All skills

Walks a directory tree and auto-generates or repairs EGM-compliant READMEs documenting each package's interface, invariants, and side effects.

An orchestrator skill that drains a GitHub Project board through Build → QA → Review → Done lanes autonomously.

Installs, repairs and tests Claude Code hooks so risky commands are blocked mechanically instead of by polite instructions.

A read-only pipeline that turns long novels or serialized web fiction into a traceable analysis layer: chapter index, adaptation triage, story units, and episode candidates.

Scans a Karpathy-pattern LLM wiki (raw sources + wikilinked markdown + schema) and builds an interactive knowledge graph with entities, implicit relationships, and topic clusters.

A BMad-native skill that slices initiatives into epics and stories, writes/refines tickets, and runs the whole board.

A read-only health check that audits your LazyCodex and Codex CLI install against the latest upstream sources and returns an evidence-backed PASS/WARN/FAIL report.

A pre-npm-publish gate that splits unpublished changes into up to 10 groups for parallel deep review, adds a 5-agent holistic pass, and an oracle release synthesis.

Five mutually hostile agents debate your plan across three rounds, and only the surviving insights get formalized into an executable plan by a dedicated planner.

A durable goal-execution skill that decomposes work into atomic steps, requires real observable evidence for every success criterion, and delegates to Codex subagents.

An execution loop skill that decomposes long-running work into goals, evidence-bound steps, and delegated background subagents.

Turns a vague or large request into ONE decision-complete work plan: explores the codebase first, asks only the forks it cannot resolve, and writes the plan only after your explicit approval.

An orchestration skill that executes an approved `.omo/plans` work plan by delegating every unit to parallel subagents and closing checkboxes only against captured evidence.

Step-by-step skill for wiring a personal WeChat account into NanoClaw using Tencent's official iLink Bot API with QR-code login.

x

Installs the rtk CLI proxy and wires it into nanoclaw agent containers via a PreToolUse hook for 60–90% token savings on dev commands.

Pressure-tests any AI plan with six Chief AI Officer questions — evals, hallucination SLO, EU AI Act tier, build-vs-buy, cost curve, next hire — and returns a SHIP/SHARPEN/BLOCK verdict.

A strict operating procedure for building, retrieving, and correcting evidence-grounded local person profiles using only Distilly's five MCP tools.

An installation skill that wires a local Ollama MCP server into NanoClaw so the container agent can run local models and optionally manage the model library.

A step-by-step skill that wires a Signal messaging channel into a NanoClaw assistant using a signal-cli device link.