An adversarial review skill that forces Claude into three hostile reviewer personas so 'LGTM' is never an option.
Designs statistically valid A/B tests end to end — hypothesis, sample size, launch checklist, and results analysis.
Read-only audit of dependency vulnerabilities, version health, and license facts across Node.js, Python, Go, Rust, JVM, and Ruby projects, with an evidence-backed report.
Plug-in vision for text-only models: hands any image path or URL to the modlens CLI and returns structured JSON evidence.
Writes evidence-grounded Google Ads RSA copy and designs controlled A/B tests to find winning messaging.
Launches the Google Gemini CLI as an independent reviewer for code, Google Ads, and SEO changes in review, challenge, or consult mode.
Launches Google's Gemini CLI to review, stress-test, or consult on your Google Ads, SEO, and code changes.
A prompt-engineering skill that detects your target AI tool and returns one paste-ready prompt tuned to that tool's quirks.
An interactive skill that decides whether to scale, optimize, or kill a growth channel using CAC, LTV, payback, customer quality, and scalability.
A canonical contract for AI research that runs without you: bounded question budget, search-plan gate, Fact/Inference/Assumption labels, do-not-invent lists, and a stable diffable output schema.
An interactive assessment that tells you whether your product org is merely "AI-first" (faster tasks) or truly "AI-shaped" (redesigned work), and which of five competencies to build next.
An interactive advisor that re-architects repetitive PM work into a set of parallel, specialized AI agents with clear boundaries, monitoring, and evals.
A workflow skill that maps growth options across the four Ansoff quadrants with sourced evidence and a risk-rated execution sequence.
Eleven focused skills to plan, draft, audit, and publish LinkedIn posts and comments with a draft → approve → publish flow.
Paste a LinkedIn post URL and get 1-3 conversation-starting comment drafts in your voice, a suggested reaction, and one-click publishing after approval.
Pulls everyone who liked or commented on a LinkedIn post, tiers them by ICP fit, and outputs ready-to-use outreach action lists.
Turns a theme and audience into a 7-day LinkedIn calendar with pillar mix, hook formulas, posting times, and daily comment targets.
Runs a blameless after-action review of an incident, launch, or finished project and outputs a full report with timeline, root cause, and owned action items.
Runs a structured, blameless postmortem or retrospective on an incident, launch, or finished project and produces a report with timeline, root cause, and owned action items.
A pre-launch QA pass over paid-ads measurement plumbing: event firing, UTM hygiene, cross-platform dedup, attribution windows, plus a UTM/event spec builder.