dotclaude-config

Plugin dotclaude-config from marketplace dotclaude in fairchild/dotclaude. Commands read from the repo's manifest — today.

Skills (50)

• agent-inbox

  File-based messaging between agents across tools. Use when notified of unread inbox mail, setting up an agent inbox, or sending, reading, or replying to agent messages.

• analyze-usage

  Analyze local AI coding-assistant activity across Claude Code, Codex, Cursor, and Pi. Use when the user asks about coding usage, tool or skill statistics, activity patterns, repositories, sessions, token costs, conversation history, or wants to query their AI coding logs. Triggers include "usage", "

• arc-handoff

  Hand off an arc of work on its tracking issue, or pick up an arc another session left. Use before a session ends or compacts with work in flight, when an arc's merge order, blockers or running processes change, or when starting on an arc with open PRs.

• ascii-art-fix

  Fix misaligned right borders in ASCII art diagrams

• backlog

  Markdown task backlog and project roadmap (backlog/{todo,doing,done,failed}/, backlog/ROADMAP.md) for adding, advancing, recording progress, rescuing, cancelling, retrying, failing, maintenance, or reflecting on backlog priorities and roadmap direction.

• brainstorm-to-brief

  Wide→Narrow design workflow taking UI/UX concepts from exploration to polished design brief. Four phases - Context, Explore, Iterate, Refine. Use for visual design exploration, user story mockups, and creating shareable design briefs.

• canon-printer

  Check status, ink levels, job queue, cancel stuck jobs, print files and rendered documents, track loaded paper, and troubleshoot reachability for the home Canon PIXMA iX6800 printer. Manually invoked only — use `/canon-printer` (optionally `status`, `jobs`, `cancel-job`, `print`, `print-doc`, `paper

• chronicle

  Session continuity for coding work. Default to /chronicle to capture, /chronicle catchup to resume, and /chronicle pending to review open threads. Use curate, recap, wrapup, summarize, publish, insights, search, and ui only when the user explicitly needs them.

• claude-as

  Run Claude Code under a different account with claude-as profiles. Use to launch a side agent on another account to spread usage, to find out which profile or account a session runs as, or to add, rename, repair or remove a profile. Triggers on claude-as, profile, account, login, CLAUDE_CONFIG_DIR,

• cloudflare-workers-deploy

  Set up Cloudflare Workers deployment for web applications with GitHub Actions CI/CD. Use when adding Workers deployment to an existing project, setting up auto-deploy on push/PR, configuring Durable Objects for stateful apps, or creating a dual-deployment pattern (keep Replit/Vercel while adding Wor

• codespaces

  Manage GitHub Codespaces lifecycle via gh CLI. Use for "create codespace", "ssh into codespace", "stop codespace", "delete codespace", "codespace secrets", "codespace logs", "list codespaces", "codespace ports", "rebuild codespace", "gh cs", "codespace machine types".

• codex-cli

  Run Codex CLI for code review or implementation, select the current model, and capture the model and session that actually ran. Use whenever invoking codex from another agent or updating a Codex CLI recipe.

• compaction-handoff

  Prepare a long-running session for compaction and pick the work up after it — write durable state before the cut, ask for the cut with instructions and a resume prompt, then rebuild from live reads instead of the summary. Use when the user says "prepare for compaction", "let's compact" or "we're get

• consequential-check

  Route a pull request to its owner when merging it is consequential — hard to undo, weakens security, costs money, makes a product decision, or could expose private data. Installs a CI workflow in which a decision model (TypeSafe's Jev) answers typed yes/no questions, a cheap Claude model answers the

• copy-review

  Review or rewrite a README, a docs page or a landing page so it informs a newcomer fast — what it is, how to install it, one example, then links to the detail. Use when asked to review copy or docs, when a page "reads as AI slop", before a public release, and for any change to a README or docs page

• dotclaude-config

  Work with Claude Code configuration at global (~/.claude) or project (.claude/) level. Use when editing settings.json (permissions, hooks, statusline, model), managing MCP servers, creating agents/commands/skills, writing CLAUDE.md, setting up rules files, or configuring a new project. Determines co

• dotfiles-checkup

  Check this machine's dotfiles against the public repo and bring them back to clean. Use when the user asks to check, tidy, or clean up their dotfiles or shell config, when a new shell prints errors, when PATH has duplicates, after installing a tool that edits ~/.zshrc, or when `mise run doctor` warn

• excalidraw-diagrams

  Create diagrams and visual artifacts using Excalidraw with real-time canvas preview. Use when the user asks to create, draw, or visualize diagrams, flowcharts, architecture diagrams, system designs, or any visual representation. Supports creating elements programmatically, Mermaid diagram conversion

• fable-session

  Hand off long-arc work to a fable session — a Fable orchestrator at xhigh effort verifies while delegating the implementation — and the operating rules for any agent fan-out — whether to fan out at all, a model named per spawn, one port and one writer per agent, and the lenses a review looks through

• fork

  Fork the current session with context carried over. Use `/fork <branch>` for a new worktree or `/fork --local` for a new session in the current directory.

• gh-apps

  Create, authenticate, and manage GitHub Apps. Use for creating apps via manifest flow, generating JWTs, getting installation tokens, managing webhooks and installations, rotating keys. Triggers on "create github app", "github app", "manage github app", "github app JWT", "github installation token",

• git-worktree

  Manage Git worktrees for concurrent local development. Creates worktrees

• gondolin-ci

  Run one GitHub Actions suite for a pull request inside a disposable gondolin micro-VM on a Mac, and watch the steps land. User-invoked only — the user asks for it by name ("run CI on my laptop", "gondolin ci"); never start a run because a pull request looks red.

• image-gen

  Generate images from prompts using AI APIs (OpenAI GPT Image, Google Gemini/Nano Banana, Google Imagen, fal.ai Flux). Use when the user asks to generate, create, make, render, or produce an image, icon, visual asset, illustration, mockup, texture, poster, or other raster image file.

• ios-simulator

  Automate iOS Simulator tasks — capture screenshots, interact with apps, generate screen flow galleries. Use when the user asks to capture app screens, screenshot the simulator, document the app UI, create a screen flow, interact with the simulator, or automate iOS testing workflows.

• macos-agent-pressure

  Diagnose live macOS memory, swap, load, and concurrent AI-agent process pressure. Use when the user asks for a Mac or agent-resource checkup, reports queued or stalled Codex/Claude work, suspects heavy swap or too many concurrent agents, asks whether to reboot, or wants a before-and-after reassessme

• persona-memory

  Build and operate a persistent persona and memory framework for Claude Code. Use when setting up personality.md injection, durable memory blocks in ~/.ai-memory, session start/end memory workflows, recall/remember/consolidate scripts, or packaging a distributable memory skill profile.

• picture

  Build "the picture" — every agent arc in flight, in ten lines or fewer — from arc chat channels, a GitHub sweep and the weekly numbers. Use when asked "where are we", asked for the picture of all arcs or everything in flight, or mentioned in the picture channel.

• plain-writing

  Plain, direct writing voice — no undefined jargon, no throat-clearing, no showing off — for any prose a person reads (reports, docs, emails, proposals, summaries, chat replies). Use by default when writing or revising prose.

• pr-closeout

  Own a pull request you opened from draft to ready to merge — CI green, every review finding given a disposition, fixed threads resolved, state verified on the current head. Use after opening or pushing to a PR, when review comments arrive on your PR, and before reporting a PR ready.

• project-scripts

  Standardize project lifecycle scripts (setup, run, stop, archive) in scripts/ so agents can manage workspaces through a single interface across runtimes. Scripts are portable bash; mise is the recommended orchestrator when available, with adapters for Conductor, Claude Code hooks, devcontainers, Cur

• release

  Create semantic versioned releases with AI-generated changelogs, for repos that do not already have a release pipeline of their own. Worktree-aware - works from any branch. Use when the user wants to create a release, cut a release, bump version, or publish a new version. Defers to the repo's own re

• repo-steward

  The repo steward role — one long-running session that owns the work in a single repository. It turns issues into isolated workspaces, workspaces into pull requests, and pull requests into merge-ready ones by dispatching workers and gating what they produce; it asks the operator only for merges and d

• retrospective

  Run a retrospective on a session, PR or milestone — find the mistakes that repeated, fix each at the strongest layer that holds it, and prove each new check catches the real past mistake. Run as /retrospective after a PR merges or is abandoned, after a failed verification, or at the end of an arc.

• review-pr

  Review a pull request, yours before opening it or someone else's, then re-check each later push for blockers only, with every verdict bound to the reviewed head. Run as /review-pr <url or branch> to review or re-review, including your own branch before opening a PR.

• runner-optin

  Run one reviewed commit of one pull request on this laptop while hosted runners are blocked. User-invoked only — the user asks for it by name ("opt in", "opt out", "run this PR on my laptop"); never start it because a pull request looks red.

• session-titles

  Session title generation, evaluation, and optimization. Auto-generates context-aware titles via Stop hook. Includes quality evaluation (pattern checks, LLM judge), GEPA-inspired prompt evolution, golden dataset tooling, and interactive title rating for training data collection.

• signoz-log

  Send structured logs to SigNoz observability platform. Use when you need to record events, errors, or activity for monitoring. Triggers on log, observe, signoz, telemetry, record event.

• skill-building

  Guide for creating, editing, and evaluating skills. Use when creating a new skill, updating an existing skill, or verifying skills work before deployment. Also use when reviewing a third-party skill from skills.sh or GitHub, when asking "should I install this skill", "is this skill safe", "review th

• skill-seeker

  Generate Claude Code skills from docs sites, GitHub repos, or local codebases using Skill Seekers.

• skills-manager

  Use when the user wants to list, search, install, remove, inspect, validate, audit,

• swiftui-expert

  Write, review, or improve SwiftUI code. Use for SwiftUI features/refactors, state management, view composition, performance, concurrency, modern Apple APIs, or native UI quality.

• team-memory

  Persistent AI teammate memory framework. Gives Claude Code agents persistent memory, evolving personality, and teammate-like behavior across sessions. Use when setting up personality.md injection, durable memory blocks in ~/.ai-memory, session start/end memory workflows, journal/remember/consolidate

• tidyup

  Proof-based sweep of a repo's accumulated worktrees, stale local branches, and in-flight PRs — reduces open threads to what's actually alive. Explicit invocation only (/tidyup); classification is squash-merge aware and nothing is deleted without proof or approval.

• tight-docs

  Use this when a coding agent writes or revises a design doc, a security review, or an ADR (an architecture decision record) and the doc must be tight: short sections, no filler, and every claim backed by evidence.

• update-dependencies

  Smart dependency updates across ecosystems (npm/bun/pnpm, uv/poetry, cargo). Use when upgrading dependencies, fixing vulnerabilities, or performing proactive maintenance. Supports intelligent batching, risk assessment, and outcome tracking for continuous improvement.

• vocal

  Speak text aloud (TTS) and transcribe speech (STT). Supports local (macOS say, mlx-whisper) and cloud (ElevenLabs) providers. Use when user asks to speak, read aloud, listen, transcribe, or use vocal.

• web-artifacts-builder

  Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

• webapp-testing

  Interact with and test web applications using Playwright. Supports ad-hoc browser tasks (screenshots, form filling, deploy checks), Python and TypeScript E2E testing, visual debugging, and browser automation.

• youtube-content

  Extract and analyze YouTube video content (transcripts + metadata). Use when the user explicitly requests to analyze, summarize, extract wisdom from, or get context from a YouTube video. Supports wisdom extraction, summary, Q&A prep, key quotes, and custom analysis. Does NOT auto-trigger on YouTube

Slash commands (4)

• /dotclaude-config:bootstrap

  Bootstrap a new project with interactive brainstorming and structure generation

• /dotclaude-config:opensource-precheck

  Audit a private repo before making it public

• /dotclaude-config:project-health

  Review health of ~/code projects (git status, tests, remote sync)

• /dotclaude-config:reflect

  Pause to review work with fresh eyes for bugs, missed cases, or simplifications

Subagents (9)

• ai-sdk-agent-architect

  Implement Vercel AI SDK 6 agents with streaming, tool orchestration, and reasoning visibility.

• chronicle-curator

  Curate and organize Chronicle memory blocks. Reviews session context, updates recent blocks, and maintains memory coherence across sessions.

• chronicle-insights

  Deep exploration of Chronicle memory and worktrees to generate meaningful insights. Spawns Explore subagents to examine actual code and cross-reference with memory blocks.

• devcontainer-setup

  Use this agent when you need to set up, configure, or verify a DevContainer environment for a project. This includes creating the initial .devcontainer configuration files, setting up security measures like firewalls and filesystem isolation, configuring development tools, and verifying the containe

• github-notifications-triager

  Check GitHub notifications and provide a prioritized summary of important items.

• project-handoff-auditor

  Audit codebase quality, docs, tests, and deployment before client handoff.

• research

  Deep codebase exploration to understand a problem and create a research artifact

• team-memory-sleep

  Sleep-time compute orchestrator for team-memory skill. Dispatched by SessionEnd hook. Runs extract → consolidate → reflect pipeline sequentially.

• vocal-listener

  Background listener that records speech, transcribes it, and sends transcripts to the main session.

Similar plugins