comment-curator
claudeLifecycle review of code comments: verifies them against the code they describe, deletes noise, keeps load-bearing constraints. Diff-scoped by default, path-scoped on demand.
1 skill · 1 agent
Claude Code and Codex plugins their authors filed under "quality". All categories.
Lifecycle review of code comments: verifies them against the code they describe, deletes noise, keeps load-bearing constraints. Diff-scoped by default, path-scoped on demand.
1 skill · 1 agent
Test automation: browser end-to-end flows and load/stress/soak profiles, gated in CI.
2 skills
AI-powered architectural review and code quality analysis
1 command · 1 agent
AI-powered architectural review and code quality analysis
1 command · 1 agent
Review the working diff before you commit: correctness, tests, and risk, with file and line references.
1 skill · 1 command
A test-first agent: writes the failing test, then the smallest change that passes it.
1 command · 1 agent
Blocks edits to committed migrations and warns on the structural invariants this system depends on.
1 skill · hooks
Defect reporting and submission workflow with dispatch contract support. Reporter skill conducts structured interviews, auto-generates reproduction steps via headless Playwright (visual bugs; plugin bridge, CI-safe) or code tracing (API bugs), cross-references requirements, and classifies as true defect, story update, or feature request. Broad trigger coverage: bugs/issues/problems/regressions, change and story updates, and concrete feature requests against existing product (not greenfield requirements). Supports dispatch from orchestrators with page URL (visual) or API endpoint identity (non-visual). Organizer skill submits to GitHub, Jira, Linear, or GitLab with system-native formatting and requirement traceability. Screenshot attachments upload to GitHub (shared defect-evidence release) and Jira (native attachments) with inline rendering.
2 skills
Plan or audit a project's software-quality posture across the whole method space — types, static analysis, tests of every kind, contracts, fuzzing, monitoring, formal methods, code review, supply-chain. Reframes "what tests should I write?" as "what uncertainty needs reducing?"
2 skills
Corrects how Python type annotations get written by default: type the boundaries with pydantic instead of bypassing them, narrow instead of casting, generate types tools can generate, and don't launder Any past a strict checker. Targets pyright and mypy.
2 skills
Enforce software development constitution - kadoppe's principles and standards
1 skill
QA artifact generator — point it at a PR or give freeform instructions. Navigates the UI, captures screenshots, stitches a GIF.
1 skill
Two hooks that block the two mistakes that cost the most: swallowing a huge file into context, and letting a shell silently corrupt a text file.
hooks
Find where your coding agent's work gets done twice - deep stacks of unverified edits, retry loops, and tools that keep erroring.
1 skill
Install the ratcheted quality-gate methodology into a TypeScript + pnpm repo: 12 gates, 6 ratchets, ast-grep invariants, secrets pre-commit hook, ADRs with mandatory enforcement, and a CI quality job. Nx optional — it powers the tag-based module-boundaries gate.
1 skill
Scan web pages for WCAG 2.2 failures with axe-core plus an LLM judgment pass, and fix what it finds.
1 skill
Audit the UI you just built — contrast, tap targets, type scale, copy, scan patterns, resilience — and fix it without leaving the agent. Every finding names its rule, the source line, the selector, and the exact change to make.
1 MCP server
Blocks multi-line or >7-word comments in new/edited code
hooks
Skeptical code review agent that assumes code is wrong until proven otherwise. Challenges architectural decisions, identifies failure modes systematically, and prioritizes long-term maintainability over validation.
1 agent
Your agent says it is done. This checks whether anything actually happened - audited from your own session transcripts.
1 skill
Find where your coding agent's work gets done twice - deep stacks of unverified edits, retry loops, and tools that keep erroring.
1 skill
Adds a skill for reviewing code quality, security, and performance
1 skill
DDD domain layer implementation guide based on Evans / Vernon: brand types, companion objects, discriminated unions, Result-based error handling, Value Object / Entity / Aggregate / Domain Event / Domain Service patterns
1 skill
Visualize a TypeScript DDD codebase: AST analysis, interactive HTML viewer (layer + ER views), Mermaid markdown for PR attachments
1 skill
One strict behavior-preserving review of a diff: how the code reads, and how it is shaped
1 skill
Subject every non-trivial decision to a fresh-context adversarial review before it stands. For when correctness matters more than speed: unfamiliar code, production, security-sensitive logic, irreversible operations.
1 skill
Zero Leak L1: Map blast radius before starting any task.
1 skill
Zero Leak L2: Enforce rules during implementation.
1 skill
Zero Leak L3: Independent inspector before presenting to user.
1 skill
Code quality hooks — auto-formatting, linting, file protection, context recovery, and subagent orientation.
hooks