skill-chain-prompts
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.
What this skill does
# 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
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.