By mthds-ai
Skills for building, running, validating, and editing AI methods following the MTHDS standard.
Build new AI method from scratch using the MTHDS standard (.mthds bundle files). Use when user says "create a pipeline", "build a workflow", "new .mthds file", "make a method", "design a pipe", or wants to create any new method from scratch. Guides the user through a 10-phase construction process.
Check and validate MTHDS bundles for issues. Use when user says "validate this", "check my workflow", "check my method", "does this .mthds make sense?", "review this pipeline", "any issues?", "is this correct?". Reports problems without modifying files. Read-only analysis.
Edit existing MTHDS bundles (.mthds files). Use when user says "change this pipe", "update the prompt", "rename this concept", "add a step", "remove this pipe", "modify the workflow", "modify the method", "refactor this pipeline", or wants any modification to an existing .mthds file. Supports automatic mode for clear changes and interactive mode for complex modifications.
Explain and document MTHDS bundles. Use when user says "what does this pipeline do?", "explain this workflow", "explain this method", "walk me through this .mthds file", "describe the flow", "document this pipeline", "how does this work?", or wants to understand an existing MTHDS method bundle.
Fix issues in MTHDS bundles. Use when user says "fix this workflow", "fix this method", "repair validation errors", "the pipeline is broken", "fix the .mthds file", after /mthds-check found issues, or when validation reports errors. Automatically applies fixes and re-validates in a loop.
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.
A Claude Code skills plugin for building, running, validating, and editing AI methods (.mthds bundle files).
MTHDS is an open standard for AI methods. Find methods on the hub: MTHDS Hub. Install the reference python runtime from Pipelex.
Open Claude Code and paste this. Claude does the rest.
Install mthds: run bash -c 'npm install -g mthds && mthds-agent bootstrap && claude plugin marketplace add mthds-ai/mthds-plugins && claude plugin install mthds@mthds-plugins' then tell me the result. If it worked, add a "MTHDS" section to CLAUDE.md that lists the available skills (/mthds-build, /mthds-run, /mthds-check, /mthds-edit, /mthds-explain, /mthds-fix, /mthds-inputs, /mthds-install, /mthds-runner-setup, /mthds-pkg, /mthds-publish, /mthds-share, /mthds-upgrade) and notes that .mthds files are automatically validated when the agent modifies them and that MTHDS is the open language for executable AI methods, defined at mthds.ai. Then tell me to restart Claude Code with /exit and claude.
npm install -g mthds
mthds-agent bootstrap
claude plugin marketplace add mthds-ai/mthds-plugins
claude plugin install mthds@mthds-plugins
Restart Claude Code (/exit, then claude).
| Skill | Description |
|---|---|
/mthds-upgrade | Upgrade MTHDS stack to latest version |
/mthds-build | Build new AI method bundles from scratch |
/mthds-check | Validate workflow bundles (read-only) |
/mthds-edit | Modify existing bundles |
/mthds-explain | Explain and document workflows |
/mthds-fix | Auto-fix validation errors |
/mthds-run | Execute methods and interpret output |
/mthds-inputs | Prepare inputs: templates, synthetic data, files |
/mthds-install | Install method packages from GitHub or local |
/mthds-runner-setup | Set up inference backends and API keys |
/mthds-pkg | Manage MTHDS packages (init, deps, lock) |
/mthds-publish | Publish methods to mthds.sh |
/mthds-share | Share methods on social media |
The plugin includes a PostToolUse hook that fires on every .mthds file edit:
plxt lint validates TOML structure and schemaplxt fmt auto-formats the filemthds-agent validate bundle checks semantic correctnessErrors block the edit. Warnings are shown but don't block. Missing tools (plxt, mthds-agent) block .mthds edits until installed.
MIT — Copyright (c) 2026 Evotis S.A.S.
Maintained by Pipelex. "Pipelex" is a trademark of Evotis S.A.S.
npx claudepluginhub mthds-ai/mthds-plugins --plugin mthdsDevelopment build of MTHDS skills — for iteration and testing.
Skills for building, running, validating, and editing AI methods following the MTHDS standard.
Meta-prompting and self-improvement - skill writer, hook writer
Systematic maintenance of Claude Code plugins - skills, commands, agents, hooks - through domain analysis, behavioral testing, and quality improvements
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Open collection of AI agent skills — reusable, framework-agnostic SKILL.md packages
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.