claudecodex

handsonai

Everything you need to design, build, and document AI workflows. The AI Workflow Framework as executable skills, plus your business knowledge graph, an AI registry, and a feature-spec toolkit.

8 on GitHubby James Grayv10.4.0MITupdated 5 days agoProductivity
/

Plugin handsonai from marketplace handsonai in jamesgray-ai/handsonai-plugins. Commands read from the repo's manifest — 4 days ago.

What it installs

Skills (16)

  • analyze

    This skill should be used when the user wants to analyze AI workflow opportunities, run a workflow audit, find automation candidates, or says "where can AI help". With the user's permission, looks through their saved memory and past chats for opportunities, walks their processes, then registers ever

  • applying-skill-best-practices

    Best-practice standards for building Agent Skills on any platform: checking for an existing skill first, scoping it to one job, writing a description that triggers, keeping instructions lean, choosing model and effort settings, and preparing test cases from real examples. Use whenever a skill is bei

  • auditing-agent-skills

    Audits existing Agent Skills for things that have gone out of date or drifted: retired model names, references to skills that were renamed or removed, naming drift, weak descriptions, dated facts, overlapping skills, missing test cases, and skills the AI Registry doesn't record. Use when the user as

  • building-knowledge-graph

    This skill should be used when the user wants to build their knowledge graph — a knowledge/ folder of markdown pages about the work a person, team, or company does (clients, offerings, processes, people, tools, policies) that the AI maintains, following the Open Knowledge Format. Triggers: "build my

  • deconstruct

    This skill should be used when the user wants to deconstruct a workflow, break down a business process, capture requirements for an AI workflow, or turn a workflow from their backlog into a clear, testable description of what it must do. It starts from anything already written down, shapes the outco

  • design

    This skill should be used when the user has a workflow's requirements and wants to plan how AI will do the work: which parts are skills or agents, how much the AI decides at each step, where a person checks, what it connects to, and how each part will be checked. It writes a plan the Build step foll

  • indexing-registry

    This skill should be used to maintain the user's AI Registry — the registry/ knowledge bundle and its derived views (the REGISTRY.md dashboard, directory indexes, GENERATED blocks, and the visual HTML dashboard). Triggers: "update my registry", "check my AI registry", "refresh my registry", "lint my

  • naming-workflows

    This skill should be used when the user wants to name a workflow, write workflow descriptions, standardize workflow documentation, add a workflow to the AI Registry, or structure workflow entries. Generates consistent, outcome-focused names and descriptions for business workflows and records them in

  • publishing-plugins

    This skill should be used when the user wants to publish their skills and agents to their team as Claude plugins, or release a change to plugins they already publish. It keeps two GitHub repositories apart: the source repository where the user builds and changes skills and agents, and a plugin repos

  • scaffolding-registry

    This skill should be used when the user wants to set up their AI Registry as a knowledge bundle — a registry/ folder with SCHEMA.md and concept nodes for the workflows, processes, and functions of their business. Triggers: "set up my registry", "set up my AI registry", "create my registry", "scaffol

  • writing-ai-governance-policies

    This skill should be used when the user wants to write, review or update their company's AI governance policy: a short set of rules every AI workflow, skill and agent must meet, each with a named check. Triggers: "write our AI governance policy", "write our AI policy", "review our AI governance poli

  • writing-feature-prds

    Use when starting a new feature, defining requirements before implementation, or when the user says "new feature", "create a spec", "create a PRD", or "feature PRD".

  • writing-governance-records

    This skill should be used when the user wants to write or update the governance record for one AI workflow: where it stands on each of the eight governance practices (name and description, ownership, process, building blocks, evaluations, SOP, operations, change management), with every gap turned in

  • writing-process-guides

    Write Business Process Guide documentation that explains when, why, and how to execute a complete business process with its component workflows, and save as markdown files. Use when documenting a business process end-to-end, creating playbooks, or explaining how multiple workflows fit together. Trig

  • writing-vision-briefs

    Use when a user has a fuzzy idea they want to explore before writing a formal PRD. Captures the essence of an idea as a Vision Brief — a structured, business-focused artifact that feeds directly into the feature-prd workflow.

  • writing-workflow-sops

    Write Standard Operating Procedure documentation for workflows and save it as a Markdown file. Selects a full or lightweight SOP template by autonomy level (deterministic vs. guided or autonomous), then adapts it for workflow type (Manual, Augmented, Automated). Use when the user asks to write an SO

View source on GitHub handsonai.info

More from jamesgray-ai/handsonai-plugins

All 2 plugins →

A complete, runnable worked example of multi-agent orchestration. Four specialist agents research, write, edit, and publish a business article, with automatic delegation, machine quality gates, and an enforced human approval step. Built to be read and adapted, not used as-is.

1 skill · 2 commands · 4 agents · hooks

8

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain handsonai?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins