All skills

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.

One CLI for AI image generation across a dozen providers (OpenAI, Google, DashScope, Replicate and more) with reference images and batch mode.

One command scans your unpushed change with the right security/secret/dependency/lint scanners plus a separate reviewer that reads every changed line, then prints a verdict and a report path.

Turns a LinkedIn post URL into 1-3 approval-gated comment drafts in your voice with a suggested reaction, plus a reshare-with-commentary mode.

Turns a theme, audience, and pillar mix into a 7-day LinkedIn calendar with hooks, CTAs, posting times, and daily comment targets.

A 12-skill bundle that plans, drafts, audits, and (after your approval) publishes LinkedIn posts and comments.

A plug-in vision bridge that lets text-only models read images: hand it a path and get back structured JSON with OCR, layout, and semantics.

A CLI bridge skill that gives models without native web tools structured web search, X (Twitter) search, and page fetching as JSON evidence.

Mines your recent agent transcripts and asks targeted questions to produce a personal `-mode` skill that agents follow.

Watches an open pull request, fixes failing CI and straightforward review comments, and drives it to a mergeable state.

Turns novels, loglines, or existing multi-episode drafts into a traceable adaptation plan, story engine, and episode map for short-form drama series.

Launches Google's Gemini CLI to review, stress-test, or consult on your Google Ads, SEO, and code changes.

Pulls everyone who liked or commented on a LinkedIn post, tiers them by ICP fit, and outputs ready-to-use outreach action lists.

Triages every unresolved review thread on a GitHub PR, verifies each claim against current code, fixes what is warranted, pushes, and replies in each thread individually.

An interactive skill that decides whether to scale, optimize, or kill a growth channel using CAC, LTV, payback, customer quality, and scalability.

A workflow skill that maps growth options across the four Ansoff quadrants with sourced evidence and a risk-rated execution sequence.

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 end-to-end workflow for drafting new Claude skills, testing them with evals and benchmarks, and tuning their descriptions for reliable triggering.

An interactive advisor that re-architects repetitive PM work into a set of parallel, specialized AI agents with clear boundaries, monitoring, and evals.

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.