ivuorinen

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

Scaffold a new helper script in local/bin/ with proper boilerplate, msgr sourcing, and documentation tag.

Scaffold a bats test file in tests/<script>.bats matching a script in local/bin/<script>. Use when adding tests for an existing script that lacks coverage.

Scaffold a new theme handler in config/theme/handlers.d/<app>. Use when adding dark/light theme support for an app the orchestrator does not yet flip.

Validate fish scripts after editing. Apply when writing or modifying any .fish file in config/fish/.

Scaffold a new fish function in config/fish/functions/ with proper conventions and event handling.

Deterministic adversarial code review focused on provable failures. Optimized for agent execution, minimal tokens, and high signal findings across web applications.

Validate Dotbot install.conf.yaml files after editing. Apply when writing or modifying any install.conf.yaml.

Comprehensive health check for a single action

Scaffold a new GitHub Action with all required files

Deterministic adversarial code review focused on provable failures. Optimized for agent execution, minimal tokens, and high signal findings across web applications.

Generate a changelog for a specific action or the whole repo

Compare two actions for pattern consistency

Verify all action references are properly SHA-pinned

Run security analysis across all or a specific action

Create a new CalVer release with validation checks

Hostile audit toolkit: one entry point dispatching specialist commands — adversarial review, security, tests, docs, architecture, performance, dependencies, error handling, CI, commits, migrations, observability, API contracts, a11y, privacy, config, resource leaks, i18n, concurrency, unwired code, PR review and review-comment implementation. Use when auditing or reviewing a repository, PR, or any quality dimension of a codebase — "audit this", "review the whole codebase", "find all problems", "exhaustive review", "/nitpicker <command>", a release gate check, or any specific audit ask (security scan, find race conditions, audit the tests, review the PR, fix the CR comments).

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

Routes audit requests to the right /nitpicker command. Use when the user wants to run one of the hostile audit commands in this repo, or asks what audit commands are available.

Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.

Use when creating a new hostile audit command for the nitpicker skill in this repository.

Use when validating that all changes in the current branch are ready to be included in a release PR managed by release-please automation.

Use when verifying that a skill actually changes Claude's behaviour — runs TDD pressure scenarios against a skill before and after writing it.

Add a new ShellSpec grammar rule with tests, following project conventions

Debug a ShellSpec parse failure by identifying ERROR nodes and tracing to grammar rules

Generate parser from grammar.js, run all tests, and verify spec files parse cleanly

Update highlights.scm to cover all grammar rules, detecting missing patterns

Run full pre-release validation - tests, spec parsing, highlight coverage, build

Run test coverage check and report per-package breakdown highlighting packages below the 72% gate and 80% new-code target

Scaffold a new YAML test fixture and register its path constant in testutil/test_constants.go

Run gremlins mutation testing on a specified Go package, following the same pattern as make test-mutation

Scaffold a new documentation theme following the project's theme registration pattern from CLAUDE.md

Run all project security scans (make security) and summarize findings by tool and severity

Run lint, phpstan, and tests in sequence, fix any issues found

Generate a Pest test for a PHP class following project conventions

Create a new final readonly DTO class with Valinor-compatible constructor

Run dedup in dry-run mode and report duplicate groups found

Regenerate README.md and index.html from emoji/ contents and verify output

Build PHAR executable and run smoke test

Run full pre-release verification suite

Generate table-driven Go tests matching gh-history project conventions