。
- 只写可核对数值：优先使用 tooltip 抓取值；没有 tooltip 时只能引用 SVG、PNG、图卡或来源正文中的明确标注，不得根据点位位置猜模型名或伪造精确值。
1. 准备仓库和运行时
先定位路径并同步远端。同步失败或出现 rebase 冲突时停止，不要继续写文章。
REPO_ROOT="$(git rev-parse --show-toplevel)"
SKILL_DIR="$REPO_ROOT/.agents/skills/ai-trends-report"
cd "$REPO_ROOT"
git pull --rebase --autostash
调用工作区依赖工具取得 bundled Node.js、Node modules 和 Python 的绝对路径，设置：
SOURCE_URL="https://llm-stats.com/ai-trends"
NODE="<bundled-node>"
NODE_PATH="<bundled-node-modules>"
PYTHON="<bundled-python>"
RUN_DIR="$(mktemp -d "${TMPDIR:-/tmp}/ai-trends-report.XXXXXX")"
用户给出新网址时只替换 SOURCE_URL。RUN_DIR 是未提交的临时证据目录；任务失败时保留路径供诊断，发布或放弃后删除。
2. 抓取全部动态图表
运行：
NODE_PATH="$NODE_PATH" PW_TEST_SCREENSHOT_NO_FONTS_READY=1 "$NODE" \
"$SKILL_DIR/scripts/capture_charts.mjs" \
--url "$SOURCE_URL" \
--output-dir "$RUN_DIR"
脚本通过连续两次一致的有序扫描判断页面稳定，不依赖固定图表数量。抓取失败时检查：
$RUN_DIR/data/capture-diagnostics.json- 浏览器控制台错误
- 失败的 API 或
_next/static/chunks请求
扫描未稳定、页面仍有 Loading、图片缺失或图表为空时，不得继续生成文章。
随后抓取散点、折线和柱状图的交互 tooltip，作为具体模型与指标值的补充证据：
What ships with it
7 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.
- agents/openai.yaml 283 B
- references/interpretation-guidelines.md 6.1 KB
- scripts/build_blog_post.py 16 KB runs code
- scripts/capture_charts.mjs 8.6 KB runs code
- scripts/enrich_chart_points.mjs 4.7 KB runs code
- scripts/prepare_interpretations.py 3.3 KB runs code
- scripts/validate_blog_post.py 11 KB runs code
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.
- 9d ago First seen · 191 lines · 121 tokens per session scan A dea293d5c8a2
ai-trends-report is a skill published in the GitHub repository puppylpg/puppylpg.github.io (2 stars, last pushed 5d ago), licensed MIT. It adds 121 tokens to every session and 3,235 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…