Diagnose and fix Cloudflare redirect loops, SSL, and DNS problems by querying the actual configuration through the Cloudflare API.
Clones and audits competitor repositories into an evidence-based competitive report with file:line citations.
Repairs hard-wrapped Claude Code .txt exports by rebuilding tables, paragraphs, paths and tool output.
Builds a complete 360-degree feedback survey instrument, or turns raw reviewer notes into a structured feedback report.
Reads your 401k paperwork and converts fund fees, match fine print, and vesting rules into concrete dollars-over-time math.
Converts a raw git log into grouped, user-facing release notes with a headline and migration note.
Turns any UI or design into a structured WCAG 2.2 audit with pass/fail checks and a prioritised remediation plan.
Turns Markdown, HTML, or raw text into a fully formatted WeChat Official Account draft with themes, cover image, and comment settings.
Creates article cover images by combining five design dimensions — type, palette, rendering style, text level, and mood.
Restructures a bloated CLAUDE.md/AGENTS.md into a lean Level 1 plus on-demand Level 2 references with guaranteed zero information loss.
Moves Claude Code's per-project memory into tool-agnostic reference docs so Codex (and other AI CLIs) can read your profile, then verifies it by actually running codex.
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.
Adversarially tears down a founder, company or product you envy — separating marketing bubble from real signal, then mapping the validated playbook onto your own resources.
Find, control, and screenshot specific macOS application windows programmatically using Swift, AppleScript, and screencapture.
A safety net that preserves your task state and key files across Claude Code context compaction cycles.
A practical playbook for managing token budgets and context quality in Claude sessions through four operations: Write, Select, Compress, Isolate.
A workflow skill that decomposes repetitive, large-scale code changes into independent units and runs one parallel agent per isolated git worktree.
Detects your project's stack and auto-configures lint, typecheck, test and format quality gates plus a Claude settings file.
A playbook for running multiple Claude Code sessions as a lead-plus-teammates team with shared tasks, messaging, and file locks.