All skills

Produces statistically rigorous A/B test plans with hypothesis, sample size, duration, safety metrics, and a results-interpretation guide.

Scrapes and aggregates bestseller/new-release rankings from major Chinese web-novel platforms to extract market trends and viable story-topic candidates.

An evidence-driven playbook that queries the Cloudflare API to diagnose redirect loops, SSL errors, DNS problems, and origin failures instead of guessing.

Turns a list of shell commands into polished animated terminal demo GIFs using VHS recordings.

Evidence-driven diagnosis and repair of repository setup, plus guarded Git sync, commit, push and hook workflows.

Runs N sub-agents on the exact same task, then makes them attack, defend and get judged in a single-elimination bracket until one solution survives.

Give it an issue number and it runs the whole loop: analyze, branch, implement, test, and open a PR.

Delegates coding, code review, and plan review to the OpenAI Codex CLI from inside Claude Code, with disciplined sandbox levels.

Reviews GitHub pull requests with seven parallel specialist subagents, then adversarially verifies every finding so only high-confidence, high-severity issues get posted.

A diagnose-first skill for writing, reviewing and debugging Terraform/OpenTofu code, tests, CI pipelines and state operations with version-aware guardrails.

Produces a statistically rigorous A/B test plan with hypothesis, sample size, duration, guardrail metrics, and a pre-committed results interpretation guide.

Repairs hard-wrapped Claude Code .txt exports by rebuilding tables, paragraphs, paths and tool output.

Turns any UI or design into a structured WCAG 2.2 audit with pass/fail checks and a prioritised remediation plan.

Cleans up speech-to-text transcripts through a two-stage pipeline — instant dictionary rules plus Claude's own AI correction — while building a personal correction database that gets smarter with every fix.

Searches Claude Code (and Codex) session history across every config home and registered archive, and recovers deleted files byte-for-byte from file-history snapshots.

Find, control, and screenshot specific macOS application windows programmatically using Swift, AppleScript, and screencapture.

Build, test and drive iOS apps in the Simulator with 31 token-efficient scripts that navigate by accessibility label instead of pixel coordinates.

Turns real logged agent failures into trace-based behavioural test cases plus a one-command Python runner.

Reads computed styles in the running app to catch hardcoded colors, off-palette backgrounds, unclickable controls, and animations that never ran.

When the console is empty and the code looks fine but the app still doesn't work, this skill gathers evidence from the running page and hands you the file:line to open.