ghchinoy

CLI and agent skills for the A2A protocol: drive a2acli to discover/invoke/monitor A2A agents, and build/audit A2A-compliant services.

Best practices and architectural guidelines for CLI tools optimized for both human users and AI coding agents.

Authoring, migration, and linting tools for packaging Agent Skills into Agent Plugins v1.0.0 spec packages.

Specification-driven evaluation, deterministic capability linting, and synthetic test harness generation for Model Context Protocol (MCP) tool suites.

Virtual music artist production suite: lore planning, audio synthesis, visual design, web player compilation, and public endpoint deployment.

Deterministic vocal and instrumental audio stem separation using Meta HTDemucs.

Deterministic audio manipulation tools and deep learning stems separation for AI agents.

Framework and tooling for evaluating workflow, skill, and process automation readiness based on the Google DeepMind Intelligent AI Delegation framework.

Tools and workflows for the beads (bd) Dolt-powered issue tracking ecosystem, including diagnostics, repairs, and plan stress-testing.

Extract brand identities and DESIGN.md design systems from live websites and sources for downstream brand-consistent image generation.

Inspect and audit C2PA Content Credentials, cryptographic signatures, provenance assertions, and AI generation metadata across media assets.

Readability metrics for text, web pages, and PDFs, exposed as an MCP tool and skill.

Tolkien Elvish lexicon MCP tools and linguistic agent skills over Paul Strack's Eldamo compilation

Google Cloud Platform and Firebase project assessment, itemized BigQuery spend analysis, quota governance, and consolidation skills.

Modern Go and Google readability standards, style guidelines, code review checklists, and testing patterns.

Smart home audio plugin for Sonos speakers: discovery, compact track metadata, playback control, and volume management.

macOS Human Interface Guidelines assistance and code reviewers for layout, interactions, and HIG compliance.

macOS and SwiftUI application performance assessment: launch-time ("quick bounce") first-frame readiness, main-actor I/O, Swift strict concurrency adoption, view-model/business-logic separation, and steady-state render budget.

Model Context Protocol (MCP) security auditing for RCE, STDIO injection, and supply chain vulnerabilities.

Production-grade, dual-transport, zero-trust Model Context Protocol (MCP) server starter template in Go

Author metric-template packs for Mizan from an agent: scaffold a pack, create rubric/pointwise/pairwise/custom_schema templates via the mizan CLI, validate the pack creds-free (the CI PR gate), and run the export->PR->import collaborator loop; and generate a rubric from a brand book (suggest-first, agent-side synthesis) then freeze it into the registry. Use when you need to author, package, validate, or share a Mizan metric template or template pack, or to generate evaluation rubrics from a brand book or guidance document.

Run Mizan evaluations from an agent: score a single response or compare two responses against a metric template via the mizan CLI, reasoning over the -o json result. Use when you need to evaluate an asset/response against guidance and explain the verdict.

Expose the Mizan eval engine to agents and MCP clients as callable tools via the mizan mcp server. Registers a local stdio MCP server (mizan mcp stdio) advertising four tools — mizan_list_metrics, mizan_get_metric (read-only), mizan_eval_run, and mizan_eval_pairwise — plus an agent-in-the-loop eval skill. Use when an agent should discover a judge and run an evaluation over MCP rather than shelling out to the CLI.

Turn stored Mizan eval results into a self-contained, standalone HTML report from an agent: query results via the mizan CLI over -o json, aggregate client-side, and render a single offline report.html. Use when you need to review, summarize, or visualize past evaluation results as an HTML report.

Configure Mizan for first use from an agent: inspect the resolved configuration via the mizan CLI over -o json, persist project/location/default-model/results-store settings with config set, verify the CLI build with version, and check (never store) Application Default Credentials. Use when you need to set up or verify a Mizan environment before running live evaluations.

Assess existing applications and determine what Agent Ecosystem tooling can be built from them (Plugins, Skills, MCP Servers, and CLIs).

Tool-agnostic authoring and validation for conformant Open Knowledge Format (OKF) v0.2 knowledge bundles, including the v0.2 provenance, trust, and lifecycle vocabulary.

Drive the binder CLI to ingest a plain-markdown corpus into a conformant OKF v0.2 bundle and curate concepts at scale, with ingestion-analysis judgment (flag choice, pre-convert triage, trust-extraction review, the post-convert acceptance loop over binder's --json output). Assumes binder is installed.

Repository management skills for technical writing, editorial report artifacts, README generation, changelog curation, and commit recaps.

Map public GitHub repositories into structured concept graphs and AI-suggested domain taxonomies.

Scion platform administration, Hub bootstrap and GCE reconciliation, authorization and broker quota diagnostics, zero-downtime agent token re-minting, fleet model assessment, live model patching, and server lifecycle operations.