attunehq

Use when working in a repository that uses eph for ephemeral dev services (a `.eph` file exists, or `eph` is on PATH). Covers workspace detection, strict .eph parsing, auto-assigned ports, up/env/down/clean, roles, hooks, one-off commands, foreground and watch sessions, logs, and stale-workspace pruning.

Use when working in a repository that uses eph for ephemeral dev services (a `.eph` file exists, or `eph` is on PATH). Covers workspace detection, strict .eph parsing, auto-assigned ports, up/env/down/clean, roles, hooks, one-off commands, foreground and watch sessions, logs, and stale-workspace pruning.

Apply Alexis King's "Names are not type safety" advice in eph. Use when adding, reviewing, or refactoring Rust newtypes, wrapper structs, workspace or process identities, service names, paths, command text, state records, domain enums, smart constructors, or APIs that rely on naming conventions for correctness.

Apply Alexis King's "Parse, don't validate" design rule in eph. Use when adding or reviewing Rust boundary code for .eph text, persisted JSON state, CLI arguments, environment variables, process identities, Compose output, release metadata, or any function that checks input validity before deeper processing.

Maintain eph's Rust architecture documentation in the Matklad Rust100k style. Use when changing module boundaries, the CLI/library split, parsing, workspace identity, lifecycle or state ownership, process control, pruning, bundled skills, updates, docs/developer-guide/architecture.md, docs/developer-guide/internals.md, or when reviewing whether code structure and architecture docs agree.

Apply Matklad Rust100k build-time, inline, workspace, and generic-boundary guidance to eph. Use when changing Rust crate structure, public generic APIs,

Apply Matklad Rust100k testing discipline to eph. Use when adding, reviewing, or reorganizing Rust tests, choosing unit versus Docker integration or stress coverage, designing fixtures, rejecting mocks, adding doctests, or changing Makefile and CI test coverage.

Rust-inspired TypeScript patterns. Must use when reading or writing TypeScript/JavaScript files.

Creating and maintaining CLAUDE.md project memory files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't obvious from code inspection.

Use Bun instead of Node.js, npm, pnpm, or vite. Provides command mappings, Bun-specific APIs, and development patterns.

Configure Bun's built-in test runner with Jest-compatible APIs. Use when setting up testing infrastructure, writing unit/integration/snapshot tests, migrating from Jest, or configuring test coverage. 3-10x faster than Jest.

Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.

Use for Nudge hook feedback and repo Nudge setup, `.nudge` rules, validation, CI, and rule debugging.

Use during repo debugging to search `.nudge/learned` before investigating, apply relevant notes, and record durable fixes with `nudge learn add`.

Use for Nudge hook feedback and repo Nudge setup, `.nudge` rules, validation, CI, and rule debugging.

Use during repo debugging to search `.nudge/learned` before investigating, apply relevant notes, and record durable fixes with `nudge learn add`.

Rust programming style guide and conventions. Use this skill when writing, reviewing, or modifying Rust code. Covers string creation, type annotations, control flow, naming conventions, imports, error handling, and Rust-specific best practices.

Rust testing patterns and best practices. Use this skill when writing, reviewing, or modifying Rust tests. Covers test organization, assertions with pretty_assertions, parameterized tests, and testing multiple input formats.

System for externalizing large task context to .scratch/tasks/ files to maintain continuity across context compactions and session resets. Use this skill when starting large/complex tasks, after /compact or /new commands, or when context window is getting full during multi-file work.