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 agentmods add skills/mindspore-ai/akg/dev-insight-extractornpx skills add mindspore-ai/akg --skill dev-insight-extractorgit clone --depth 1 https://github.com/mindspore-ai/akgWrote 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/mindspore-ai/akg/dev-insight-extractor)<a href="https://agentmods.dev/skills/mindspore-ai/akg/dev-insight-extractor"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/dev-insight-extractor.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.04328 |
| Opus 5 | $0.00046 | $0.02164 |
| Sonnet 5 | $0.00018 | $0.00866 |
| Haiku 4.5 | $0.00009 | $0.00433 |
Grade A, and why
dev-insight-extractor 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 6d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
算子优化经验提取
前提
- 输入格式为 Cursor 的 agent-transcripts JSONL（
.jsonl文件） - 需要 Python 3.8+ 环境（预处理脚本仅用标准库）
- 对话记录中看不到 Agent 写的代码（工具调用内容未被记录），你只能从用户建议和 Agent 文本回复中提取方法论和代码片段
关键约束（必须遵守，违反则结果无效）
| # | 约束 | 说明 |
|---|---|---|
| C1 | 逐窗口处理 | 每次只读取 1 个 window JSON，分析完并写入 insights_{i}.json 后才能读取下一个。严禁一次性读取多个窗口。 |
| C2 | 逐窗口写入检查点 | 每个窗口必须写入 insights_{i}.json 后才能处理下一个窗口。不得跳过。 |
| C3 | 输出路径固定 | 最终 SKILL.md 写入 ~/.akg/evolved_skills/{dsl_key}/evolved-improvement/{skill_name}/SKILL.md。不得写入 .opencode/skills/ 或其他位置。 |
| C4 | 按算子特性分组 | 经验按算子特性大类 + 问题子类型二级分组。大类：elemwise（逐元素）、reduction（归约）、matmul（矩阵乘）、attention（注意力机制）。子类型描述问题特征（如 broadcast、large-reduce、fused-elemwise）。skill_name 格式为 op-insight-{category}-{subtype}，如 op-insight-elemwise-broadcast、op-insight-reduction-large-reduce。一个 skill 包含该子类型下的所有优化手段。 |
| C5 | 泛化要求 | 正文和 description 中禁止出现具体算子名（softmax、relu、layernorm、gelu 等）和具体 shape，必须用问题类别（如"逐元素类算子"、"归约类算子"）替代。可附关键代码片段来说明做法。 |
| C6 | 写入前必须检查冲突 | 写入任何 SKILL.md 之前，必须先检查目标路径是否已存在同名文件。如果已存在，执行合并逻辑（读取旧文件 → 合并经验 → 去重 → 更新 version），严禁直接覆盖。 |
Step 1: 确认输入
情况 A：用户已提供文件路径 → 确认文件存在，跳到 Step 2。
情况 B：用户未提供文件路径 → 自行定位 Cursor 的 agent-transcripts 目录，然后调用脚本展示预览。
**第一步：定位 agent-transcripts 目录
Windows: %USERPROFILE%\.cursor\projects\
Linux/Mac: ~/.cursor/projects/
遍历该目录下所有子目录，查找含 agent-transcripts/ 的项目。
第二步：调用脚本提取预览
python @scripts/list_transcripts.py <agent-transcripts目录路径> --top 5
脚本接受 agent-transcripts 目录路径作为参数，扫描其中的 JSONL 文件，按修改时间倒序列出每个对话的首条和末条用户消息预览。输出示例：
目录: /path/to/agent-transcripts
共 5 条对话（按时间倒序）：
[1] 03-25 15:13 109KB 首: "请你根据这个方案写一个详细的文档..."
末: "帮我改成按算子特性分组..."
路径: /path/to/.../89533e8d....jsonl
[2] 03-24 14:39 30KB 首: "给我分析一下当前仓库..."
路径: /path/to/.../751ea849....jsonl
What ships with it
4 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.
- 6d ago First seen · 366 lines · 91 tokens per session scan A 55a90f5a3b89
dev-insight-extractor is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 26d ago), licensed Apache-2.0. It adds 91 tokens to every session and 4,328 once invoked, about $0.0005 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…