Explorar skills

Setup, configure, audit, and modernize Vitest testing in projects. Use when creating new test configs, auditing existing Vitest implementations for v4.0+ best practices, fixing deprecated patterns, migrating from Jest, or configuring test environments (Node.js, browser, monorepo). Checks for breaking changes, outdated configs, missing coverage settings, and performance issues. Covers browser mode,

Read-only audit of vault/wiki/ for structural and provenance drift. Reports Errors, Warnings, and Info per the rules in /SPEC.md §13 and vault/CLAUDE.md. Trigger when the user says "lint the vault", "audit the wiki", "check for broken links", "run a health check on the wiki", or invokes /llm-wiki-stack:llm-wiki-lint directly. Does not repair anything — that is /llm-wiki-stack:llm-wiki-fix.

Query the wiki and render the answer as portable, GitHub-flavored markdown saved under vault/output/. Trigger when the user asks to "export X as markdown", "produce a markdown brief", "save the answer to the output folder", "give me a plain markdown version of …", or invokes /llm-wiki-stack:llm-wiki-markdown directly. Reuses the llm-wiki-query reading contract, then strips Obsidian-only syntax so

Guide for writing expressive, behavior-focused tests following Vladimir Khorikov's testing principles. Apply when writing, reviewing, or renaming any test (unit, integration, e2e) in any programming language. Triggers: writing tests, creating test files, adding test cases, reviewing test names, 'test naming', 'rename tests', 'Khorikov', or any test creation task. Covers: naming conventions (plain

Deploy TenantFlow to staging or production on Vercel. Handles build, test gate, and Vercel deployment.

Show current project state for TenantFlow. Reports what's done, in progress, blocked, failed, and next. Run any time to see where the project stands.

Audita, cria ou reescreve CLAUDE.md e README.md. Garante que CLAUDE.md seja minimalista e apenas para operadores, complementando o CLAUDE.md global, e que README.md esteja pronto para publicação no GitHub, também autocriando arquivos ausentes a partir de modelos.

Draft, rewrite, and review Git commit messages using Conventional Commits and commit hygiene rules. Use whenever the user asks for commit text, commit message fixes, type/scope selection, breaking-change notation, trailers (for example See or Co-authored-by), splitting work into atomic commits, or commit readiness before a PR, even if they ask in informal terms like "polish this commit message".

Auto-repair what /llm-wiki-stack:llm-wiki-lint reports. Idempotent — running twice on a clean tree produces no diff. Trigger when the user says "fix the lint errors", "repair the wiki", "auto-fix", or invokes /llm-wiki-stack:llm-wiki-fix directly. Expects a fresh lint report in context, or runs its own lint pass internally.

Run the TenantFlow test suite. Vitest unit tests and Playwright e2e tests.

Ingest one or more sources from vault/raw/ into typed wiki pages under vault/wiki/. Trigger when the user says "ingest this source", "process the file I just dropped in raw/", "add this to the wiki", or invokes /llm-wiki-stack:llm-wiki-ingest directly. Prefer the pipeline (/llm-wiki-stack:llm-wiki-stack-ingest-agent) unless the user has asked to skip lint-fix and synthesis.

Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing, decisions, strategy, study plans, life choices, brainstorming. Orchestrates an automatic back-and-forth debate where both agents critique, propose alternatives, and iterate on the user's idea until reaching consensus. Codex CLI runs READ-ONLY, forms its own opinions, and normally do