All skills

Extracts and analyzes Google Takeout exports of your Gemini chat history, producing a topic breakdown, key insights, and PII warnings.

A battle-tested guide to writing, testing, registering, and debugging Claude Code PreToolUse / PostToolUse / SessionStart / Stop hooks.

A macOS network-debugging skill that isolates and fixes Tailscale conflicts with Shadowrocket/Clash/Surge/OrbStack — route hijacks, proxy env vars, SSH double tunnels, Docker proxy propagation and stalled DNS.

Extracts 50+ fields — tiered pricing, SKU variants, seller scores, coupons — from 1688.com product detail pages.

Pulls Airbnb search results straight from the page's SSR-embedded JSON and returns listing ID, name, coordinates, rating, price, photos and pagination cursors.

A gateway skill for the browser-act CLI: fetch JS-rendered pages, keep logged-in sessions, automate forms, capture screenshots and network responses.

A Bugcrowd-specific reporting overlay: VRT selection, manual severity-override requests, and ready-made out-of-scope rebuttals.

Turns a document, thread, transcript, or pasted text into a scannable briefing you can absorb in seconds.

A conversation-style skill that forces Claude into terse, zero-warmth answers with the conclusion on line one.

A step-by-step skill for committing and pushing your working tree straight to a PR whose head branch lives on a fork — without touching origin/upstream.

Rebuilds any animation from a URL, video or GIF in your own codebase, then re-records the clone and proves the match frame by frame.

Authors, audits and regionalizes the commercial policy that defines what terms sales may offer and what triggers approval.

Models the true financial structure of go-to-market channels — direct, reseller, marketplace, OEM — and designs partner tiers, rebates and channel-conflict rules.

Runs a WCAG 2.1 AA accessibility audit across five testing stages and produces a prioritized remediation report.

Designs a full measurement framework — north star metric, KPI hierarchy, event taxonomy, dashboards and attribution — and outputs a usable tracking plan.

A senior creative strategist's system for producing, testing, and refreshing performance ad creative at scale.

An editorial playbook for deciding what humans must own, where AI may help, and how to keep AI-assisted content on-voice and honest.

A discipline playbook for reading paid media dashboards without fooling yourself — attribution, reconciliation, incrementality, and a scale/hold/kill decision.

One command that runs the right security, secret, dependency and lint scanners on your unpushed diff, then has a separate AI reviewer verify every finding before you `git push`.

One command that runs the right security, secret, dependency and lint scanners on your pending change and has a separate reviewer re-check every finding before you push.