edmundmiller
@edmundmiller
Public Skills
dotfiles
by edmundmiller
For keeping all my Dotfiles update to date
callstack-diff
by edmundmiller
This skill should be used when a user asks to "map the logic flow", "show the call flow", "visualize how this request branches", presents a prose or architecture flow such as A → B → C with branches, or asks to render or compare static JavaScript and TypeScript call-stack trees.
skillopt-sleep-learned
by edmundmiller
Preferences and procedures learned from past local agent sessions.
omp-model-config
by edmundmiller
Configure OMP model roles, providers, fallback chains, and per-host overrides in this nix-darwin dotfiles repo. Use when changing which models OMP uses, shifting providers, fixing fallback chains, or troubleshooting why a model change didn't take effect after rebuild.
using-jj-workspaces
by edmundmiller
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.
herdr-jj-workflow
by edmundmiller
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.
just-say-no-to-process-porn
by edmundmiller
Stop AI process-porn, ceremony, and fake progress so work finishes as real software. Use at session start when the user wants anti-ceremony defaults; mid-session when the agent is planning, todoling, scaffolding, or status-reporting instead of shipping; before claiming done; or when the user mentions process porn, ceremony, performative work, reward hacking, or endless foundation/MVP theater. Do not use for genuine multi-stakeholder process the user explicitly requested.
autonomous-agent-loop
by edmundmiller
Use when a task is broad, multi-step, cross-session, or the user says agents need too many re-prompts/kicks, asks to use createGoal/goals, says continue/keep going, or wants rough Pi/agent sessions improved. Keeps work moving from objective to evidence-backed completion.
done
by edmundmiller
Lands finished Git worktrees or jj workspaces, publishes, proves remote equality, and cleans up.
herdr
by edmundmiller
Control live Herdr workspaces, tabs, panes, agents, worktrees, plugins, and waits. Use when running inside Herdr (HERDR_ENV=1) to inspect sibling agents, delegate work—including dedicated Pi workspaces—run services, debug agent detection, or coordinate terminal state.
honcho-integration
by edmundmiller
Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, implementing the dialectic chat endpoint for AI agents, or wiring Honcho into bot frameworks (nanobot, openclaw, picoclaw, etc).
jj-history-investigation
by edmundmiller
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.
batch
by edmundmiller
Coordinate a sweeping mechanical change across independent work units and pull requests.
deslop
by edmundmiller
Run a final review-readiness pass for rule conformance, type safety, and overengineering.
simplify
by edmundmiller
Review changed code for reuse, quality, and efficiency, then fix worthwhile issues.
skill-quality
by edmundmiller
Validate and review agent skills for portable structure, clear triggers, executable helpers, and reliable behavior across Terra and Sol.
context-efficiency
by edmundmiller
Filter data at the source before it enters context. Use when querying APIs, CLIs, or databases where the full output would be large. Prefer structured output + jg when available, or python/tool-native selectors when not. Use jq only when jg cannot express the needed transformation. Trigger phrases: "find the entity for", "get the ID of", "which service handles", "what's the value of", or any time you'd otherwise dump a large dataset to find one thing.
ggsql
by edmundmiller
Writes, modifies, explains, validates, and runs ggsql grammar-of-graphics visualization queries.
pr-review-handoff
by edmundmiller
Prepares intended GitHub pull requests from today's Codex tasks for a concise human review handoff. Use when asked to find today's PRs, make PRs or a PR stack review-ready, audit current-head checks and reviews, improve PR titles/bodies, or draft or send a Slack review handoff.
herdr-voice-dispatcher
by edmundmiller
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.
agent-ci
by edmundmiller
Run GitHub Actions CI locally with Agent CI only when explicitly requested.
via-negativa
by edmundmiller
Simplifies bloated products, offerings, documents, plans, and flows through purpose-locked subtraction. Use when asked to cut scope, remove bloat, create a kill list, decide what to keep or remove, or improve something by subtraction. Do not use for code-only refactors, optimizing individual flow steps, release prioritization, or evaluating one proposed addition.
homepage-custom-api-widget
by edmundmiller
This skill should be used when the user asks to "configure a Homepage customapi widget", "map API fields in Homepage", "use dynamic-list in Homepage", or mentions Homepage Custom API widget mappings.
ballmer-peak
by edmundmiller
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.
microdose
by edmundmiller
A subtle creativity mode for escaping obvious solutions without losing coherence. Use when the work feels technically correct but predictable, flat, or overly constrained.
derive-web-api-client
by edmundmiller
Derive a narrow, efficient API client or CLI from an authorized browser workflow by recording and analyzing HAR network traffic. Use when repeated browser automation is slow or brittle, when asked to inspect a HAR or reverse-engineer a site's first-party requests, or when turning a demonstrated website action into a structured command-line tool.
zbench
by edmundmiller
Benchmark interactive zsh performance with zsh-bench and track regressions. Use when benchmarking shell startup, comparing zsh latency after config changes, investigating slow shell, or running git bisect on performance. Trigger phrases: "benchmark zsh", "shell is slow", "zbench", "zsh-bench", "shell startup time", "profile zsh", "zsh performance".
fork-bead-threads
by edmundmiller
Fork one isolated Codex worktree thread per Beads issue and start each with a dependency-aware completion contract. Use when the user asks to start, fork, split, parallelize, or create separate chats for beads, tickets, issues, or a backlog with the goal of fixing them all.
nix-package-patching
by edmundmiller
This skill should be used when the user asks to "bump a package", "update an upstream revision", "refresh a Nix source hash", "rebase local patches", "carry fork changes as patches", "hack on upstream software in this repo", or fix a package whose patches no longer apply.
healthchecks-io
by edmundmiller
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.
ast-grep
by edmundmiller
Structural code search, refactoring, and repository lint-rule setup with ast-grep. Use when searching by syntax shape, writing or testing ast-grep rules, configuring sgconfig.yml, enforcing coding standards, selecting rule severity, or adding ast-grep to project checks and CI.
code-search
by edmundmiller
Use when searching code by unknown means or choosing between text and structural search tools. Owns ast-grep vs ripgrep selection and text-search guidance.
hunk-review
by edmundmiller
Review and steer live Hunk diff sessions, inspect focused files/hunks, navigate, reload sources, resume worktree reviews, and add validated inline comments. Use when the user has Hunk open, asks for an interactive diff review, mentions Hunk comments, or wants to resume a paired agent/Hunk worktree.
acpx-claude
by edmundmiller
Hand off a bounded implementation or review pass to Claude through ACPX.
github-fine-grained-pat
by edmundmiller
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.
dotfiles-agent-workflow
by edmundmiller
Use this skill to apply the canonical risk-gated dotfiles workflow when work is broad, autonomous, high-risk, or multi-session; when the user tags AGENT_WORKFLOW.md; or when repeated agent friction needs durable guidance.
stack-maintenance
by edmundmiller
Maintains stacked GitHub PRs and branches. Triggers on "fix stacked PRs", "merge this PR stack", "restack branches", "turn on auto-merge", gh stack, gh pr, jj spr, wrong PR bases, merge queues, or force-pushing stack repairs.
home-assistant-best-practices
by edmundmiller
Best practices for HA automations, helpers, scripts, controls, and dashboards. TRIGGER THIS SKILL WHEN: - Creating or editing automations, scripts, scenes, or dashboards - Choosing between template sensors and built-in helpers - Restructuring triggers, conditions, or automation modes - Setting up Zigbee button/remote automations - Renaming entities or migrating device_id to entity_id - Configuring dashboard cards or selecting helpers - Looking up card types or domain docs - Writing or reviewing AppDaemon apps SYMPTOMS: - Agent uses Jinja2 templates where native options exist - Agent uses device_id instead of entity_id - Agent changes entity IDs without checking consumers - Wrong automation mode - Agent hard-codes values or uses raw sensor over helper - Agent edits .storage, writes YAML, or generates YAML snippets - Agent tells user to edit configuration.yaml for UI integrations
writing-agent-friendly-clis
by edmundmiller
Write, design, or review agent-friendly CLIs and agentic interfaces for humans, scripts, and coding agents, with progressive disclosure, structured output, actionable errors, stdout/stderr separation, and explicit non-interactive modes.
skillopt-sleep
by edmundmiller
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.
nix-darwin-reference
by edmundmiller
This skill should be used when editing nix-darwin or Darwin-specific Nix configuration in this dotfiles repo, troubleshooting darwin-rebuild failures, looking up macOS module options, bootstrapping a Mac with Lix/Nix, or using legacy nix-build during nix-darwin work.
writing-git-commits
by edmundmiller
Split staged or uncommitted changes into conventional commits. Use when asked to commit, generate commit messages, split commits, squash commits, or reorder history.
defragmenting-memory
by edmundmiller
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".
initializing-memory
by edmundmiller
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".
Searching Memory
by edmundmiller
Preserve frontmatter schema (description, limit, optional protected read_only).
amoxide-project-aliases
by edmundmiller
Use amoxide for project-local .aliases and optional profiles when commands are simple, trusted, and useful to agents without shadowing zsh aliases.
tufte-viz
by edmundmiller
Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays Applies principles: data-ink ratio, chartjunk elimination, graphical integrity, lie factor, small multiples, and data density.
spec-driven-spock
by edmundmiller
Use Spock 2.x metadata annotations (@Title, @Narrative, @Subject, @See, @Issue, @PendingFeature, @Unroll, @Snapshot) to make Spock specs act as executable design documentation — each spec tied to the ADR, ticket, or design doc it exercises. Use this skill whenever the user is writing or refactoring a Spock test, drafting an ADR that should ship with an executable contract, pinning design decisions to tests, splitting a large spec, marking unimplemented behaviour as pending, or wants the test suite to read as a self-documenting checklist of what the design promises — even if they do not explicitly mention Spock annotations.
implementation-notes
by edmundmiller
Keep a running implementation-notes.html while implementing a spec. Use this whenever the user asks to implement a SPEC, PRD, design doc, issue, or feature and wants ongoing notes about design decisions, spec interpretations, deviations, tradeoffs, or open questions. Also trigger for prompts like “maintain implementation notes”, “document how this diverges from the spec”, or “capture anything I should know as you build”.
code-simplifier
by edmundmiller
Simplify and refine code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify", "clean up", "refine", or "tidy" code, or after a round of changes to polish recently modified code.
inspect
by edmundmiller
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.
pr-review
by edmundmiller
Review GitHub pull requests with structured analysis and gh CLI integration. Use when asked to "review a PR", "check my PRs", "review pull request", or help with code review workflows.
python-scripts
by edmundmiller
Use when writing standalone Python scripts (one-off scripts, utilities, not part of a larger Python project with pyproject.toml or setup.py). Provides UV shebang template and best practices.
tdd
by edmundmiller
"Write behavior-first tests in small vertical slices, with separate regression-test and fix commits for bugs."
tufte-test
by edmundmiller
Review charts with a simple Tufte-style rubric. Use when judging whether a chart is clean, honest, readable, and insight-forward, or when iterating on a visualization until it passes a concise quality bar.
ui-skills
by edmundmiller
Opinionated constraints for building better interfaces with agents.
weave
by edmundmiller
Entity-level merge with weave. Use when setting up weave, previewing merges, reducing false Git conflicts, or validating merge-driver behavior.
nixos-usb-recovery
by edmundmiller
"Recover or rebuild an installed NixOS system from a NixOS USB/live ISO. Use for boot failures, broken generations, bootloader repairs, or rescue rebuilds."
pi-nix-syntax
by edmundmiller
Use when converting Pi config/extension/skill setup (Pi settings.json packages, ~/.pi/agent/extensions, git:... sources) into this dotfiles repo's Nix representation (skills-catalog/agent-skills-nix, modules/agents/pi/default.nix home.file links), or converting the other direction.
agenix-secrets
by edmundmiller
Create, edit, and wire up agenix-encrypted secrets in this dotfiles repo. Use when adding API keys, tokens, credentials, passwords, or any sensitive values to NixOS host configs. Trigger phrases: "add a secret", "encrypt with agenix", "new age secret", "hide this value", "agenix secret".
hass-declarative
by edmundmiller
Manage Home Assistant automations, scenes, and scripts declaratively via NixOS modules. Covers adding/editing/removing entities in the domain-based Nix structure, the ensureEnabled wrapper (initial_state enforcement), the sweep service that cleans orphaned entities, entity identity (IDs, slugs, unique_ids), the eval test assertions, and the build-time manifest. Trigger phrases: "add HA automation", "new scene", "new script", "remove automation", "declarative HA", "sweep unmanaged", "entity drift", "ghost entity", "orphaned automation", "HA domain file", "eval-automations test", "hass assertion", "ensureEnabled", "initial_state".
ghostty-config
by edmundmiller
Use when configuring Ghostty terminal emulator, working with ghostty config files, or looking up Ghostty settings and options.
jj-merge-repos
by edmundmiller
Merges two separate Jujutsu (jj) repositories into one. Use when combining repos, rebasing one repo onto another, or recovering from diverged histories.
oracle
by edmundmiller
Use Oracle to bundle prompts + files for another AI (GPT 5 Pro, etc.) when stuck, debugging, or reviewing. Also covers self-improvement — codifying learnings into agent memory and noting tool improvement ideas.
hass-config-flow
by edmundmiller
Interact with Home Assistant via the REST API on a NixOS host. Use when adding integrations, querying entities, managing config flows, creating API tokens, or automating HA setup programmatically. Also covers identifying device protocols (Matter, Zigbee, Thread, HomeKit) from the device registry. Trigger phrases: "add HA integration", "configure home assistant", "query HA entities", "create HA token", "HA REST API", "pair homekit", "set up matter in HA", "add spotify to HA", "is this device zigbee or thread", "what protocol is this device", "move devices to ZHA", "identify matter devices".
jut
by edmundmiller
"Jujutsu version control through jut, a human and agentic framework around jj. Use for: check status, view changes, commit work, create branches, push, pull, create PRs, squash commits, reword messages, absorb changes, undo operations, view history. Complements jj — use jut for opinionated workflows, drop into raw jj for everything else."
nix-rebuild
by edmundmiller
Rebuild nix-darwin/NixOS system after dotfiles changes. Use when config files managed by Nix (lazygit, ghostty, etc.) need to be regenerated, or after editing any .nix file in the dotfiles repo.
nix-platform-specific-options
by edmundmiller
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.
tmux-status-debug
by edmundmiller
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.