Agent Skills › AgentEra/Agently › interview-question-preparer

interview-question-preparer

GitHub

为指定人物或项目准备基于公开证据的博客/媒体采访提纲。通过研究背景、评估信息充分性,撰写包含具体问题和来源引用的Markdown文档,确保内容客观准确,适用于深度访谈而非招聘面试。

examples/agent_task/skills/interview-question-preparer/SKILL.md AgentEra/Agently

Trigger Scenarios

需要为某位创始人或作者准备媒体采访问题 生成基于公开资料的人物专访提纲

Install

npx skills add AgentEra/Agently --skill interview-question-preparer -g -y
More Options

Non-standard path

npx skills add https://github.com/AgentEra/Agently/tree/main/examples/agent_task/skills/interview-question-preparer -g -y

Use without installing

npx skills use AgentEra/Agently@interview-question-preparer

指定 Agent (Claude Code)

npx skills add AgentEra/Agently --skill interview-question-preparer -a claude-code -g -y

安装 repo 全部 skill

npx skills add AgentEra/Agently --all -g -y

预览 repo 内 skill

npx skills add AgentEra/Agently --list

SKILL.md

Frontmatter
{
    "name": "interview-question-preparer",
    "description": "Prepare an evidence-backed blog\/media interview preparation brief for a specified person by researching public context, reflecting on information sufficiency, and writing the final Markdown deliverable."
}

Interview Question Preparer

Use this Skill when the task is to prepare a serious blog-style or media-style interview brief for a specified person, author, founder, maintainer, or project owner. This is for a published article or long-form conversation, not a hiring interview, recruiting screen, or candidate evaluation.

Workflow

  1. Clarify the interview target, audience, and intended article angle from the task input.
  2. Research public context before drafting. Search broadly first, then browse only the most relevant pages.
  3. Keep compact notes for source URLs, source titles, and why each source is relevant.
  4. Reflect on information sufficiency:
    • what is well-supported by public evidence;
    • what is weak, ambiguous, or missing;
    • whether any supplied affiliation, organization, work, role, or alias is contradicted or not supported by the sources;
    • whether another search or browse step is needed before finalizing.
  5. Draft grouped article interview questions that connect the person, project, product philosophy, technical tradeoffs, community adoption, business context, personal narrative, tensions, and future direction.
  6. Write the final Markdown deliverable to the requested workspace path.
  7. After writing or revising the requested file, read file back from the workspace when a workspace read capability is available, then include a concise validation checklist in the final response so the verifier can inspect the written content against the task criteria.

Output Requirements

The final Markdown file must include:

  • title;
  • target and audience;
  • story/interview angle;
  • source notes with URLs or source labels;
  • sufficiency reflection;
  • grouped blog/media interview questions;
  • at least eight concrete questions;
  • a short closing section for optional follow-up probes.

Boundaries

  • Do not invent biographical facts when public evidence is weak.
  • Mark weak assumptions explicitly.
  • Source notes must be specific: include a URL, title, or clear source label, plus one sentence explaining why that source matters to the interview angle.
  • If the user's wording implies an affiliation or relationship that sources do not support, mark it as uncertain or contradicted instead of repeating it as fact.
  • When public evidence is sparse, state low confidence, list unknowns, and use clarifying or exploratory questions rather than invented biography.
  • When names, aliases, or same-name people are ambiguous, preserve the user's original wording and explain the disambiguation choice.
  • When multiple targets are supplied, include target-specific questions for each target and comparative article questions that connect them.
  • Prefer questions that can elicit original insight from the interviewee, not generic product promotion.
  • Do not frame the deliverable as a job interview, hiring guide, candidate assessment, or recruiting screen.
  • If the task asks for a file, use the workspace file-writing capability and report the written path.
  • If the task is correcting a previously written file, prefer reading the file before deciding whether to patch or fully rewrite it.

Version History

  • 4f2a184 Current 2026-08-20 15:26

Same Skill Collection

examples/agent_task_experiments/skills/equity-risk-reviewer/SKILL.md
examples/agent_task_experiments/skills/market-entry-analyst/SKILL.md
examples/agent_task_experiments/skills/travel-planner/SKILL.md
examples/release_pinned_usage/skills/pinned-release-checklist/SKILL.md
examples/release_pinned_usage/skills/pinned-script-candidate/SKILL.md
examples/skills_executor/skills/architecture-diagram/SKILL.md
examples/skills_executor/skills/conditional-resource-guide/SKILL.md
examples/skills_executor/skills/release-checklist/SKILL.md
examples/skills_executor/skills/release-readiness-reviewer/SKILL.md
examples/skills_executor/skills/script-release-probe/SKILL.md
examples/skills_executor/skills/ok-status-skill/SKILL.md

Metadata

Files
0
Version
d582395
Hash
09e3956c
Indexed
2026-08-20 15:26

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-17 09:34
浙ICP备14020137号-1