How do I install the Chain skill?

Run npx skillmds@latest add tomevault-io/chain 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 Chain safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Chain?

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 Chain free to use?

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

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

Chain by tomevault-io — Agent Skill

Name: Chain
Author: tomevault-io

Chain

Build and execute chains that run multiple skills sequentially with data passing. Use when user says "chain skills", "run sequence", "pipeline", or needs to compose multiple skills into a single workflow. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Skill Chaining

Builds and executes chains that run multiple skills sequentially.

Syntax

/chain skill1 -> skill2 -> skill3

Predefined Chains

Predefined chains use Task subagent types (launched via Task tool). Custom chains can mix Skills and agents.

feature (new feature development)

task-planner -> coder -> test-writer -> code-reviewer

bugfix (bug fix)

debugger -> coder -> test-writer -> code-reviewer

refactor (refactoring)

code-reviewer -> coder -> test-writer -> code-reviewer

security-review (security review)

security-auditor -> code-reviewer -> coder (fix) -> security-auditor (verify)

Chain Execution Rules

1. Sequential Execution

Each skill waits for the previous skill to complete

2. Context Propagation

The output of the previous skill becomes the input for the next skill

3. Abort on Failure

If a skill fails, the chain is aborted

/chain --continue to force continuation

4. Checkpoints

Automatically creates a checkpoint when each skill completes

Custom Chain Definition

.claude/chains/custom-chain.yaml:

name: my-custom-chain
description: Custom chain description
steps:
    - skill: task-planner
      output_key: plan
    - skill: coder
      input_from: plan
      output_key: code
    - skill: test-writer
      input_from: code
      condition: "code.files_changed > 0"

Usage Examples

# Predefined chain
> /chain feature Add a new login feature

# Custom chain
> /chain debugger -> coder -> reflect

# Conditional execution
> /chain coder -> test-writer --if-changed

Source: gr1m0h/dot — distributed by TomeVault.

---name: chaindescription: Build and execute chains that run multiple skills sequentially with data passing. Use when user says "chain skills", "run sequence", "pipeline", or needs to compose multiple skills into a single workflow. Use when this capability is needed.---# Skill ChainingBuilds and executes chains that run multiple skills sequentially.## Syntax```/chain skill1 -> skill2 -> skill3```## Predefined ChainsPredefined chains use Task subagent types (launched via Task tool). Custom chains can mix Skills and agents.### feature (new feature development)```task-planner -> coder -> test-writer -> code-reviewer```### bugfix (bug fix)```debugger -> coder -> test-writer -> code-reviewer```### refactor (refactoring)```code-reviewer -> coder -> test-writer -> code-reviewer```### security-review (security review)```security-auditor -> code-reviewer -> coder (fix) -> security-auditor (verify)```## Chain Execution Rules### 1. Sequential ExecutionEach skill waits for the previous skill to complete### 2. Context PropagationThe output of the previous skill becomes the input for the next skill### 3. Abort on FailureIf a skill fails, the chain is aborted- /chain --continue to force continuation### 4. CheckpointsAutomatically creates a checkpoint when each skill completes## Custom Chain Definition`.claude/chains/custom-chain.yaml`:```yamlname: my-custom-chaindescription: Custom chain descriptionsteps: - skill: task-planner output_key: plan - skill: coder input_from: plan output_key: code - skill: test-writer input_from: code condition: "code.files_changed > 0"```## Usage Examples```# Predefined chain> /chain feature Add a new login feature# Custom chain> /chain debugger -> coder -> reflect# Conditional execution> /chain coder -> test-writer --if-changed```---> Source: [gr1m0h/dot](https://github.com/gr1m0h/dot) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions