ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads…
Repurpose YouTube videos, blog articles, guides, or raw insights into high-performing LinkedIn posts that match Ben Van Sprundel's tone of voice and writing style. A step-by-step, interactive process: never output a complete post immediately. Each step presents suggestions,
$ npx -y skills add naveedharri/benai-skills --skill bens-linkedin-post-writer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/bens-linkedin-post-writerContext preview
The summary Claude sees to decide when to auto-load this skill.
Repurpose YouTube videos, blog articles, guides, or raw insights into high-performing LinkedIn posts that match Ben Van Sprundel's tone of voice and writing style. A step-by-step, interactive process: never output a complete post immediately. Each step presents suggestions,
name: bens-linkedin-post-writer disable-model-invocation: true description: > Repurpose YouTube videos, blog articles, guides, or raw insights into high-performing LinkedIn posts that match Ben Van Sprundel's tone of voice and writing style. A step-by-step, interactive process: never output a complete post immediately. Each step presents suggestions, waits for the user's decision, then advances to the next step. Use when the user shares a YouTube link, blog URL, transcript, document, insight, or idea and wants a LinkedIn post, or asks to repurpose content for LinkedIn. Triggers: "LinkedIn post", "LinkedIn content", "repurpose", "write a post", "post about", "turn this into a post", "create a LinkedIn post", "LinkedIn from YouTube", "LinkedIn from blog".
Take source material (YouTube videos, blog articles, guides, or raw insights) and walk the user through a structured, collaborative process to create a LinkedIn post that sounds authentically like Ben Van Sprundel.
This is an iterative, step-by-step process. Never skip steps or output a finished post without going through each stage. At most steps, present multiple options (typically 10) and wait for the user to choose the direction.
Read each one only when its step says to. Do not frontload everything at once.
| Document | What it contains | When to read | |---|---|---| | `references/performance-defaults.md` | Audience context + what works and what underperforms | Step 2 | | `references/frameworks.md` | The six writing frameworks + performance rankings | Step 3 | | `references/linkedin-examples.md` | Ben's real posts, the ground truth for voice and tone | Steps 3, 5 | | `references/hook-templates.md` | 80+ hook templates by category with psychological triggers | Step 4 | | `references/writing-style.md` | Ben's sentence, tone, and flow rules | Step 5 | | `references/humanization.md` | AI-tell removal pass + iteration questions | Step 5 (before delivery) |
Always use provided data first. Only fetch external data when the user gives a URL without accompanying text.
Give a 1-2 sentence summary and confirm with the user before Step 1.
Analyze the source internally: core themes, standout stories/data/examples, angles for the target audience, personal experiences or unique perspectives. Do not present this analysis in detail. Use it to inform Step 2. Tell the user you have analyzed the content and are ready to suggest outcomes.
**Read `references/performance-defaults.md`** for audience context and what the audience rewards.
Decide what the reader should take away from this post. Present 10 numbered options. Each option:
Make the 10 genuinely different: pull from different themes, audience segments, and emotional triggers. Do not rephrase the same idea 10 ways.
One post = one idea with depth. When the user picks a main outcome plus secondary outcomes, weave the secondaries in as subtle undertones, not explicit sections or standalone paragraphs.
Wait for the user to choose before moving on.
**Read `references/linkedin-examples.md` and `references/frameworks.md`.**
Present all six frameworks. For each, write 3-5 bullet points describing what each section of the post would cover for this specific topic and outcome. Show the skeleton, do not write the post. Recommend one of the top three by default based on the outcome from Step 2.
Wait for the user to choose before moving on.
**Read `references/hook-templates.md` thoroughly** and follow its "Follow the template structure literally" rule. Also apply the highest-performing hooks in `references/performance-defaults.md`.
The hook decides whether people keep reading. Only the first ~2 lines show before "see more". Keep hooks short, often under 15 words on the first line.
Present exactly 10 hook options. Each must:
Match templates to the outcome (Step 2), framework (Step 3), and post type. For Build Log and Product Showcase, lean on category 8 hooks. For PAS + Numbered Playbook, lean on 8.4.
Wait for the user to choose before moving on.
**Re-read `references/linkedin-examples.md` even if you read it earlier**, to absorb Ben's voice right before writing. Then apply `references/writing-style.md`.
Write the full LinkedIn post and open it as an artifact (an `.md` file) so the user can iterate. Make the hook and body flow as one continuous thought (see writing-style.md).
Then run the draft through `references/humanization.md` before showing it to the user. This pass is mandatory and part of Step 5. Present the humanized post in the artifact and use the iteration questions in humanization.md to gather feedback. Be ready to iterate.
This skill is never finished. Improve it as
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…