wyattowalsh

Authorized pentest planning with mandatory ROE scope gate. Synthesizes phase checklists and findings. NOT for static audit (security-scanner), CTF labs (ctf-*), or C2/webshell tooling.

Operate MCPHub groups, endpoints, compression, and CLI from repo registry. Use for hub preflight, group picking, tunnel vs local exposure. NOT harness sync.

Use for session, scoped, PR, range, full audit, simplification, and source/provenance reviews with evidence-first findings. NOT for feature implementation or benchmarking.

Deep multi-source research with reviewable plans, source-support auditing, and confidence scoring. Use for technical, academic, market, fact-checking investigation. NOT for code review or simple Q&A.

Extract clean article text and metadata from URLs or HTML with trafilatura CLI. Use for single-page extraction, piped/local HTML, bounded discovery. NOT for research synthesis (research), PDFs (docling), raw fetch (fetch), video (yt-dlp).

Plan cross-harness skills sync dry-run steps before any live install. Use when reconciling harness skill inventory. NOT for --apply or npx installs.

Phase 1 dry-run JSON smoke and phase 2 temp-HOME install smoke for skills sync. Use when validating cross-harness install parity. NOT for live --apply installs.

Summarize bundle components from agent-bundle.json and repo skill/agent counts. Use when packaging or auditing distributable bundles. NOT for live plugin installs.

Compose and manage MDX blog posts from topics, URLs, GitHub repos, or project paths. Use when writing, editing, auditing, refreshing, or ideating posts. NOT for docs or changelogs.

Unified blog post manager for this Next.js MDX site. Compose new posts from topics, URLs, or project links; update or refresh existing posts; list posts; audit SEO and quality; and brainstorm ideas. Use when asked to "write a post about", "blog about", "new post", "list posts", "blog status", "edit post", "audit blog", "check SEO", "refresh post", or "brainstorm topics". NOT for non-blog content, docs sites, or changelog generation.

Generate, refine, critique, and explain p5.js v2.2.1 sketches for a sandboxed generative art studio. Six modes: create complete sketches from natural language descriptions, refine existing code, generate variations, critique visual quality, explain techniques, and fix errors. Encodes generative art algorithms (noise fields, particle systems, fractals, attractors, cellular automata, reaction-diffusion), performance constraints (100K loop limit, 5s watchdog), and anti-slop aesthetic rules that prevent cookie-cutter output. Use when creating, editing, optimizing, or analyzing p5.js sketches for the studio. NOT for GLSL shaders, WGSL compute shaders, general JavaScript, React components, or non-p5 canvas code.

Use when preparing the Riso repository for a production release, especially to coordinate no-legacy Copier answer cleanup, release gates, render validation, docs hardening, package dry-runs, and final evidence capture.

Scaffold Python/Node/full-stack projects from the Riso Copier template using the `riso` CLI. Use when the user wants to generate a Riso project, run copier copy/update, validate copier-answers.yml, list template variants, explore module catalog, or scaffold from the riso template. Triggers: "scaffold riso", "riso template", "copier copy riso", "generate riso project", "riso variants", "validate copier answers".

Maintain docs across Starlight, Docusaurus, MkDocs. Sync, health checks, migrations, ADRs, runbooks. Use when docs change. NOT for backend code, skills (skill-creator), or MCP servers (mcp-creator).

Curate proxywhirl proxy sources — prune broken/stale/duplicate sources and discover new high-quality ones via web research. Syncs all downstream files: sources.py, tests, docs, and reference inventories. Use when asked to update, clean up, audit, curate, or refresh proxy sources.

Maintain docs across Starlight, Docusaurus, MkDocs. Sync, health checks, migrations, ADRs, runbooks. Use when docs change. NOT for backend code, skills (skill-creator), or MCP servers (mcp-creator).

Hosts interactive expert panel discussions on any topic. Dynamically generates diverse master-level expert personas, facilitates structured multi-round debate using Hegelian dialectic patterns, and synthesizes actionable consensus. Useful for exploring complex topics, making architectural decisions, evaluating trade-offs, or seeking diverse expert perspectives on strategic questions.

Maintains this repo's README prompt catalog: copyable prompt recipes, pattern notes, paste-zone tables, generated ShieldCN badges and icon-only recipe headings, provider-doc freshness, safety/eval hygiene, and GFM polish. Use when auditing, enriching, updating, validating, or syncing README.md badge surfaces. NOT for running prompts, MCP servers, unrelated docs, or unsupported badges.

Create setup-gated FL MCP production workflows for FL Studio: setup, mock rehearsal, live execution, render, and audio evidence. Use when producing or verifying projects through fl-mcp. NOT for server code, public MCP tools, DB, pipelines, UI, or tutorials.

Use `/spicetify <prompt>` for safe local Spicetify customization, existing plugin/theme research, audit, repair, dry-run plans, rollback, and eval-driven evolve workflows. Always infer the safest next artifact, never arbitrary shell, and never install, trust, or run third-party code without audit and confirmation.

Generate, revise, and convert paste-ready email drafts for Copy to Gmail. Use when composing Gmail messages through gmail-composer. NOT for inbox triage, sending, Gmail API automation, or raw HTML.

Use when an agent needs to compare public GitHub repositories, shortlist OSS projects, or produce provenance-backed repo reports with the keyless CLI, typed schema, HTML dashboard, and ChatGPT App bridge. NOT for private repo audits, paid-source research, or changing repositories.