Agent skill
oracle
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.
Install this agent skill to your Project
npx add-skill https://github.com/edmundmiller/dotfiles/tree/main/.agents/skills/oracle
SKILL.md
Rules
The Oracle
- Oracle bundles a prompt plus the right files so another AI (GPT 5 Pro + more) can answer. Use when stuck/bugs/reviewing.
- Run
npx -y @steipete/oracle --helponce per session before first use.
Self-improvement
- Continuously improve agent workflows.
- When a repeated correction or better approach is found, codify it:
- Global rules (apply to all agents/projects): add a numbered
.mdfile in~/.config/dotfiles/config/agents/rules/(e.g.09-<name>.md). These get concatenated into every agent's system prompt at rebuild (hey re). Keep rules short (<500B) — if longer, make a skill instead. - Project-specific memory (pi only): use
memory_writetosystem/style.md,system/project.md, orreference/<topic>.md.
- Global rules (apply to all agents/projects): add a numbered
- No prior approval needed for codifying learnings.
- When applying a previously codified rule in a future session, call it out and tell the user which rule triggered the behavior.
- Echo back any new learnings to the user when writing them.
Tool-specific memory
- Actively think beyond the immediate task.
- When using or working near a tool the user maintains: if you notice patterns, friction, missing features, risks, or improvement opportunities, jot them down.
- Do not interrupt the current task to implement speculative changes.
- Write notes via
memory_write(pi) or directly to files:reference/ideas/<tool-name>.md— new concepts or future directionsreference/improvements/<tool-name>.md— enhancements to existing behavior
- These notes are informal, forward-looking, and may be partial.
- No permission needed to add or update these files.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
zbench
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".
nix-rebuild
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.
hass-config-flow
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".
hass-declarative
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".
agenix-secrets
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".
linear
Read-only Linear issue access via the Linear GraphQL API.
Didn't find tool you were looking for?