A step-by-step runbook for wiring DeltaChat — email-based, end-to-end encrypted messaging — into a NanoClaw bot.
Runs a three-layer, parallel multi-agent review of all unpublished changes before an npm publish and returns a SAFE/CAUTION/RISKY/BLOCK verdict plus a version-bump recommendation.
An install playbook that adds the pinned Firecrawl AnyDoc CLI to NanoClaw agent containers so Office documents convert to Markdown locally.
Case-by-case QA of opencode itself — CLI, HTTP server, plugin hooks/events over SSE, tmux TUI smoke, and read-only session DB investigation.
Fans out one background agent per open issue/PR to produce evidence-backed, permalink-cited triage reports in /tmp — with zero writes to GitHub.
Official skill that walks you through researching, implementing, testing, and evaluating high-quality MCP (Model Context Protocol) servers in TypeScript or Python.
Reads your local screenpipe timeline, clusters repeated workflows, and drafts new skills or composition recipes for the patterns not yet covered.
Automate Benchling registry entities, inventory, ELN entries, workflows, Apps, and Data Warehouse queries with the Python SDK or v2 REST API.
Official skill that drafts internal communications — 3P updates, newsletters, FAQs, incident and leadership reports — using your company's preferred formats.
Guides Claude to infer transcription factor–target gene networks from expression data using arboreto's GRNBoost2 and GENIE3.
An official Anthropic skill that first authors a design philosophy, then executes it as a museum-grade poster or art piece in PDF/PNG.
Interviews you, designs a custom claude-mem memory mode, installs it, wires optional Telegram alerts, and verifies it is actually active.
Runs multi-pass, multi-source research and returns a cited brief with contradictions, gaps and next steps, archiving every run for later grep.
Builds Angular 17+ features with standalone components, signals, NgRx state, RxJS patterns, bundle optimization, and TestBed tests.
Designs and runs failure-injection experiments for distributed systems, with blast-radius controls, rollback scripts, and game day playbooks.
Turns Claude into a senior architect that designs systems, weighs technology trade-offs, and writes ADRs.
Triages the 37signals 38-question decision guide down to 6–8 load-bearing questions, forces a clear call, and archives the rationale with a revisit date.
Convenes each git worktree and PR as its own agent in a shared markdown room, then drives rounds until one consolidation plan emerges.
Maps a codebase into feature-grouped Mermaid flowcharts, hunts duplicated concerns with file:line evidence, and proposes the simplest unified architecture before a refactor.
Teaches the agent to use `lsp` MCP tools for diagnostics, definitions, references, symbols and safe renames.