js-refactor-logic

Frame A/B tests with falsifiable hypothesis, variants, pre-committed primary/secondary/guardrail metrics, MDE, sample size (formula shown), duration spanning a weekly cycle, peek policy, pre-committed decision rule, validity risks with mitigations, and ethics review. Mermaid diagrams with optional PNG export.

1 skill

Write, audit, or split acceptance criteria for a user story. Given/When/Then (Gherkin) default + rule-based + mixed formats. Systematic coverage (happy path + negative + edge + boundary + a11y + optional performance/security/data/integration). INVEST at story + AC level. SPIDR split (Spike / Path / Interface / Data / Rule) when story too big. Scenario outlines for parametric data. Mermaid coverage pie + split diagrams with optional PNG export.

1 skill

Define accessibility requirements against WCAG 2.2 AA (default), AAA, EN 301 549, EAA, Section 508, ADA. Produces per-feature Given/When/Then criteria, assistive-technology support matrix per platform, combined automated + manual + AT + user-testing plan, and remediation priority for existing products. Not a conformance audit. Mermaid diagrams with optional PNG export.

1 skill

Write, review, supersede, or index Architecture Decision Records. Michael Nygard format (default) + Y-statement alternative. Immutable once accepted — supersession chain preserves old ADRs. Status lifecycle (Proposed / Accepted / Deprecated / Superseded). ADR log with chronological index + supersession chains visible. Review mode flags stale ADRs + missing consequences. Integrates with traceability-matrix. Mermaid timeline with optional PNG export.

1 skill

Bottom-up thematic clustering of unstructured items (research notes, interview quotes, brainstorm ideas, feedback) using the KJ method. Discovers emergent themes with evidence traceability, identifies patterns/tensions/gaps, flags outliers, and prioritizes clusters by signal strength. Mermaid diagrams with optional PNG export.

1 skill

Algorithm design pre-implementation: problem + inputs/outputs + constraints, ≥2 candidate approaches compared on time+space+stability+in-place+parallelism, chosen approach with loop/data/global invariants, language-neutral pseudocode, correctness argument (invariant / induction / preservation / reduction), edge-case catalog, worst/avg/space complexity, numerical + concurrency concerns, property-based + boundary + performance + fuzz tests, parallelization + out-of-core + streaming variants.

1 skill

Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.

1 skill · 1 command · 1 agent

Build and deploy Base44 full-stack apps with CLI project management and JavaScript/TypeScript SDK development skills

9 skills

JavaScript and TypeScript development with ES6+, Node.js, React, and modern web frameworks

4 skills · 1 command · 2 agents

Build and deploy Base44 full-stack apps with CLI project management and JavaScript/TypeScript SDK development skills

9 skills

Comprehensive SEO analysis plugin for Claude Code. 26 sub-skills and 19 sub-agents, plus 9 optional MCP extensions. v2.6.0 adds deterministic page, TLS and header, sitemap and JavaScript-gap checks ported from web-obs; v2.5.1 merged 39 community fixes and raised the urllib3 floor for three advisories; v2.5.0 fixed Claude Desktop installs and hardened Google sign-in, page rendering and agent prompts; v2.4.2 added the seo-cockpit companion and gcloud sign-in; v2.4.1 brought Google guidance current through 2026-09-28; v2.4.0 added /seo agentic for agent readiness (Lighthouse Agentic Browsing, WebMCP, AI agent access).

33 skills · 19 agents · hooks

Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.