All skills

A full production skill for making art-style and explainer animations in code — shot list, lint, per-shot render, QA, and a delivery gate that blocks weak films.

Picks a multi-agent orchestration pattern from requirements, generates and validates provider-ready tool schemas, and evaluates run logs for cost, latency, and bottlenecks.

Compiles a goal into a verifiable task plan and drives a bounded agent loop with machine-run checks, retry caps, and human escalation.

Acts as a French DGFIP tax inspector, auditing a company's books across 9 axes and issuing a reassessment report with legal grounds and penalty estimates.

Runs a French statutory-audit program (NEP, 7 phases) over annual accounts and issues a structured audit opinion report.

Spawns N parallel subagents on the same task in isolated git worktrees, ranks their results, and merges the winning branch.

An engineering skill for scaffolding and registering Paperclip agent adapters that satisfy the server, UI, and CLI surfaces at once.

Installs and configures the GitHub channel adapter so a NanoClaw agent can converse inside PR and issue comment threads.

Spins up five mutually hostile expert agents, runs a three-round cross-critique debate, and hands only the surviving insights to a dedicated plan agent for an executable work plan.

Fans out one background agent per open issue/PR to produce evidence-backed, permalink-cited triage reports in /tmp — with zero writes to GitHub.

Case-by-case QA of opencode itself — CLI, HTTP server, plugin hooks/events over SSE, tmux TUI smoke, and read-only session DB investigation.

Turns Claude Code transcript tokens into a manager-readable cost report (HTML/PDF/CSV/JSON) showing cost per completed outcome and what mistakes cost.

Splits a task into atomic PRs, builds each in its own git worktree, and loops through CI and bot review gates until merged.

Runs 3 vulnerability hunters and 2 PoC engineers in parallel so only findings with a proven, reproducible attack path survive.

A step-by-step runbook for wiring DeltaChat — email-based, end-to-end encrypted messaging — into a NanoClaw bot.

Judges slow, flaky, redundant or brittle tests by the real failure they protect, and trims feedback cost to the smallest verification that covers the risk.

Runs a three-layer, parallel multi-agent review of all unpublished changes before an npm publish and returns a SAFE/CAUTION/RISKY/BLOCK verdict plus a version-bump recommendation.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.

An evidence-driven skill for finding and safely removing accidental complexity — dead code, duplicate state, redundant layers — within an authorized scope.

An interactive, resumable eight-phase journey that measures, untangles, and speeds up a working-but-slow codebase while logging every decision in docs/.