Skip to content
Back to skills

Skill Chain Prompts

ASecurity

Orchestrate multi-skill workflows with prompt-based skill chaining. Define sequential or parallel skill invocations using YAML chain definitions, track progress through chains, and use pre-built chains for development, documentation, and career workflows. Use when coordinating multiple skills for complex tasks.

  • 11 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 10, 2026
documentationgotestinggitapifrontendbackendfullstackdocumentation

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 10 files and shows the line behind each finding

Scanned September 10, 2026

npx -y skills add luokai0/ai-agent-skills-by-luo-kai --skill skill-chain-prompts --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Chain Prompts?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Skill Chain Prompts
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/luokai0-skill-chain-prompts/badge)](https://www.skillsdirectory.com/skills/luokai0-skill-chain-prompts)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: skill-chain-prompts
description: Orchestrate multi-skill workflows with prompt-based skill chaining. Define sequential or parallel skill invocations using YAML chain definitions, track progress through chains, and use pre-built chains for development, documentation, and career workflows. Use when coordinating multiple skills for complex tasks.
license: MIT
complexity: intermediate
time_to_learn: 30min
tags: [orchestration, workflow, chaining, multi-skill, automation, meta]
governance_phases: [shape]
organ_affinity: [organ-iv]
triggers: [user-asks-about-skill-chains, user-asks-about-workflow-composition, context:skill-orchestration]
complements: [agent-swarm-orchestrator, multi-agent-workforce-planner]
---

# Skill Chain Prompts

Orchestrate complex workflows by chaining multiple skills together. Define sequences, track progress, and use pre-built chains for common development patterns.

## Concept

A **chain** is a sequence of skills that work together to accomplish a larger goal. Each step invokes a skill, passes context forward, and tracks completion. Chains work through Claude's sequential processing—no external engine required.

## Quick Reference

### Chain Format

```yaml
chain:
  name: "my-workflow"
  description: "What this chain accomplishes"

steps:
  - id: first
    skill: skill-name
    description: "What this step does"
    outputs: [artifact1, artifact2]

  - id: second
    skill: another-skill
    depends_on: [first]
    checkpoint: true  # Pause for review

  - id: third
    skill: final-skill
    depends_on: [second]
    optional: true  # Can be skipped
```

### Commands

| Command | Purpose |
|---------|---------|
| `/skill-chain-prompts run <chain>` | Execute a named chain |
| `/skill-chain-prompts list` | Show available chains |
| `/skill-chain-prompts status` | Display current progress |
| `/skill-chain-prompts resume` | Continue from checkpoint |
| `/skill-chain-prompts skip` | Skip current optional step |

## Pre-Built Chains

### Development Workflows

**api-development** — Full API from design to deployment
```
api-design-patterns → tdd-workflow → backend-implementation-patterns → verification-loop → deployment-cicd
```

**fullstack-feature** — Complete feature implementation
```
product-requirements-designer → api-design-patterns → backend-implementation-patterns → frontend-design-systems → testing-patterns → verification-loop
```

**mcp-development** — MCP server creation
```
mcp-builder → testing-patterns → verification-loop → mcp-server-orchestrator
```

### Professional Workflows

**career-preparation** — Job search readiness
```
cv-resume-builder → portfolio-presentation → interview-preparation → networking-outreach
```

**documentation** — Project documentation
```
doc-coauthoring → github-repository-standards → github-profile-architect
```

## Usage Examples

### Run a Pre-Built Chain

```
User: /skill-chain-prompts run api-development

Claude: Starting chain: api-development
        "Full API development from design to deployment"

        Step 1/5: design (api-design-patterns)
        Invoking /api-design-patterns...
```

### Check Progress

```
User: /skill-chain-prompts status

Claude: ## Chain Progress: api-development

        | Step | Skill | Status | Notes |
        |------|-------|--------|-------|
        | design | api-design-patterns | ● Done | OpenAPI spec created |
        | test-first | tdd-workflow | ◐ Active | Writing endpoint tests |
        | implement | backend-implementation-patterns | ○ Pending | |
        | verify | verification-loop | ○ Pending | |
        | deploy | deployment-cicd | ⊖ Optional | |

        **Progress**: 2/5 steps (40%)
        **Current**: test-first
```

### Create Custom Chain

```
User: I need a chain for building a CLI tool

Claude: Creating custom chain...

        chain:
          name: "cli-tool"
          description: "Build a CLI application"

        steps:
          - id: design
            skill: api-design-patterns
            description: "Design CLI interface and commands"

          - id: implement
            skill: backend-implementation-patterns
            depends_on: [design]

          - id: test
            skill: testing-patterns
            depends_on: [implement]

          - id: docs
            skill: doc-coauthoring
            depends_on: [implement]
            optional: true

        Ready to execute?
```

## State Tracking

Progress is tracked in the conversation using markdown tables:

```markdown
## Chain Progress: fullstack-feature

| Step | Skill | Status | Notes |
|------|-------|--------|-------|
| requirements | product-requirements-designer | ● Done | PRD complete |
| api | api-design-patterns | ● Done | 12 endpoints |
| backend | backend-implementation-patterns | ◐ Active | 8/12 endpoints |
| frontend | frontend-design-systems | ○ Pending | |
| testing | testing-patterns | ○ Pending | |
| verify | verification-loop | ○ Pending | |

**Progress**: 2.5/6 steps (42%)
**Checkpoint**: After verify
```

### Status Icons

| Icon | Meaning |
|------|---------|
| ○ | Pending |
| ◐ | In Progress |
| ● | Complete |
| ⊖ | Optional/Skipped |
| ✕ | Failed |

## Checkpoints

Checkpoints pause the chain for review:

```yaml
- id: verify
  skill: verification-loop
  depends_on: [implement]
  checkpoint: true  # Chain pauses here
```

At a checkpoint:
1. Chain pauses and shows summary
2. User reviews artifacts and progress
3. `/skill-chain-prompts resume` continues
4. Or user can modify, redo, or abort

## Best Practices

1. **Start with pre-built chains** — Customize as needed
2. **Use checkpoints** — Add after critical steps for review
3. **Mark optional steps** — Deployment, documentation often optional
4. **Keep chains focused** — 3-7 steps is ideal
5. **Pass context forward** — Reference outputs from prior steps

## References

- `references/chain-format.md` — Complete YAML specification
- `references/execution-model.md` — How chains are processed
- `references/state-tracking.md` — Progress visualization formats
- `references/built-in-chains.md` — All pre-built chains documented

## Chain Templates

Pre-built chain files in `assets/chains/`:
- `api-development.yaml`
- `fullstack-feature.yaml`
- `career-preparation.yaml`
- `mcp-development.yaml`
- `custom-chain.yaml` — Blank template

Files in this skill

  • SKILL.md6.3 KB
  • assets/chains/api-development.yaml2.2 KB
  • assets/chains/career-preparation.yaml2.4 KB
  • assets/chains/custom-chain.yaml3.8 KB
  • assets/chains/fullstack-feature.yaml3.1 KB
  • assets/chains/mcp-development.yaml2.2 KB
  • references/built-in-chains.md5.9 KB
  • references/chain-format.md4.3 KB
  • references/execution-model.md5.1 KB
  • references/state-tracking.md5.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.