dotfiles

Use when handed a set/batch of iterations, plans, or work slices to carry out end to end in one run — multiple iteration/story IDs to execute, ordered by blocking edges, each with review, commit, and doc-status transitions, until the whole set is done. lazyspec or any DAG-backed backlog.

Interview the user relentlessly about a plan or design. Use when the user wants to plan/design a system, break down a problem, or asks an open question.

You MUST use this skill when authoring an iteration, work slice, or "iteration document" that hands a bounded unit of work to a coding agent — drawn from a story, card, spec, or backlog. Symptoms include an iteration that bundles several acceptance criteria, restates a spec it links to, or won't finish in one agent session.

You MUST use when writing a story/user story; when decomposing a system, feature, epic, requirement, or spec into a backlog of user stories, or whenever about to write user stories or acceptance criteria during planning. Symptoms include "break this into stories", "write the backlog", "split this epic", stories that feel too big to estimate, or technical tasks masquerading as stories.

You MUST use this skill any time you are investigating a bug/unintended behaviour, before proposing fixes

Use when comparing a running web UI against its intended design (Figma mockups or reference screenshots), reviewing visual/layout/spacing/typography fidelity of a page, component, or interaction, or when a design-vs-build diff is needed before shipping or to feed a fix loop.

Use when adding, installing, upgrading, or pinning a package/library in any language, choosing which version to use, or when install commands fail with externally-managed-environment, SSL/certificate, DNS (gaierror), or connection errors inside a sandbox.

Use when opening a pull request with gh, writing a PR title/body, or pushing finished work for review

Use when structuring React components — composition over configuration, state ownership and colocation, hook design, render/effect boundaries, and prop API design.

Use when restructuring existing code without changing behavior — extracting functions/modules, decoupling, removing duplication, and improving names while keeping tests green.

Use when designing, structuring, or reviewing tests — deciding what to test, choosing test doubles/fakes, organizing suites, or driving implementation test-first (red-green-refactor TDD). Trigger this whenever you are about to write or change tests, add a feature that needs coverage, or are asked "how should I test this?", even if the user does not say the word "test".

Use when modeling a domain with the type system to make illegal states unrepresentable — discriminated unions, exhaustive matching, newtypes/branded types, and Result/Option error modeling in TypeScript and Rust.

Use when searching for structural code patterns - function signatures, struct/class definitions, trait implementations, specific argument patterns, or any query where text grep would require complex regex or produce false positives. Prefer over Grep when the search target has syntactic structure.