interview-question-preparer

An interview-research and question-writing workflow for preparing a published blog or media conversation with a specific person, such as a founder, author, or project maintainer.

In plain words
What is it for?
Use it to research the interview subject, record relevant sources, assess what is known, and produce grouped Markdown questions about their work, decisions, community, business context, background, and future plans.
Why use it?
It helps avoid writing questions from guesswork by checking public evidence first and identifying information that is missing, unclear, or unsupported.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agentera/agently/interview-question-preparer
Any agent
npx skills add AgentEra/Agently --skill interview-question-preparer
Clone the repo
git clone --depth 1 https://github.com/AgentEra/Agently

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00684
Opus 5 $0.00019 $0.00342
Sonnet 5 $0.00008 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured yesterday against content hash 09e3956cdcef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-question-preparer 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 yesterday.

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.

examples/agent_task/skills/interview-question-preparer/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Read the full file on GitHub · 72 lines

Changes

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.

  1. yesterday First seen · 72 lines · 38 tokens per session scan A 09e3956cdcef

Subscribe to this mod's changes

interview-question-preparer is a skill published in the GitHub repository AgentEra/Agently (1,644 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 684 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

implementation-final-review

Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…

openai/openai-agents-python · 58 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

testing-skill

Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.

pydantic/pydantic-ai · 44 tokens

gh-pr-description

Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.

vercel/eve · 38 tokens

adding-a-provider-api-feature

Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…

pydantic/pydantic-ai · 97 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens