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 chengkj99/kj-skills --skill industry-best-practicesgit clone --depth 1 https://github.com/chengkj99/kj-skillsWrote 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/chengkj99/kj-skills/industry-best-practices)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/industry-best-practices"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/industry-best-practices/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/chengkj99/kj-skills/industry-best-practices"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/industry-best-practices.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 | $0.00178 | $0.03243 |
| Opus 5 | $0.00089 | $0.01622 |
| Sonnet 5 | $0.00036 | $0.00649 |
| Haiku 4.5 | $0.00018 | $0.00324 |
Grade A, and why
industry-best-practices 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 12d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
行业最佳实践 Skill
使命
把外部行业信号转成可执行决策。用户给出一个方向、概念、产品、能力、流程、技术方案、竞品或业务问题后，系统性识别“业界已经验证过什么”，判断哪些是真趋势、哪些是噪音，并落到可复用的做法、适用边界、优化建议、MVP、指标和风险。
核心链路：
问题/目标
-> 外部信号
-> 证据判断
-> 范式/能力/用户变化
-> 对目标对象的影响
-> 优化建议
-> MVP 实验
-> 指标和风险
-> 行动计划
适用场景
使用本 skill 处理这些请求：
- 调研某个行业、产品方向、功能能力、技术方案或业务流程的最佳实践。
- 调研一个概念或技术的定义之外的内容：解决什么问题、成熟做法、常见架构、实施步骤、反模式、适用边界和验证指标。
- 了解最近有什么新范式、新理念、新架构、新论文、新开源项目或竞品动作。
- 把外部趋势转成产品优化建议、架构建议、流程建议、机会池或路线图。
- 为 PRD、方案评审、战略讨论、日报/周报、深度报告提供来源可靠的输入。
- 持续跟踪某个主题，并按天、周或月沉淀成可执行建议。
不要把本 skill 用成单纯资料列表。每个重要信号都必须转译成“对目标对象有什么影响，下一步怎么验证”。
不适用场景
以下情况不要使用本 skill，直接回答或改用更合适的方式：
- 只需要一句事实答案：某 API 参数、某工具用法、某概念定义；若用户问“这个概念/技术怎么正确落地、有哪些最佳实践或踩坑”，则使用本 skill。
- 方案已明确的实现任务：用户要的是写代码，不是调研。
- 用户只要链接或资料列表，且明确拒绝分析建议。
- 不限定主题的 AI 前沿泛日报（如本仓库场景应使用
ai-daily-websearch/ai-daily-from-x）；本 skill 的日报/周报必须绑定一个明确主题和优化对象。
选择调研深度
先根据用户意图选档，不要默认跑满完整流程：
| 档位 | 触发信号 | 来源族 | 输出 |
|---|---|---|---|
| 快速扫描 | “看一眼”“大概了解”“有什么新东西” | 2-3 个最相关来源族 | 结论先行 + 精简信号地图 + Top 3 建议 |
| 标准调研（默认） | “调研一下”“帮我看看最佳实践” | 4-6 个来源族 | 完整简报（assets/templates/research-brief.md） |
| 深度报告 | “系统性调研”“写一份报告”“做方案评审输入” | 全部 8 个来源族 | 深度报告（assets/templates/deep-research-report.md） |
不确定时选标准档，并在报告「范围和假设」中写明所选档位，方便用户要求加深。
概念/技术最佳实践模式
当主题是概念、方法、框架或技术（如 RAG、DDD、可观测性、事件驱动、零信任）时，默认仍选标准调研，但报告必须回答以下问题，不能退化成概念解释或热点罗列：
- 它解决的具体问题，以及不适用的问题。
- 至少 3 条可操作实践，每条包含“何时做、如何做、为什么、验证指标、失败边界”。
- 至少 2 个可核验的真实采用/工程案例（或官方/标准/高质量开源实现）；没有案例时明确写“证据不足”，不可把观点包装成最佳实践。
- 至少 2 个反模式或常见失败模式，以及替代做法。
- 一个按 1 周、1 个月、1 季度拆分的渐进式落地路径。
涉及技术方案时，优先覆盖官方文档/标准、生产工程实践、开源实现与评估资料；论文只用于解释方法或证明边界，不能单独替代生产实践。
工作流
1. 归一化任务
先从用户输入中提取：
research_target：要研究的主题。optimization_object：要优化的产品、能力、流程、系统或决策。domain：所属行业或技术域。user_context：目标用户、业务场景、已有约束。research_goal：找机会、写方案、做竞品、做路线图、做日报/周报等。time_window：默认最近 30 天；信息不足时扩展到 90 天；经典理论和标准可引用更早来源，但必须说明当前有效性。expected_output：默认输出“结论 + 信号地图 + 优化建议池 + MVP + 指标 + 风险 + 下一步”。constraints：成本、安全、合规、技术栈、组织条件、上线周期等。research_mode：industry_signal（默认）或concept_technical_practice。主题为概念、架构或技术方法时选择后者。
What ships with it
15 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 261 B
- assets/examples/invocations.md 1.7 KB
- assets/examples/sample-report.md 5.8 KB
- assets/templates/daily-digest.md 866 B
- assets/templates/deep-research-report.md 1.5 KB
- assets/templates/opportunity-backlog.md 444 B
- assets/templates/research-brief.md 2.4 KB
- references/daily-automation.md 1.5 KB
- references/evidence-and-scoring-rubric.md 8.9 KB
- references/output-contracts.md 2.0 KB
- references/search-query-playbook.md 3.4 KB
- references/signal-to-optimization-framework.md 2.8 KB
- references/source-map.md 5.1 KB
- scripts/score_signal.py 5.3 KB runs code
- scripts/validate_report.py 6.7 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.
- 12d ago First seen · 248 lines · 178 tokens per session scan A 370b34b18c00
industry-best-practices is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 178 tokens to every session and 3,243 once invoked, about $0.0009 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…