Quality plugins

Auto-run golangci-lint on package when Go files are edited

hooks

Hook that guards commit trailers on the current branch: after a command that writes, moves or publishes commits it flags your own commits that lost Signed-off-by, carry a Claude-Session line, or name a model in Assisted-by instead of the neutral Assisted-by: LLM, and it blocks git push, git send-email, git send-pack, git imap-send, git subtree push, git svn dcommit/set-tree, git p4 submit, gh pr create/ready/merge and gh stack submit/sync/push/merge/link until they are fixed; a branch stacked on another local branch is judged and repaired from that branch's tip, and the repair recipe rewrites only your commits

hooks

SessionStart hook that injects code-comment discipline into every session — every comment must earn its place: say what the code cannot, never duplicate it; bans narration, changelog comments, reviewer asides, signature-restating docstrings, and leaky provenance

hooks

Dev Life Cycle quality gates: security scans, code quality, performance analysis, test coverage, and PR review compliance with automated GitHub issue creation

9 skills

Comprehensive validation for Claude Code marketplaces and plugins with quality scoring, security scanning, and automated checks

6 skills · 33 commands · 1 agent · hooks

Quality assurance and testing expertise for manual testing, test automation, performance testing, and comprehensive test planning.

4 skills · 2 agents

Quality governance - agent evaluation, quality tracking, lessons learned

3 skills · 1 command

Test strategy and implementation: unit/integration/e2e, TDD, mocking, fixtures, and coverage.

1 skill

Systematic debugging: reproduction, hypothesis testing, bisection, logging, and root-cause analysis.

1 skill

Safe, incremental refactoring: code smells, behavior-preserving transforms, and test-backed changes.

1 skill

Detects uncertain language in Claude's responses and reminds it to investigate before guessing.

Blocks general-purpose Agent calls (redirecting to spawn-claude) and Agent resume calls (preventing polling loops).

Detects correction phrases in user prompts and reminds Claude to call advisor before its next substantive response.

Complete quality skills for ESLint, SonarQube, dead code, technical debt, and quality decision workflows.

17 skills

Dead-code and SonarQube skills for orphan files, unused exports, dead branches, complexity, duplication, coverage, and gate triage.

8 skills

Lint-focused quality skills for ESLint baseline hardening, disable governance, and safe autofix cleanup.

6 skills

Multi-perspective code analysis covering architecture, security, and best practices

2 commands · 3 agents

Performance analysis, test coverage review, and AI-powered code quality assessment

2 commands · 2 agents

AI-powered architectural review and code quality analysis

1 command · 1 agent

Formats every file Claude edits with the right formatter for its language.

Runs the linter on each edited file and hands the errors straight back to Claude.

Runs the tests related to what changed and shows pass/fail in the status line.

Execution-first delivery pipeline: brainstorm -> plan -> decompose into proof-carrying tasks -> implement -> end-user test -> audit, with no-mock discipline and a live execution ledger.

19 skills · 7 commands · 3 agents · hooks

RGAA 4.1.2 accessibility audits on a WCAG 2.2 AA core: automatic review before commit, push and pull request, plus dated, evidenced Markdown, HTML and per-page conformance reports in Claude Code.

2 skills · hooks

Detects correction phrases in user prompts and reminds Claude to call advisor before its next substantive response.

Blocks general-purpose Agent calls (redirecting to spawn-claude) and Agent resume calls (preventing polling loops).

Provides a research subagent with anti-hallucination guardrails for investigating external projects, GitHub discussions, and technical questions.

Manifest-driven, model-aware, test-driven audit/fix pipeline: /audit:* execution (status, next, run, phase, review, resume, report), /audit:init multi-agent manifest generation, /audit:task + /audit:bug tracking (red-first TDD bug fixes), /audit:sync Azure DevOps work-item sync, /audit:usage token spend attributed by phase/task/model/author (cache economics, cost-per-task, trend), /audit:panel browser control panel for config + composition + usage, /audit:layout manifest layout either way (sharded = fewer tokens + parallel-safe phases across worktrees, single-file = one file and one diff), /audit:worktree list/add/remove/sweep for the git worktrees a plan owns (sweep is read-only until --apply and reaps only what the plugin itself created for a phase that has signed off), /audit:doctor setup diagnostics, plan-first + secret-safety + TDD-reminder hooks. Configure per-repo via .claude/audit.config.json.

2 skills · 21 commands · 4 agents · hooks

Slopocop communication layer for clear development replies, plus targeted RU/EN prose editing across agents. Three skills: slopocop for concise, technically precise replies, questions and progress; humanizer-ru for Russian text; slop-humanizer for English text or requested prose. Use when improving agent communication, humanizing text or auditing prose. Adds to existing instructions through Claude Code hooks, trusted Codex hooks, an OMP extension or a host-neutral startup-instruction installer. Editorial commands and the slop-cop reviewer remain Claude-native. No per-reply editor, evaluator or runtime network downloads.

3 skills · 2 commands · 1 agent · hooks

Slop cop for design — stops UI from looking AI-generated. The design counterpart to slopocop (text). Ships hallmark (anti-AI-slop design engine: 58-gate slop-test, 21 macrostructures, 50 components, audit/redesign/study) plus two taste skills (frontend-design by Anthropic, design-taste-frontend), two commands (/design-audit ranked slop findings with no edits, /design-redesign a fresh visual take that preserves routes/copy/logic), and an on-demand design-cop reviewer agent. No hook by design — laws-of-ux already nudges on frontend edits. Use when building or redesigning a page, or auditing UI for templated slop. Text slop lives in slopocop. v1.1.0: Каждый агент пакета получил секцию `## Model tier`: какой ЯРУС нужен его работе и почему ярус задаёт самая трудная стадия, а не самая частая. Там же сказано, что значение `model:` во фронтматтере — привязка Claude Code, а не требование: в OMP/OpenCode/Codex/Gemini этих имён нет, надо подставить модель своего яруса и при промахе промахиваться ВВЕРХ. Лестница ярусов — `docs/GUIDE-AI-SDLC-PDLC-RU.md` §6.2, здесь она не пересказывается.

3 skills · 2 commands · 1 agent