From mthds
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mthds:mthds-fixThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Automatically fix issues in MTHDS method bundles.
Automatically fix issues in MTHDS method bundles.
Run mthds-agent --version. The minimum required version is 0.1.3 (declared in this skill's front matter as min_mthds_version).
The
mthds-agentCLI is required but not installed. Install it with:npm install -g mthdsThen re-run this skill.
This skill requires
mthds-agentversion 0.1.3 or higher (found X.Y.Z). Upgrade with:npm install -g mthds@latestThen re-run this skill.
Do not write .mthds files manually, do not scan for existing methods, do not do any other work. The CLI is required for validation, formatting, and execution — without it the output will be broken.
No backend setup needed: This skill works without configuring inference backends or API keys. You can start building/validating methods right away. Backend configuration is only needed to run methods with live inference — use
/mthds-pipelex-setupwhen you're ready.
Always use -L pointing to the bundle's own directory to avoid namespace collisions:
mthds-agent pipelex validate bundle <file>.mthds -L <bundle-directory>/
Parse the JSON output:
success: true — nothing to fix, report clean statuserror_type: "ValidateBundleError" — iterate through validation_errors array and fix each (Step 2)Use the error_type field from each validation error to determine the fix:
| Error Type | Fix Strategy |
|---|---|
missing_input_variable | Add the missing variable(s) to the parent pipe's inputs line |
extraneous_input_variable | Remove the unused variable(s) from the pipe's inputs line |
input_stuff_spec_mismatch | Correct the concept type in inputs to match what the sub-pipe expects |
inadequate_output_concept | Change the output field to the correct concept type |
inadequate_output_multiplicity | Add or remove [] from the output concept |
circular_dependency_error | Restructure the method to break the cycle |
llm_output_cannot_be_image | Use PipeImgGen instead of PipeLLM for image generation |
img_gen_input_not_text_compatible | Ensure PipeImgGen input is text-based (use ImgGenPrompt) |
invalid_pipe_code_syntax | Rename the pipe to valid snake_case |
unknown_concept | Add the concept definition to the bundle, or fix the typo |
batch_item_name_collision | Rename input_item_name (or batch_as) to a distinct singular form of the list name. Also update the branch pipe's inputs to use the new item name. |
For error type descriptions, see Error Handling — Validation Error Types.
After applying semantic fixes, run mthds-agent plxt lint <file>.mthds as a quick TOML/schema correctness check. If lint passes, run mthds-agent plxt fmt <file>.mthds to auto-format the file before re-validating semantically in the next step.
Beyond what plxt catches, watch for these common issues:
Multi-line inputs — must be on a single line:
# WRONG
inputs = {
a = "A",
b = "B"
}
# CORRECT
inputs = { a = "A", b = "B" }
Pipe ordering — controllers before sub-pipes:
# CORRECT: main pipe first, then sub-pipes in execution order
[pipe.main_workflow]
type = "PipeSequence"
steps = [
{ pipe = "step_one", result = "intermediate" },
{ pipe = "step_two", result = "final" }
]
[pipe.step_one]
...
[pipe.step_two]
...
Missing required fields — add with sensible defaults:
description on every pipe and concepttype on every pipeoutput on every pipeAfter applying fixes, re-validate:
mthds-agent pipelex validate bundle <file>.mthds -L <bundle-directory>/
Continue the fix-validate loop until success: true is returned. Some fixes reveal new issues — for example, fixing a missing_input_variable may expose an input_stuff_spec_mismatch on the newly added input.
On the final successful validation, re-run with --graph to generate a flowchart:
mthds-agent pipelex validate bundle <file>.mthds -L <bundle-directory>/ --graph
If the fix-validate loop gets stuck or errors are unclear, re-run with --log-level debug for additional context:
mthds-agent --log-level debug pipelex validate bundle <file>.mthds -L <bundle-directory>/
dry_run.html flowchart next to the bundleCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mthds-ai/skills-sandbox --plugin mthds