Analyzes your local screenpipe history to detect repeated research workflows and drafts new skills or composition recipes for whatever isn't covered yet.
Orchestrates a reproducible bulk RNA-seq workflow from raw FASTQ through QC, quantification, differential expression, pathway enrichment and publication figures.
Runs a long-horizon experiment loop that improves a scorable artifact through a persistent hypothesis tree, with a held-out test gate to block overfitting.
Restructures a bloated CLAUDE.md / AGENTS.md into a lean Level 1 plus on-demand Level 2 references, with verified zero information loss.
An evidence-driven, falsification-first playbook for network, streaming and protocol bugs where the obvious cause is probably wrong.
Measure any OpenAI- or Anthropic-compatible endpoint across six dimensions — availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
A battle-tested guide to writing, testing, registering and debugging Claude Code PreToolUse/PostToolUse/SessionStart/Stop hooks.
A meta-skill for authoring new Claude Code skills, upgrading existing ones, and proving the change worked with tiered evals.
A field-tested guide for building iOS/macOS apps with XcodeGen, SwiftUI and SPM, plus Apple signing, notarization and CI/CD fixes.
Scan, scrub, verify, and safely force-push away secrets, private domains, and PII hiding in your Git history.
Turns any Claude Code skills repo into an official plugin marketplace that users can install with `claude plugin install`.
Audits already-rendered web, dashboard, HTML deck, and Electron UIs with real-browser journeys, inspected screenshots, and a bundled Playwright sweep to catch layout, responsive, state, and output defects.
Turns audio and video into speaker-labeled, timestamped transcripts — and owns ASR audio preprocessing as a first-class job.
Turns a frontend project or webpage into a cinematic product promo video using Remotion, real page screenshots, 2.5D camera moves, beat-synced cuts and sound design.
Audits a paid ad account against a 20-item ROAS rubric and returns a SHIP/FIX/BLOCK verdict before you launch or scale spend.
Run several Claude Code sessions as a lead-plus-teammates crew with a shared task list, mailbox messaging, and file locks.
A step-by-step, approval-gated runbook for moving legacy NanoClaw and Claude-native memory files into the shared `memory/` tree.
Spins up 5 mutually hostile agents for a 3-round critique debate, keeps only the defensible insights, then hands them to the `plan` agent for an executable plan.
Maps your codebase into per-feature Mermaid flowcharts, proves where logic is duplicated, and proposes the simplest unified architecture.
A three-tier escalation skill that reaches pages blocked by 403, Cloudflare, JS-only rendering, or login walls.