helloworldtang/wei-ailang SkillScore 68 Maintained 按「AI浪」调性写作——人工智能与智能体方向,快节奏口语化的技术讲解。当用户要写 AI 底层原理(大模型/注意力/幻觉)、工程实践(RAG/Agent 设计)、bug 排查、前沿技术(新模型/新框架)、工具对比(LangChain/LlamaIndex)等主题时使用。不适合纯后端/架构(→wei-danxin)、生活省钱(→wei-mingdeng)。
by helloworldtang
Use this skill Links this skill to your agents and keeps it current with the author’s updates.
On-demand On-demand: invoked explicitly — never occupies your agent's context until called.
◆ Marketing & Content pack
$ decimalai skills pull helloworldtang-wei-ailangCopy
Copy link Copy README badge Copy SKILL.md Get this skill — curl · raw file $ curl -fsSL https://app.decimal.ai/s/helloworldtang-wei-ailang/SKILL.mdCopy
how this skill behaves on real traffic · last 30 days
No production data for this skill yet — usage numbers appear here once agents start running it.
Anonymized aggregate across every org using this skill — proof from real production use, not a demo. Sign in and install to see your own agents here →
Does this skill help? · Benchmark: with vs. without sign in to run this on your agents 22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago
Yes — +41% lift +19% tokens 0% turns 68% of whole cases pass with skill (15/22)
Showing 5 of 22 cases See all cases & grading →
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported Imported 8/1/2026Version v1
Contents Benchmark Live Traces Versions (1) Ratings (0)
AI浪 定位 专注 AI 与智能体领域的知识分享,已认证科技自媒体。读者是对 AI 底层原理、工程实践、前沿技术感兴趣的人。
结构骨架(快节奏,按此顺序) 开头 :痛点场景或热点速览问题放大 :为什么大多数人做法是错的 / 行业现状解决方案 :≤3 个要点,每个配具体工具 / 参数代码示例 :核心代码片段(不堆砌,完整代码放 GitHub)结尾 :行动引导 + GitHub 链接必备元素 + 完成标准(每条可核验) ] 含具体工具名 / 参数 / 命令(非泛泛"用某个模型")→ 检查是否出现可复现的参数 ] 核心代码展示(非完整类/配置)→ 代码块是片段 ] 有代码则附 GitHub 链接 ] 字数 1500-2500 → wc -m 落在区间 ] 代码块无嵌套、标识完整、前后空行 ] 禁用词命中 = 0(扫 ../references/writing-standards.md 禁用词表) 代码规则(Less is more) ✅ 展示:核心逻辑、关键 API、简化示例 ❌ 不展示:完整类、完整配置、训练脚本 禁止代码块嵌套;代码块内不放纯文本(用 > 引用块) 写作执行 语气 :像一个懂技术的朋友在聊天——快节奏、口语化、带情绪,不是念 PPT人称 :第三人称技术讲解,偶尔穿插第一人称"我用过"素材锚定 :每个 H2 ≥1 条真实素材(官方文档 / 论文 / 实测数据 / 社区反馈),不编造反 AI 规范 + 自检清单 :见 ../references/writing-standards.md查重(写前必做) :见 ../references/dedup-rules.md选题边界 适合 :AI 底层原理、工程实践、bug 排查、前沿技术、工具框架对比不适合 :后端/架构/数据库 → wei-danxin;生活省钱/职场非技术 → wei-mingdengWant to see if helloworldtang/wei-ailang would activate on your phrasing? Try it before you install — no LLM call, no signup. Try this skill →