macos-development-environment

Use this skill when the user wants to transition to the next workflow step, wrap up a session cleanly, prepare a handoff, or says things like "next step", "continue the workflow", "wrap up", "hand off", "move to the next phase", "what's next in embrace", or "prepare for /clear". Also triggers when the current octo:embrace phase appears complete and no explicit next action is set.

Spawn a dotfiles team for changes spanning chezmoi templates, mise config, and system validation. Use when adding tools that need both mise config and shell config changes.

Use when diagnosing brew failures in mde update, auditing brew-owned packages, resolving brew-vs-mise ownership conflicts, or troubleshooting Homebrew on macOS. Key files: src/mde/maintain/update.py, src/mde/validate/brew.py, configs/mde-tool-ownership.json. Keywords: brew doctor, brew upgrade, cask sudo, tap repair, formula conflict, Brewfile.

This skill should be used when the user asks to manage AI agent configurations (CLAUDE.md, AGENTS.md, permissions, MCP settings, skills) across multiple tools and machines using chezmoi templates. Use when syncing .claude/ settings across machines, templating CLAUDE.md for different environments, distributing agent instructions to Claude Code/Codex/Copilot from one source, managing AI agent permissions via chezmoi data, backing up Claude Code config with chezmoi, or setting up a shared skills directory.

This skill should be used when the user asks to "add a tool to mise", "install a new CLI tool", "choose a mise backend", "search the mise registry", "detect tool drift", or mentions mise tool installation, backend selection, GIT_TERMINAL_PROMPT enforcement, or adding new dependencies to mise config.

Use when setting up Doppler as secrets source of truth, syncing Doppler to fnox/Keychain, bulk importing/exporting secrets, validating Doppler vs fnox parity, or troubleshooting Doppler CLI issues in this mise+chezmoi dev environment.

This skill should be used when the user asks to "evaluate plugins", "scan marketplace", "audit community plugins", "find plugins for X", "screen marketplace", "plugin audit", "what plugins should we install", or "review marketplace plugins". Orchestrates full marketplace evaluation pipeline: screen all plugins, deep-review finalists, persist findings to repo, and optionally run multi-model review rounds.

This skill should be used when the user asks to "update evaluation goals", "add plugin goal", "change marketplace evaluator config", "modify evaluation criteria", "add a new capability need", "remove a goal", or "reconfigure evaluator models". Manages the goals.yaml configuration for the marketplace evaluator.

This skill should be used when the user asks to "improve evaluator", "learn from evaluations", "evolve evaluation prompts", "check prediction accuracy", "review overridden verdicts", "meta-learn", or "how accurate are plugin evaluations". Reviews past evaluations vs actual outcomes and evolves the screening/review prompts.

This skill should be used when the user asks to "audit evaluator", "check for replacement", "can another plugin replace this", "self-audit marketplace evaluator", "is there a better evaluator plugin", or "should we replace marketplace-evaluator". Checks if any community plugin now provides the same functionality as this plugin, and whether this plugin should be improved or replaced.

Run full verification suite (ruff check, ruff format, ty type check, pytest) and report results. Use before committing, before marking work done, or when asked to verify changes.

This skill should be used when the user asks to "check consensus", "validate agreement", "evaluate review threshold", "check autonomy mode", "verify consensus gate", or mentions consensus validation, agreement threshold, 75% gate, autonomy modes, or ConsensusGate evaluation.

This skill should be used when the user asks to "run a multi-model review", "debate code changes", "invoke reviewd", "get multiple model opinions", "run adversarial review", or mentions multi-model review, debate orchestration, reviewd CLI, codex review, gemini review, or adversarial code analysis.

This skill should be used when the user asks to "synthesize findings", "combine research", "cross-reference sources", "summarize evidence", "write a deep review", or mentions evidence synthesis, finding consolidation, cross-source analysis, or research summarization.

This skill should be used when the user asks to "ingest into NotebookLM", "query NotebookLM", "add sources to notebook", "cross-source synthesis", "check stale sources", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.

This skill should be used when the user asks to "score research", "check research quality", "evaluate coverage", "measure improvement", "assess research completeness", or mentions research scoring, quality metrics, coverage gaps, improvement baseline, or research pipeline status.

This skill should be used when the user asks to "summarize review findings", "prioritize fixes", "rank review issues", "combine reviewer feedback", "create action items from review", or mentions review synthesis, finding prioritization, severity ranking, or review result summarization.

This skill should be used when the user asks to "find sources", "discover URLs", "catalog a source", "classify a URL", "search for libraries", "check what exists", or mentions source discovery, URL cataloging, source classification, or research source management.

Run autonomous multi-model code review on a finding. Invokes claude/codex/gemini via reviewd, evaluates consensus, and auto-commits or escalates to human.

Search all Claude Code skill/plugin marketplaces, curated collections, and GitHub for skills matching a use case. Compares findings to installed inventory, ranks by adoption, and handles install + symlink + agent wiring. Use PROACTIVELY when any agent is missing skills, when the user asks "find a skill for X", "is there a skill for Y", "search for Z", or when you notice a capability gap that an existing skill might fill. Also use when setting up a new specialist agent that needs domain skills.

This skill should be used when the user asks about "devcontainer CLI", "devcontainer up", "devcontainer exec", "devcontainer build", "devcontainer read-configuration", "run-user-commands", "CI devcontainer", "install devcontainer CLI", or needs to automate devcontainer operations from the command line.

This skill should be used when the user asks about "devcontainer Docker Compose", "dockerComposeFile", "runServices", "shutdownAction", "sidecar services", "compose integration", "postStartCommand for compose", "multi-container devcontainer", or needs to decide between dockerComposeFile mode and lifecycle-based compose management for dev environments.

This skill should be used when the user asks about "devcontainer features", "feature installation", "installsAfter", "feature registry", "ghcr.io features", "docker-in-docker feature", "composable dev environment", "create custom feature", "publish devcontainer feature", or needs to configure the devcontainer feature system for modular environment composition.

This skill should be used when the user asks about "devcontainer lifecycle events", "postStartCommand", "postCreateCommand", "onCreateCommand", "lifecycle execution order", "parallel named commands", "waitFor property", "command failure semantics", "prebuild commands", "container startup hooks", or needs to understand when and how devcontainer lifecycle events execute.

This skill should be used when the user asks to "create a devcontainer", "set up a dev container", "initialize devcontainer.json", "add devcontainer to project", "configure development container", "devcontainer from scratch", or wants to create a new devcontainer configuration from scratch based on project analysis.

Guides the user through developing, validating, and publishing plugins for the rsm-subagents local marketplace. Activate when the user mentions "rsm-subagents", "create rsm plugin", "marketplace plugin", "local plugin development", "plugin workflow", "plugin validate", or wants to add a new plugin to the rsm-subagents directory.

This skill should be used when the user asks about advanced chezmoi configuration beyond basic templates, such as setting up monorepo dotfiles with .chezmoiroot, removing old files with .chezmoiremove, configuring git autoCommit/autoPush, setting up age or GPG encryption, managing encryption keys, using multiple config formats (YAML/JSON/TOML), or creating custom chezmoi commands.

This skill should be used when the user asks about chezmoi dotfile management, creating, modifying, or maintaining dotfile templates, configuration files, scripts, and external resources. Use when the user asks to "create a chezmoi template", "add a .tmpl file", "write Go template syntax", "manage .chezmoi.toml.tmpl", "configure .chezmoiexternal", "write run_once/run_onchange scripts", "integrate 1Password with chezmoi", "add password manager to dotfiles", "manage cross-platform configs", or "add OS-conditional logic". Also use when editing .chezmoidata files or working with chezmoi template variables.

This skill should be used when the user asks to adopt chezmoi on new machines or migrate from other dotfile managers, such as setting up dotfiles on a new Mac, doing a fresh chezmoi install, migrating from stow/yadm/bare-git repos, setting up multi-account GitHub SSH, deploying dotfiles in CI/Docker with one-shot mode, or onboarding team members to chezmoi.

This skill should be used when the user encounters chezmoi failures, state issues, or configuration problems, such as when chezmoi doctor shows errors, scripts don't run as expected, chezmoi verify fails, chezmoi diff shows unexpected changes, state needs resetting, or merge conflicts occur in chezmoi source.

This skill should be used when the user asks about dotfile backup, sync, and daily operations with chezmoi, such as to "sync dotfiles", "backup configs", "cross-machine sync", "chezmoi add", "chezmoi diff", "chezmoi status", "push dotfiles", "pull dotfiles", "track a new file with chezmoi", "resolve merge conflicts in dotfiles", or "set up chezmoi remote". Do NOT use for template authoring (use chezmoi-config) or troubleshooting (use chezmoi-troubleshooting).

This skill should be used when the user asks to edit or manage hk.pkl configuration files, such as adding stash settings, changing hook modes, configuring profiles, or modifying any hk configuration. Also use when user asks about hk settings or pkl syntax.

This skill should be used when the user asks to add, remove, or modify hook steps in hk.pkl, such as adding new linters, removing deprecated steps, changing file globs, or reorganizing hook structure.

This skill should be used when the user encounters hk hook failures including stash restoration errors, step failures, environment issues, and configuration problems. Use when pre-commit hooks fail, when hk behaves unexpectedly, or when hooks pass/fail inconsistently.

This skill should be used when the user asks to "install a CLI tool", "add a global tool", "check mise policy", "enforce mise-first", or when reviewing scripts that mention brew install, npm -g, bun add -g, bun install -g, pipx install, pip install --user, cargo install, go install, or gem install. Also use when validating runtime/tool commands to ensure a strict mise-first workflow. After blocking a direct install, see the mise-tool-management skill for the correct path to add tools via mise.

This skill should be used when the user asks to "configure environment variables", "set up mise env", "add env vars to mise.toml", "use _.file for secrets", "set up redact", "configure multi-environment", or mentions mise [env] section, mise set/unset, _.file, _.path, _.python.venv, or secrets in mise config.

This skill should be used when the user asks to orchestrate multi-step project workflows using mise task definitions with dependency management and argument handling. Use whenever the user wants to create, edit, or debug mise tasks, wire up task dependencies with depends/depends_post, or run workflows via 'mise run'. Also use when setting up task runners or automating build pipelines through mise. Do NOT use for mise environment variable configuration (use mise-env-config instead) or for general shell scripting unrelated to mise.

This skill should be used when the user asks to "generate a GitHub Action for mise", "create a devcontainer with mise", "generate a bootstrap script", "generate task documentation", "create task stubs", or mentions mise generate, CI/CD setup with mise, devcontainer configuration, or mise bootstrap scripts.

This skill should be used when the user asks to "configure mise settings", "change mise config", "format mise.toml", "trust a config file", "set up IDE integration for mise", or mentions mise config, mise settings, mise fmt, mise trust, mise.local.toml, or IDE/editor integration with mise.

This skill should be used when the user asks about "pitchfork", "fnox", "hk git hooks", "usage CLI specs", "jdx tools", or mentions process management with mise, secrets management with fnox, git hooks with hk, or CLI argument parsing with usage. Also use when integrating multiple jdx tools together.