1. Explicit override: If the user states a preference, always honor it:
   • Automatic signals: "just do it", "go ahead", "automatic", "quick", "don't ask"
   • Interactive signals: "walk me through", "help me", "guide me", "step by step", "let me decide"
2. Skill default: Each skill defines its own default based on the nature of the task.
3. Request analysis: If no explicit signal and no strong skill default, assess the request:
   • Detailed, specific requirements → automatic
   • Brief, ambiguous, or subjective → interactive

• State assumptions briefly before proceeding
• Make reasonable decisions at each step
• Present the result when done
• Pause only if a critical ambiguity could lead to wasted work

• Ask clarifying questions at the start
• Present options at decision points
• Confirm before proceeding at checkpoints
• Allow the user to steer direction

• If in automatic mode and the user asks a question or gives feedback → switch to interactive for the current phase
• If in interactive mode and the user says "looks good, go ahead" or similar → switch to automatic for remaining phases

/mthds-build

• Which user files map to which inputs (when ambiguous)
• Domain/industry context for realistic synthetic data
• Whether to generate edge cases or happy-path data
• Specific values or constraints for certain fields

mthds-agent --version

• If it succeeds: proceed to the next step.
• If it fails or the command is not found: STOP. Do not proceed with this skill. Tell the user:

The

mthds-agent

CLI is required but not installed. Install it with:

npm install -g mthds

Then re-run this skill.

.mthds

.mthds

<output_dir>

bundle.mthds

mthds-wip/pipeline_01/

inputs.json

bundle.mthds

• <output_dir>/inputs.json

• <output_dir>/inputs/

/inputs

inputs.json

• Template Strategy — placeholder JSON, no real data
• Synthetic Strategy — AI-generated realistic test data
• User Data Strategy — integrate user-provided files
• Mixed Strategy — user files + synthetic for the rest

inputs.json

1. Take the

   inputs

   object from Step 2's output
2. Save it to

   <output_dir>/inputs.json

   (next to

   bundle.mthds

   )
3. Report the saved file path and show the template content
4. Offer: "To populate this with realistic test data, re-run /mthds-inputs and ask for synthetic data. Or provide your own files."

• If the method processes invoices, generate invoice-like text
• If it analyzes reports, generate report-style content
• Match expected length (short prompts vs long documents)

1. List all files in the folder (non-recursive by default, recursive if user requests)
2. Filter to supported file types
3. Group files by detected type
4. Match to list-type inputs (

   Image[]

   ,

   Document[]

   , etc.)

./invoices/

documents: Document[]

1. Exact name match: Input variable

   invoice

   matches a file named

   invoice.pdf

2. Type match (single candidate): If only one input expects

   native.Image

   and the user provided exactly one image file, match them
3. Type match (multiple candidates): If multiple inputs of the same type exist:
   • In automatic mode: match by name similarity (variable name vs filename)
   • In interactive mode: ask the user which file goes where
4. Folder to list: If a folder contains files of a single type and an input expects a list of that type, map the folder contents to that input
5. Unmatched files: Report them and ask if they should be ignored or mapped to a specific input
6. Unfilled inputs: After matching, any inputs still without data can be left as placeholders or filled with synthetic data (see Mixed Strategy)

• Which files were matched to which inputs
• Any unfilled inputs (offer synthetic or placeholder)
• The final

  inputs.json

  content
• Path to the saved file

1. Follow User Data Strategy Steps A-E to match user files
2. For each unfilled input, apply Synthetic Strategy
3. Assemble the complete

   inputs.json

   combining both sources
4. Report which inputs came from user data and which were synthesized

reportlab

is a dependency of

pipelex

— always available, no additional installation needed.

Inputs are ready.

inputs.json

has been saved with real values — no placeholders remain.

undefined

image: Image

analysis_prompt: Text

1. Get schema, identify needs: test photograph + instruction text
2. Generate image via

   synthesize_image.mthds

   with category

   photograph

3. Write analysis prompt text matching the method context
4. Assemble:

{
  "image": {
    "concept": "native.Image",
    "content": {
      "url": "mthds-wip/pipeline_01/inputs/city_street.jpg",
      "mime_type": "image/jpeg"
    }
  },
  "analysis_prompt": {
    "concept": "native.Text",
    "content": {
      "text": "Analyze this street scene. Count visible people and describe the atmosphere."
    }
  }
}

invoice: Document

instructions: Text

~/documents/invoice_march.pdf

1. Get schema: needs

   invoice

   (Document) +

   instructions

   (Text)
2. Inventory: user provided

   invoice_march.pdf

   (PDF = Document type)
3. Match:

   invoice_march.pdf

   maps to

   invoice

   input (name similarity + type match)
4. Copy:

   cp ~/documents/invoice_march.pdf mthds-wip/pipeline_01/inputs/invoice.pdf

5. Unfilled:

   instructions

   has no user file. Generate synthetic text: "Extract all line items, totals, and vendor information from this invoice."
6. Assemble:

{
  "invoice": {
    "concept": "native.Document",
    "content": {
      "url": "mthds-wip/pipeline_01/inputs/invoice.pdf",
      "mime_type": "application/pdf"
    }
  },
  "instructions": {
    "concept": "native.Text",
    "content": {
      "text": "Extract all line items, totals, and vendor information from this invoice."
    }
  }
}

images: Image[]

./product-photos/

1. Get schema: needs

   images

   (Image[])
2. Expand folder:

   ./product-photos/

   contains

   shoe.jpg

   ,

   hat.png

   ,

   bag.jpg

3. Copy all to

   <output_dir>/inputs/

4. Assemble:

{
  "images": {
    "concept": "native.Image",
    "content": [
      {"url": "mthds-wip/pipeline_01/inputs/shoe.jpg", "mime_type": "image/jpeg"},
      {"url": "mthds-wip/pipeline_01/inputs/hat.png", "mime_type": "image/png"},
      {"url": "mthds-wip/pipeline_01/inputs/bag.jpg", "mime_type": "image/jpeg"}
    ]
  }
}

• Error Handling — read when CLI returns an error to determine recovery
• MTHDS Agent Guide — read for CLI command syntax or output format details
• MTHDS Language Reference — read for concept definitions and syntax
• Native Content Types — read for the full attribute reference of each native content type when assembling input JSON