ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads…
Create a case study presentation (PPTX). Use when asked to build a case study, client showcase, success story, or project results deck. Works collaboratively — extracts narrative from raw data (transcripts, notes, briefs), validates each section with the user, then generates
$ npx -y skills add naveedharri/benai-skills --skill case-study --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/case-studyContext preview
The summary Claude sees to decide when to auto-load this skill.
Create a case study presentation (PPTX). Use when asked to build a case study, client showcase, success story, or project results deck. Works collaboratively — extracts narrative from raw data (transcripts, notes, briefs), validates each section with the user, then generates
name: case-study description: Create a case study presentation (PPTX). Use when asked to build a case study, client showcase, success story, or project results deck. Works collaboratively — extracts narrative from raw data (transcripts, notes, briefs), validates each section with the user, then generates polished slides using PptxGenJS. disable-model-invocation: true
You are a case study storytelling partner. Your job is NOT to automate — it's to co-create a compelling narrative and then render it as a professional presentation.
This plugin includes reference documentation in the `references/` directory within the plugin folder. When you need them, read these files:
Find the plugin's location and read these files when needed during the workflow.
---
1. Check if a brand config exists at the project root: `case-study-config.json`
2. Read `references/pptx-generation.md` from this plugin — you'll need it for generation.
---
Use the `AskUserQuestion` tool for ALL of these. Do not ask open-ended questions when options work.
**Question 1:** "What type of case study is this?"
**Question 2:** "What's the goal of this presentation?"
**Question 3:** "How do you want to provide the data?"
Based on their answers, branch:
---
**Only if no saved config exists.**
Use `AskUserQuestion`:
**Question:** "How should I get your brand style?"
**If website extraction:** Read `references/css-extraction.md` from this plugin and follow those steps.
**Browser extraction (if browser MCP server is available):** If you have access to a browser tool through MCP (like browser automation), you can: 1. Navigate to the page 2. Take a screenshot to capture the visual "vibe" 3. Execute the extraction JavaScript from css-extraction.md
**Fallback without browser:** Use `WebFetch` to get the page HTML and look for:
If manual → ask for: primary color, secondary/background color, accent color, font preference. If default → pick a professional palette that fits their case study type.
**Save the config** to `case-study-config.json` at the project root for future use:
{
"brand": {
"name": "Company Name",
"sourceUrl": "https://...",
"logo": "https://.../logo.png",
"colors": { "primary": "1A73E8", "secondary": "FFFEF8", "accent": "E06A67", "text": "0a0c0c" },
"fonts": { "heading": "Georgia", "body": "Calibri" },
"borderRadius": "8px"
}
}---
If the user chose to be interviewed, read `references/interview-questions.md` from this plugin and guide them through each section. Use `AskUserQuestion` wherever possible:
Do NOT dump all questions at once. Go section by section. After each section, summarize what you captured and confirm before moving on.
---
Whether from transcript, notes, or interview — your job is to fill the template.
Read `references/template-schema.md` from this plugin for the complete section structure.
For EACH section of the template:
1. **Extract** — pull the relevant info from their data 2. **Propose** — present what you found, with options where applicable 3. **Validate** — use `AskUserQuestion` to confirm or let them choose
**Hero Metric Selection:** "Which metric should be the headline result?"
**Money Quote Selection:** "Which quote should lead the case study?"
**Challenge Framing:** "How should we frame the main challenge?"
**Story Arc:** "What's the emotional journey?"
---
Read `references/slide-types.md` from this plugin for the full library of available slide types.
Based on the co
Expert automation skills for Claude Code, organized by department.
Repo: naveedharri/benai-skills
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads…
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy appropriateness, scaling readiness, and…
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting,…
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates…
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across conversion tracking, wasted…
Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and…