ivuorinen
UserMy assortment of Claude Code skills
Categories
Indexed Skills (17)
release-prep
Use when validating that all changes in the current branch are ready to be included in a release PR managed by release-please automation.
skill-tester
Use when verifying that a skill actually changes Claude's behaviour — runs TDD pressure scenarios against a skill before and after writing it.
validate-skills
Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.
skills
Use when the user wants to run one of the hostile audit skills in this repo, or asks what skills are available.
adversarial-reviewer
Performs hostile code review assuming bugs exist, hunting for logic errors, edge cases, security flaws, and missing tests. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this".
arch-auditor
Audits a codebase for architectural violations against detected or declared patterns and writes a structured findings report. Use when auditing a codebase for architectural violations, dependency rule breaches, layer boundary violations, or pattern inconsistencies. Triggers: "audit the architecture", "find architecture violations", "check layer boundaries", "run arch-auditor", "are there any DDD violations?", "check hexagonal boundaries".
arch-detector
Detects which architectural patterns a codebase uses and produces docs/audit/arch-profile.md with inferred structural rules. Use when you need to identify which architectural patterns a codebase uses, understand its structural boundaries, or generate an architecture profile before auditing. Triggers: "what architecture is this?", "detect the architecture", "profile this codebase", "what pattern does this follow?", "run arch-detector".
claude-rules-auditor
Audits .claude/rules/ files for quality and suggests new rules from project conventions and audit artifacts. Use when auditing .claude/rules/ files for quality and completeness, checking CLAUDE.md for rules that belong in .claude/rules/ instead, or discovering new rules from project conventions and audit artifacts.
cr-implementer
Fetches GitHub PR review comments, evaluates validity, and implements valid ones one at a time with test verification. Use when implementing unresolved GitHub PR review comments, when told "fix the cr comments", "implement review feedback", "address pr comments", or when a PR has unresolved reviewer comments that need addressing.
doc-auditor
Verifies all documentation accuracy against the codebase and writes a structured findings report. Use when verifying documentation accuracy against the codebase, finding stale or missing docs, detecting incorrect behavior descriptions, or applying documentation improvements. Triggers: "audit the docs", "find stale documentation", "verify docs against code", "run doc-auditor", "is the documentation accurate?", "find missing docs".
nitpicker
Performs adversarial, exhaustive whole-repository code review across code, tests, docs, and config, and optionally applies fixes. Use when performing a comprehensive repository audit, reviewing code before a release, checking a PR for all bugs and defects, or when asked to "review the whole codebase", "audit this", "find all problems", "exhaustive review", or run a release gate check.
pr-reviewer
Produces copy-paste-ready markdown code review with constructive criticism — problems, severity, and suggested fixes — formatted for GitHub PR comments. Use when reviewing a pull request, staged changes, or a specific diff.
security-auditor
Runs available security scanners, parses results, and writes a consolidated security findings report. Use when you need to check a project for vulnerabilities, exposed secrets, insecure dependencies, or other security issues. Triggers: "security audit", "run security scan", "find vulnerabilities", "check for secrets", "scan dependencies", "run security-auditor".
hooks-enforcer
Audits an agent project's hook coverage against its own evidence base — current hooks, audit-findings history, git history, and project memory — surfacing recurring failures that no hook guards and context-discipline gaps where large-output work bypasses a context-saving tool. Use when auditing which agent hooks a project should enforce, when asked to "enforce hooks", "harden hook coverage", or "make sure context-mode is used", and when invoked by nitpicker in loophole mode or by release-prep as a release gate.
loophole-hunter
Audits a Claude Code project's enforcement surface (rules, hooks, settings, permissions, skills) for bypassable or unenforced constraints and closes them. Use when auditing .claude/rules, hooks, .claude/settings.json, and skills for loopholes, when asked to close loopholes or harden the Claude Code setup against evasion, or when invoked by nitpicker in loophole mode.
release-check
Run full pre-release verification suite
fish-validate
Validate fish scripts after editing. Apply when writing or modifying any .fish file in config/fish/.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.