Utilities

Anthropic's official meta-skill for drafting new Claude skills, testing them against baselines, and tuning descriptions for reliable triggering.

Fetch any webpage through Chrome and save it as a clean Markdown file.

A blunt Marc Andreessen persona that pressure-tests ideas and ventures market-first and ends with a BUILD / DERISK / KILL verdict plus confidence level.

Conservatively detects the CPU, memory, disk and accelerator limits your current process actually has, emitting a redacted JSON snapshot plus safe worker-planning helpers.

A persona skill that makes Claude analyze AI direction, safety strategy and research taste through Ilya Sutskever's thinking framework.

Auto-detects any knowledge source — docs site, GitHub repo, PDF, video, codebase — and turns it into a packaged AI skill.

An AI tax adviser for French personal taxation — income tax, wealth tax, capital income, rentals, equity and crypto — with step-by-step math and legal citations.

Installs a macOS menu bar icon that shows whether NanoClaw is running, with Start, Stop and Restart controls.

A concise skill for installing and configuring the claude-mem memory layer on Cursor with either a local or remote worker.

Configures and verifies claude-mem cloud sync against a cmem.ai Pro SyncHub connection.

Interviews you, designs a custom claude-mem memory mode, installs it, wires optional Telegram alerts, and verifies it is actually active.

Explains any senpi `Tip:` line in depth by querying the live tip list, checking your own settings, and reading the real feature source code.

A reference skill for picking, configuring and ordering automated wet-lab protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio).

Generates short, warm companion replies via Zhipu GLM and pushes them (with a matching image) to Feishu/Discord/Telegram/WhatsApp through OpenClaw.

Generates warm, in-character encouragement via Zhipu AI (GLM-4.7-flash) and delivers it with a matching image through OpenClaw messaging.

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.

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

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.

Inventories recent local Claude Code and Codex conversations for a workspace with a single read-only command.