
Claude Skills by edmundmiller
github.com/edmundmillerRun GitHub Actions CI locally with Agent CI only when explicitly requested.
Applies dotfiles completion and durable handoff conventions for multi-session work or explicit AGENT_WORKFLOW.md requests.
Use when configuring Ghostty terminal emulator, working with ghostty config files, or looking up Ghostty settings and options.
Create, manage, and verify healthchecks.io monitors via the REST API. Use when adding monitoring to a new cron job or service, auditing existing checks, wiring ping URLs into configs, or verifying a check fired correctly.
Selects Home Assistant automation, helper, device-control, and dashboard patterns. Use for HA configuration design, refactoring, or AppDaemon apps.
Maps API responses into Homepage customapi widgets, including dynamic-list. Use when configuring those widget mappings.
Integrates Honcho memory into Python or TypeScript agents. Use for Honcho SDK peers, sessions, and dialectic chat wiring.
Investigate jj commit history, split commits, annotate file changes, and clean up redundant commits. Use when debugging history, splitting large commits, or explicitly authorized history rewrites.
Merges two separate Jujutsu (jj) repositories into one. Use when combining repos, rebasing one repo onto another, or recovering from diverged histories.
Provides nix-darwin references for macOS module options, Mac bootstrap, and Darwin rebuild failures in dotfiles.
Updates Nix package pins, source hashes, and carried upstream patches. Use for package bumps, patch rebases, or upstream source changes packaged here.
Write Nix modules with platform-specific options (NixOS vs Darwin) without infinite recursion. Use when mkIf causes evaluation errors or options don't exist across platforms.
Recover or rebuild an installed NixOS system from a NixOS USB/live ISO. Use for boot failures, broken generations, bootloader repairs, or rescue rebuilds.
Configures OMP model roles, provider fallbacks, and per-host overrides. Use for OMP model changes or mismatches between source and active configuration.
Bundles prompts and files with the Oracle CLI. Use when explicitly requesting that CLI or preparing a focused unresolved question for an external model.
Maps Pi packages, extensions, and skills to this repository's Nix ownership. Use when converting between Pi setup instructions and declarative dotfiles.
Debug and test tmux pane status detection for AI agents (opencode, claude, amp). Use when patterns aren't matching, status icons are wrong, or adding new detection patterns.
Creates or records isolated jj agent workspaces. Use when starting jj task work, entering a Herdr-created workspace, or handling an agent-created Git worktree boundary.
Creates and wires agenix-encrypted dotfiles secrets. Use for age recipients, encrypted credential updates, and NixOS service secret ownership.
Uses Home Assistant APIs on NixOS for integration config flows, entity/device inspection, and token setup. Use for live HA API work rather than declarative Nix edits.
Manages Nix-owned HA automations, scenes, scripts, and entity identity. Use for domain edits, ensureEnabled assertions, or orphan-sweep debugging.
Activates dotfiles on managed hosts through hey. Use when a system rebuild, activation, or rollback is explicitly requested, not after every Nix edit.
Measures interactive zsh latency with zsh-bench. Use for slow-shell diagnosis, performance comparisons, or regression bisection.
Renders and compares static JS/TS call trees with callstack-diff. Use for requested branching call-flow maps from source or stated architecture.
Use when the user wants OMP to run Microsoft SkillOpt-Sleep, learn from past OMP sessions, review or adopt staged skill improvements, or schedule an offline sleep/dream self-improvement cycle.
Decomposes and reorganizes agent memory files into focused, single-purpose components. Use when memory has large multi-topic blocks, redundancy, or poor organization. Trigger phrases: "defrag memory", "reorganize memory", "clean up memory files", "split memory blocks".
Comprehensive guide for initializing or reorganizing agent memory into a deeply hierarchical file structure. Use when running /init, when user asks to set up memory, or when memory needs a major reorganization. Trigger phrases: "initialize memory", "set up memory", "populate memory", "build my memory", "memory init".
Retrieves pi-context-repo notes and checks memory sync state. Use to find prior preferences, read memory files, or synchronize requested updates.
Use amoxide for project-local .aliases and optional profiles when commands are simple, trusted, and useful to agents without shadowing zsh aliases.
Searches and rewrites syntax with ast-grep. Use for AST-pattern codemods or authoring, testing, and configuring structural lint rules.
Maintains durable goal and handoff state. Use for explicit goal-management requests, resuming a recorded goal, or diagnosing agents that stall and need repeated prompts.
A high-divergence, low-inhibition ideation mode that encourages bold exploration first and strict validation second. Use when you want unusually creative problem solving, surprising solution candidates, and wider search before converging.
Renders and compares static JS/TS call trees with callstack-diff. Use for requested branching call-flow maps from source or stated architecture.
Compares text and structural search strategies. Use when selecting a search/codemod approach, not for ordinary known-string lookups.
Refines code without changing behavior. Use when explicitly asked to simplify, clean up, or improve code readability.
Filters large API, CLI, or database results before retrieval. Use when a query needs source-side selection or projection to avoid oversized output.
Derives a task-focused API client from authorized HAR/browser traffic. Use to inspect first-party requests or replace a demonstrated browser workflow with a CLI.
Run a final review-readiness pass for rule conformance, type safety, and overengineering.
Use when inspecting, previewing, drawing, messaging, capturing, publishing, or diagnosing the BUSY Bar or TRMNL OG/X displays from the declarative dotfiles configuration.
Close an explicit repository task by shaping, landing, publishing, proving, and cleaning it up; also handles narrower commit, publish, and landing-verification requests without exceeding their authority.
Starts isolated Codex worktree threads for dependency-aware Beads work. Use when explicitly asked to split a Beads backlog into separate implementation threads.
Writes, modifies, explains, validates, and runs ggsql grammar-of-graphics visualization queries.
Attach local images or videos to GitHub issues, pull requests, and comments with GitHub CLI's repeatable --attach flag. Use when publishing screenshots, recordings, diagrams, or rendered results from local files to GitHub.
Create least-privilege fine-grained GitHub personal access tokens. Use when the user wants a PAT template, recurring machine credential, private-repository token, or GitHub token rotation.
Copies commands to an authorized remote machine's clipboard over SSH and retrieves explicitly captured results. Use when a human must run a local interactive or privileged command on another machine but cannot conveniently transfer the command between devices.
Runs Herdr task workspaces with OMP, jj, Hunk, and durable receipts from creation through cleanup. Use for creating, resuming, reviewing, publishing, shipping, or removing a Herdr jj task workspace.
Dispatches spoken or written prompts to live Herdr agents and reports their status or results. Use when the user says to list, check, ask, tell, prompt, steer, or wait for an OMP, Codex, or other agent running in Herdr.
Maintains reviewable HTML notes on spec decisions and deviations. Use when the user requests ongoing implementation notes alongside a build.
Entity-level code review with Ataraxy Labs inspect. Use when triaging PR/commit risk, ranking changed entities by impact, grouping tangled changes, or deciding review depth from blast radius/dependents.
Use the TWG CLI for explicit Jira issue reads, searches, queries, and mutations while minimizing returned context and preventing refetch or help loops. Do not use for Confluence, general Atlassian context, or TWG setup.