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/arcblock/agent-skills/interview-writernpx skills add ArcBlock/agent-skills --skill interview-writergit clone --depth 1 https://github.com/ArcBlock/agent-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/arcblock/agent-skills/interview-writer)<a href="https://agentmods.dev/skills/arcblock/agent-skills/interview-writer"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/interview-writer.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 | $0.00079 | $0.02254 |
| Opus 5 | $0.00039 | $0.01127 |
| Sonnet 5 | $0.00016 | $0.00451 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
interview-writer 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 4d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Writer
AI 采访式内容创作系统 - 通过结构化采访,生成符合用户风格的原创内容。
核心理念
- 不是自动写:AI 不会凭空生成内容
- 不是代写:不是简单记录用户说的话
- 是采访式创作:AI 分析 + 提问 + 用户回答 + AI 按风格整合
Resource Loading Policy
优先级顺序(用户配置覆盖默认):
- 用户自定义(如存在):
~/.claude/content-profile/ - 技能默认(作为 fallback):本技能的
references/目录
加载逻辑:
For each profile file (writing-style, opinions, thinking-patterns, domain-knowledge):
1. Check if ~/.claude/content-profile/{file}.md exists
2. If exists → use user's version
3. If not exists → use references/{file}.md from this skill
画像更新目标:
- 始终更新到
~/.claude/content-profile/ - 如该目录不存在,创建之
Workflow
Phase 1: 触发分析
接收内容触发(用户提供以下任一):
- 一篇文章/链接(需要评论或回应)
- 一个事件/话题(需要发表观点)
- 一个产品/技术(需要介绍或分析)
- 一个想法草稿(需要展开成文)
AI 分析步骤:
- 按 Resource Loading Policy 加载用户画像
- 读取
~/.claude/profile/下相关背景文件(如有必要) - 分析触发内容的核心议题
- 基于已有画像,预判用户可能的立场和角度
- 自动判断内容类型(不让用户选,AI 先判断最可能的类型)
内容类型自动识别:
| 触发内容特征 | 判断类型 | 输出组合 |
|---|---|---|
| 自己的产品/功能发布 | Release Blog | 博客 + 社交媒体 + 中英双语 |
| 需要媒体报道的重大事件 | Press Release | 新闻稿 + 社交媒体 + 中英双语 |
| 对他人文章/事件的评论 | Opinion/Commentary | 社交媒体为主,可选长文 |
| 技术实现/架构分享 | Engineering Blog | 博客 + 社交媒体 + 英文优先 |
| 行业趋势/洞察分析 | Insight Blog | 博客 + 社交媒体 + 中英双语 |
关键原则:文章、社交媒体、多语种不是选择关系,而是同时需要。一次性给出全面结果。
Phase 2: 采访问答
问题生成原则:
- 先用已积累的知识自动判断,避免重复问题
- 只问必要的、无法推断的问题
- 混合使用选择题(降低门槛)和开放式问题(获取深度)
问题类型:
1. 立场确认(选择题)
"关于 X 的观点,你更倾向于 A 还是 B?"
2. 角度挖掘(开放式)
"这件事最让你在意的是什么?"
3. 深度追问(基于回答)
"你提到 Y,能展开说说为什么?"
4. 风格确认(选择题)
"这篇内容的语气:A) 犀利批判 B) 冷静分析 C) 热情推荐"
5. 故事/案例询问(根据文章类型)
**Founder 观点类**:
- 先总结 2-3 类最适合的故事方向(基于论点)
- 让用户选择后再描述,防止跑题
- 示例:"这个观点可以用以下几类故事支撑:A) 创业早期的决策 B) 技术选型的教训 C) 团队协作的案例,有相关经历吗?"
**Marketing 类**:
- 优先问客户成功案例
- 次之问自己的故事/案例
- 示例:"有没有客户因为这个功能获得明显收益的案例?"
**审核机制**:
- 用户提供故事后,审核是否符合论点
- 符合 → 使用
- 不符合 → clarify 或拒绝,不能硬塞
- 没有合适故事 → 不加,不编造
采访轮次:
- 通常 2-4 轮问答即可
- 每轮 1-3 个问题
- 当核心观点和角度明确后结束采访
Phase 3: 内容生成
生成步骤:
- 整合采访收集的观点
- 应用
writing-style.md中的风格特征 - 遵循
thinking-patterns.md中的思考框架 - 结合
domain-knowledge.md中的专业见解 - 一次性生成完整输出包
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.
- 4d ago First seen · 258 lines · 79 tokens per session scan A fd96888bc29a
interview-writer is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 2,254 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…