How do I install the Pipelex Explain skill?

Run npx skillmds@latest add pipelex/pipelex-explain in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pipelex Explain safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pipelex Explain?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pipelex Explain free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pipelex Explain?

pipelex (@pipelex) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pipelex Explain by pipelex — Agent Skill

Name: Pipelex Explain
Author: pipelex

Pipelex Explain

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.

pipelex 0c2c398 2.5 KB Updated Sep 17, 2026

File contents

Explain MTHDS bundles

Analyze and explain existing MTHDS method bundles in plain language.

This skill is read-only: it reads a bundle and explains it. It never modifies the .mthds file.

Process

Step 1: Read the .mthds File

Read the entire bundle file to understand its structure.

Step 2: Identify Components

List all components found in the bundle:

Domain: the top-level domain key (bundle header, not a [domain] section)
Concepts: all [concept.*] blocks — note which are custom vs references to native concepts
Pipes: all [pipe.*] blocks — identify the main pipe and sub-pipes
Main pipe: the top-level main_pipe key (bundle header, not a [bundle] section)

Step 3: Trace Execution Flow

Starting from the main pipe, trace the execution path:

For PipeSequence: follow the steps array in order
For PipeBatch: identify batch_over and batch_as, then the inner pipe
For PipeParallel: list all branches
For PipeCondition: map condition → pipe for each branch
For PipeLLM / PipeExtract / PipeImgGen / PipeSearch / PipeFunc: these are leaf operations

Step 4: Present Explanation

Structure the explanation as:

Purpose: one-sentence summary of what the method does
Inputs: list each input with its concept type and expected content
Output: the final output concept and what it contains
Step-by-step flow: walk through execution in order, explaining what each pipe does
Key concepts: explain any custom concepts defined in the bundle

Step 5: Generate Flow Diagram

Create a text diagram showing the execution flow. Example:

main_sequence
  1. step_one (PipeLLM) -> intermediate_result
  2. step_two (PipeExtract) -> final_output

Inputs: input_a, input_b
Output: final_output

Adapt the format to the method structure (linear, branching, batched).

Reference

MTHDS Language Reference — read for concept definitions and syntax
Native Content Types — read when explaining what data flows through pipes (e.g., what attributes Page or Image content carries)

---name: pipelex-explaindescription: 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.---# Explain MTHDS bundlesAnalyze and explain existing MTHDS method bundles in plain language.This skill is read-only: it reads a bundle and explains it. It never modifies the `.mthds` file.## Process### Step 1: Read the .mthds FileRead the entire bundle file to understand its structure.### Step 2: Identify ComponentsList all components found in the bundle:- **Domain**: the top-level `domain` key (bundle header, not a `[domain]` section)- **Concepts**: all `[concept.*]` blocks — note which are custom vs references to native concepts- **Pipes**: all `[pipe.*]` blocks — identify the main pipe and sub-pipes- **Main pipe**: the top-level `main_pipe` key (bundle header, not a `[bundle]` section)### Step 3: Trace Execution FlowStarting from the main pipe, trace the execution path:1. For **PipeSequence**: follow the `steps` array in order2. For **PipeBatch**: identify `batch_over` and `batch_as`, then the inner pipe3. For **PipeParallel**: list all branches4. For **PipeCondition**: map condition → pipe for each branch5. For **PipeLLM / PipeExtract / PipeImgGen / PipeSearch / PipeFunc**: these are leaf operations### Step 4: Present ExplanationStructure the explanation as:1. **Purpose**: one-sentence summary of what the method does2. **Inputs**: list each input with its concept type and expected content3. **Output**: the final output concept and what it contains4. **Step-by-step flow**: walk through execution in order, explaining what each pipe does5. **Key concepts**: explain any custom concepts defined in the bundle### Step 5: Generate Flow DiagramCreate a text diagram showing the execution flow. Example:```main_sequence 1. step_one (PipeLLM) -> intermediate_result 2. step_two (PipeExtract) -> final_outputInputs: input_a, input_bOutput: final_output```Adapt the format to the method structure (linear, branching, batched).## Reference- [MTHDS Language Reference](../shared/mthds-reference.md) — read for concept definitions and syntax- [Native Content Types](../shared/native-content-types.md) — read when explaining what data flows through pipes (e.g., what attributes Page or Image content carries)

Frequently asked questions