interview-to-blog SKILL.md skillA

interview-to-blog from intrafind/ihub-apps is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add intrafind/ihub-apps/interview-to-blog@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
intrafind/ihub-apps
Path
server/defaults/skills/interview-to-blog/SKILL.md
Versions recorded
1
Latest version
v1.0, committed Feb 23, 2026
Size
5,835 bytes
Repository stars
26
License
a license file GitHub does not identify

Produce deep, long-form blog posts (1,800–2,500+ words) by interviewing the user first, researching the topic, architecting the structure, then writing. Use this skill whenever the user wants to create a blog post, write an article, draft a long-form piece, or asks for help turning their expertise into written content. Also trigger when the user says things like "help me write about," "I want to blog about," "turn this into a post," "ghostwrite," "interview me," or "write-up." Do NOT use for…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Interview-to-Blog Post Skill

A four-phase workflow that produces deep, long-form blog posts by interviewing the user first, researching the topic, then synthesizing everything into content that reads like it was written by a domain expert — because it was shaped by one.

**Core insight: the depth of AI output is directly proportional to the depth of human input.** Most AI blog posts feel shallow because the writer skips the hardest part — extracting what they actually know and think. The interview phase solves this.

## Why Interview-First Beats Outline-First

The dominant approach — "generate outline → expand sections → polish" — produces generic content because the AI draws entirely from its training data. Interview-first inverts this: extract unique knowledge, specific examples, and genuine opinions _before_ structuring anything.

## Workflow Overview

The skill runs four sequential phases. Each phase builds on the previous one.

| Phase           | Purpose                                            | Duration  | Reference                                                                |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add intrafind/ihub-apps/interview-to-blog@sha256:4089b4d4dda9926b

The line at the top of this page pins the label v1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ttyeqhyhkhj6e4kj.svg)](https://markdownregistry.com/a/art_ttyeqhyhkhj6e4kj)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Feb 23, 2026.

versioncommittedcommitsizeaudit
v1.0 latest2026-02-23 5071304 5,835 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5835 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

intrafind/ihub-apps · 26 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ttyeqhyhkhj6e4kj
GET https://markdownregistry.com/api/v1/resolve?ref=intrafind/ihub-apps/interview-to-blog
GET https://markdownregistry.com/api/v1/blob/4089b4d4dda9926b1150528ed4bbb4ec0141538063cdee4b265c7e55287cb59c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from intrafind/ihub-apps

claude-automation-recommender SKILL.md skill
intrafind/ihub-apps · .agents/skills/claude-automation-recommender/SKILL.md · Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when…
git:20260224.ecbe01b · audit A · 26 stars
a11y-audit SKILL.md skill
intrafind/ihub-apps · .claude/skills/a11y-audit/SKILL.md · Audit iHub's accessibility (WCAG 2.2 AA, BITV 2.0 / BFSG, EN 301 549) against a requirement list, fix findings, or keep…
git:20261022.495951e · audit A · 26 stars
add-app SKILL.md skill
intrafind/ihub-apps · .claude/skills/add-app/SKILL.md · Scaffold a new AI app config JSON file in contents/apps/ that passes the project's Zod schema validation. Use when…
git:20261107.950015c · audit A · 26 stars
api-design SKILL.md skill
intrafind/ihub-apps · .claude/skills/api-design/SKILL.md · REST conventions for iHub's HTTP API — URL naming, `_action` segments, status codes, RFC 9457 error bodies, cursor…
git:20261107.26be12a · audit A · 26 stars
api-security SKILL.md skill
intrafind/ihub-apps · .claude/skills/api-security/SKILL.md · Guide for securing API endpoints with proper input validation, path traversal prevention, and parameter sanitization…
git:20260224.14571f2 · audit A · 26 stars
caveman-learn SKILL.md skill
intrafind/ihub-apps · .claude/skills/caveman-learn/SKILL.md · Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and…
git:20260914.30914b9 · audit A · 26 stars
create-migration SKILL.md skill
intrafind/ihub-apps · .claude/skills/create-migration/SKILL.md · Create a new versioned config migration in server/migrations/ following the project's Flyway-style pattern. Use when…
git:20260922.bc1396c · audit A · 26 stars
deep-review-pr SKILL.md skill
intrafind/ihub-apps · .claude/skills/deep-review-pr/SKILL.md · Deep review of a GitHub pull request with parallel sub-agent investigation
git:20260914.7763865 · audit A · 26 stars
document-feature SKILL.md skill
intrafind/ihub-apps · .claude/skills/document-feature/SKILL.md · Use when a new feature, improvement, bug fix, or breaking change has been implemented. Adds an entry to…
git:20260915.49623fb · audit A · 26 stars
review-pr-inline SKILL.md skill
intrafind/ihub-apps · .claude/skills/review-pr-inline/SKILL.md · Review a GitHub pull request for defects the author would want fixed before merging, then post the findings as inline…
git:20261029.dad6b44 · audit A · 26 stars
CLAUDE.md@.github/workflows CLAUDE.md file
intrafind/ihub-apps · .github/workflows/CLAUDE.md
git:20260519.a29cd30 · audit A · 26 stars
AGENTS.md AGENTS.md file
intrafind/ihub-apps · AGENTS.md
git:20260706.86a87fe · audit B · 26 stars

Every file in intrafind/ihub-apps

Browse by kind, by grade A, or by owner.