Claude Skills by nino-chavez

Find what a change could break outside its own diff before it ships, and prove the one fact its safety rests on by running real code instead of writing a convincing paragraph. Use when the user says "blast radius", "what could this break", "is this safe to merge", or hands over a small-looking diff they do not trust yet; also before shipping a change to a shared contract, schema, wire format, config, or dependency version. Complement to `symbol-surgery`, which covers the references a language...

Find architectural deepening opportunities in a codebase using Ousterhout's depth/seam/locality vocabulary and the deletion test. Use when user wants to evaluate whether modules pull their weight, surface shallow modules, identify refactoring opportunities, or improve testability and AI-navigability. Complement to the `simplify` skill — simplify reviews code quality, deepen evaluates module leverage.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Use when about to produce ≥2 substantive artifacts whose specs are fully derived in-thread and whose file scopes don't overlap. Codifies the orchestrator workflow for parallel agent dispatch — brief construction (nine mandatory fields, runtime isolation and cleanup included), model selection (Sonnet for execution-from-spec, Opus for judgment-bearing), inline work during wait, post-flight cross-review for inter-artifact consistency, and commit-and-push following the project's dev-push pattern....

Adversarial provenance audit of a draft deliverable before it ships — re-derive load-bearing claims at their sources, downgrade what fails. Use before publishing any client- or stakeholder-facing artifact containing numbers, ratings, prices, or "verified" language; or when the operator says "audit this", "check the claims", or "is this actually verified?"

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Preserve durable lessons and produce an archive-safety receipt before ending, clearing, or archiving an agent task. Use when the operator says close out, wrap up, end the session, prepare the task for archive, make it archive-ready, or invokes $session-closeout after substantive work.

Deploy, release, or run migrations against production for a project. Use when user says "deploy", "ship", "push to prod", "release", "run the migration", "apply migrations", or asks how a project gets deployed / where it lives. Reads per-project DEPLOY.md as source of truth; falls back to inference + offer to scaffold one.

Symbol-first refactoring discipline using the native LSP tool — locate by symbol, check blast radius before changing, edit at symbol boundaries, verify references after. Use when renaming, changing a signature, moving/extracting/inlining, or deleting code that other code depends on; or whenever the question is "where is this used and what breaks if I change it?" Mechanical-execution complement to `deepen` (which decides what to refactor) and `simplify` (which decides what's clean).

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.