evanstern

Orchestrate a multi-task board sweep through the full PDLC — author a dependency-laned runbook from a set of board tasks (or adopt an existing runbook), get operator sign-off on the lanes, then execute every task automatically through spec → link → worktree →…

Bootstrap a NEW or EXISTING project folder for the praxis development lifecycle (PDLC), OR update an already-bootstrapped one after a plugin upgrade. Use when the user wants to set up praxisflux in a project, says "bootstrap this project for praxis/PDLC",…

Run operator-in-the-loop design iteration on a board task under PDLC — cut a long-running worktree, claim the card, produce N rounds of comparable demo artifacts, record the operator's selection as a tracked decision, and only then author the spec against the…

Evaluate a body of merged work — a post-sweep commit range or the whole repo — for tech debt and intent drift, triage every finding with the operator (accept / reject / defer, rationale recorded), and execute accepted findings onto the Backlog board as cited,…

Run a lead-engineer-plus-team architecture review of a codebase using parallel subagents, producing one consolidated, evidence-backed report — what's good, what could be improved, what should be removed, steal-worthy patterns, new ideas, and open questions.…

Orchestrate a learning lesson's lifecycle in an educate project — placement, scaffolding, the teach -> build -> deck handoff seam, and the Definition-of-Done gate. Use when starting, resuming, or finishing a lesson, or when the user asks where a lesson should…

Implement a build SPEC handed off from a learning lesson (or any producer), verify it works, and return findings for the lesson to fold back in. Use when a lesson has handed off a SPEC to build, when the user says "run build", "/build-me", "build the spec",…

Corpus-grounded reorientation of a project's direction — N parallel evaluator subagents each judge one research branch under a stated lens against the project's wiki and board, the operator steers between rounds, evaluators cross-ground each other, and the…

Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run…

Add Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants agents to deploy web applications to Vercel.

Add WeChat (personal) channel integration via Tencent's official iLink Bot API. Uses long-polling and QR scan — no webhook, no ToS risk, no paid token.

Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to…

Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and common issues.

On-demand codebase analysis that dispatches multiple independent agents to find issues, filters for high-confidence findings via convergence scoring, and produces structured reports with cross-run tracking. Use when you want a health check of the codebase —…

Zip each subfolder of a source folder individually, move the original unzipped subfolders into a sibling "<name>-raw" folder, then zip the whole source folder into "<name>.zip". Use whenever the user wants to "nested-zip" a folder, archive a folder of…

Process downloaded media files from /mnt/jace_complete folders. Extracts RAR archives and moves files to the correct location in /mnt/jace_media. Handles TV series (organized by show and season) and movies.

Launch multiple worktree agents in parallel to work on independent tasks. Each agent gets its own git branch, isolated worktree, and clear scope. Manages the full lifecycle: launch, track, push, PR, and merge. Use when you have a list of features, fixes, or…

Spin off an idea from the current conversation into a new GitHub repository. Creates the repo, clones it locally, scaffolds a CLAUDE.md capturing the context and vision from the conversation, and pushes the initial commit. Use when an idea has been explored…

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism,…

Runs a freeform polish session — small FE/TUI changes and gameplay tweaks worked against a live world, on one long-running card and one PR, with a decision recorded before each fix. Covers the loop, the ad-hoc-versus-spec test, the stub-first ordering…

Routes UI work in internal/tui to the generated frame harness (docs/design/tui/frames/) instead of reasoning from lipgloss calls. Covers how to see a screen, the design loop, and three repo traps a fresh session hits. Check first: node…

Generates and refreshes docs/player/ — sixteen self-contained HTML pages that project the code-grounded wiki (docs/wiki/), README.md, docs/llm-providers.md, and (for the curriculum-ladder quickstarts) the spec 046 spec/contracts into plain-language…

Produce the Principle VIII learning artifact that closes a spec cycle: a feature-scoped, self-contained interactive HTML course under docs/courses/<feature>/, authored in the-stacks skilled-developer register and seeded from the feature's spec artifacts +…

Run a full spec cycle end-to-end — specify → clarify → plan → tasks → worktree pivot → implement → analyze/converge → course — pausing at operator review gates between steps. The operator reviews and re-orients; the skill drives. Use when asked to 'run a spec…

Boot orchestrator identity from config directory. Reads SOUL.md, MEMORY.md, PROJECT.md, recent memory, learnings, dreams, and wiki. MUST USE at session start or when identity feels generic/blank.

Triage focus cards before acting. Determines whether each card needs design, a feature session, or inline work. Use when the user says "start work on X" or references one or more focus cards for implementation.