ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Interview the user one question at a time before starting a big or fuzzy task, then write the brief and execute it. Use when the user says "interview me", "brief me", "help me brief this", "I don't know where to start", or hands over a large task with obvious gaps in the
Claude Code
$ npx -y skills add naveedharri/benai-skills --skill interview-me --agent claude-code
Codex
$ npx skills add naveedharri/benai-skills --skill interview-me -a codex -y
Cursor
$ npx skills add naveedharri/benai-skills --skill interview-me -a cursor -y
Gemini CLI
$ npx skills add naveedharri/benai-skills --skill interview-me -a gemini-cli -y
GitHub Copilot
$ npx skills add naveedharri/benai-skills --skill interview-me -a github-copilot -y
OpenCode
$ npx skills add naveedharri/benai-skills --skill interview-me -a opencode -y
Windsurf
$ npx skills add naveedharri/benai-skills --skill interview-me -a windsurf -y
name: interview-me description: Interview the user one question at a time before starting a big or fuzzy task, then write the brief and execute it. Use when the user says "interview me", "brief me", "help me brief this", "I don't know where to start", or hands over a large task with obvious gaps in the request. Based on the interview pattern Anthropic recommends in the Claude Fable 5 field guide. disable-model-invocation: true
Most briefs fail because the missing context is in the user's head and nobody asked for it. This skill pulls it out before any work starts, using the pattern Anthropic recommends: interview one question at a time, prioritising the questions whose answers would change the plan.
Source: A field guide to Claude Fable 5 (https://claude.com/blog/a-field-guide-to-claude-fable-finding-your-unknowns).
1. **Read before you ask.** Look at whatever is already available: the folder, the files the user mentioned, recent related work. Never ask a question you could answer yourself by reading. Questions you burned on discoverable facts are questions you cannot spend on real unknowns.
2. **Interview, one question at a time.** Ask 5 to 7 questions maximum, one per turn, in plain language. Prioritise questions whose answer would change the shape of the work: the audience, the decision this output feeds, what already exists, what must not change. Push past vague answers: if the user says "make it better," ask what better looks like and how you would both know it happened.
3. **Cover four things by the end of the interview:**
4. **Run a blind spot pass.** Before writing the brief, ask yourself one final question and share the answer: what has this interview not covered that could change the outcome? Name the unknown unknowns you can see.
5. **Write the brief back.** Compile everything into one master brief with these parts: the job, the why (who it is for and what it enables), the guardrails (scope, what not to touch), and done-means (exit criteria, deliverable size, how to report back). Show it to the user.
6. **On approval, execute the brief.** Check in only at decisions the user claimed in step 3.
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy…
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative…
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative…
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across…
Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…