By DonalMoloney
Factory templates for building standardized Claude Code tools — skills, agents, hooks, and slash commands.
Use when creating a new custom agent or sub-agent, refactoring an existing agent definition to match current best practices, or when the user asks to build a specialist agent. Generates production-ready Claude Code agent definitions with enhanced YAML frontmatter, tool access patterns, and MCP integration.
Use when validating the quality of a Claude Code agent .md file. Checks YAML frontmatter completeness, tool restrictions, When-to-invoke examples, and output format documentation. Returns a 0-100 quality score.
Use when validating the quality of a Claude Code slash command .md file. Checks YAML frontmatter, bash permissions, argument syntax, naming convention, help text, and examples. Returns a 0-100 quality score.
Use when wiring up a new Claude Code lifecycle hook, converting an ad-hoc shell command into a proper hook entry, or when the user asks to automate something on a Claude Code event. Generates production-ready hook configurations through interactive Q&A with automated installation and enhanced validation across 10 templates and 7 event types.
Use when validating the quality of a Claude Code hook configuration (hook.json). Checks event type, matcher specificity, command safety, timeout configuration, and absence of secrets. Returns a 0-100 quality score.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
factory templates is a Claude Code plugin that standardizes how teams build, validate, and maintain Claude Code tools — skills, agents, hooks, and slash commands. Ships factories, validators, QA agents, hooks, standards, and GitHub automation behind a single entry point: /build.
Status: Phases 1–4 complete. Every bundled skill scores 100/100 against the rubric. Quality-gate hook blocks SKILL.md writes under 80. Multi-model CI runs every PR.
claude-code plugin install factory-templates --scope=org
git clone https://github.com/DonalMoloney/factory-templates
cd factory-templates
mkdir -p ~/.claude/{skills,agents,commands}
cp -R skills/* ~/.claude/skills/
cp -R agents/* ~/.claude/agents/
cp -R commands/* ~/.claude/commands/
Restart Claude Code afterwards so the new tools register.
| Goal | Command |
|---|---|
| Build any tool (guided) | /build |
| Build a skill | /build skill |
| Build a prompt | /build prompt |
| Build an agent | /build agent |
| Build a hook | /build hook |
| Audit the repo | /audit-tools |
| Validate a skill | /validate-skill <path> |
| Validate an agent | /validate-agent <path> |
Example — install and use the Prompt Factory:
/install-skill skills/prompt-factory
# then:
"Generate a prompt for a Senior DevOps Engineer"
skills/name: shown): generating-prompts, generating-hooks, generating-agents, generating-slash-commandsevaluating-skills (canonical 8-point rubric), reviewing-skills (structural review), validating-agents, validating-commands, validating-hooksDirectory paths under skills/ still use the historical names (e.g. skills/prompt-factory/SKILL.md); the gerund form is what Claude uses to trigger the skill.
agents/<name>.mdfactory-guide, skills-guide, agents-guide, hooks-guide, prompts-guidequality-reviewer, standards-enforcer, tool-architectcommands/<name>.md/build, /build-hook, /install-skill, /install-hook, /validate-skill, /validate-agent, /validate-output, /test-factory, /factory-status, /audit-tools
Git workflow: /cm (commit), /cp (commit + push), /pr (open PR), /rv (review gate), /sc (security scan)
hooks/hooks.json + script dirsdescription-linter — blocks SKILL.md writes that violate frontmatter rules (trigger phrase, third person, name format)line-count-reporter — warns when SKILL.md exceeds 500 linesquality-gate — runs evaluating-skills on every SKILL.md write and blocks at score < 80notify-factory-guide-completion — macOS notification when the factory-guide agent finishesFull canonical list: tools-index.md.
| Feature | What it does | Where |
|---|---|---|
| One entry point | /build routes to the correct guide agent | commands/build.md |
| Factory templates | Generate skills, agents, hooks, commands, prompts | templates/ |
| Quality standards | Per-tool rubrics with 0–100 scoring | standards/ |
| Validators | Score any tool against its standard | skills/*-quality-validator/ |
| Quality agents | quality-reviewer reports, standards-enforcer fixes | agents/ |
| Quality hooks | Description linting, line-count warnings, quality-gate blocking, completion alerts | hooks/ |
| Multi-model CI | Runs every skill's evaluations/ against Haiku 4.5 / Sonnet 4.6 / Opus 4.7 and reports cross-model deltas on each PR | .github/workflows/multi-model-test.yml |
| GitHub automation | Plan→Task→Subtask issue tree, board sync, health monitor | .github/workflows/ |
/build skill
# Answer the guided questions; install to ~/.claude/skills/
/build hook
# Answer 5–7 questions; auto-installs into settings.json
/audit-tools
# Lists skills, agents, hooks, commands with quality scores and conflicts
npx claudepluginhub donalmoloney/factory-templateHarness Claude's dynamic workflow and parallel agent orchestration to compress hours of sequential work into minutes.
Hand off context to any AI coding agent. Creates comprehensive handoff documents that capture the current task, progress, modified files, and all relevant context needed to seamlessly continue work in any AI assistant (Claude Code, Cursor, Copilot, Aider, etc.).
Orchestrate parallel and sequential AI agent swarms from YAML blueprints, with a live web dashboard.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.