workflow-create
Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)
What this skill does
# Workflow Create
Author a workflow on whichever surface fits the job.
## Pick a surface
- **MCP workflow template** — a persisted definition with a pause/resume lifecycle. Use for long-lived, human-gated, resumable pipelines.
- **Native `.claude/workflows/*.js`** — an imperative orchestration script that fans subagents out. Use for comprehensive fan-out (review, audit, migration, research) where you aggregate structured results in code.
## A — MCP workflow template
1. **List templates** — call `mcp__claude-flow__workflow_template` to see available templates
2. **Create workflow** — call `mcp__claude-flow__workflow_create` with steps, conditions, and execution order
3. **List workflows** — call `mcp__claude-flow__workflow_list` to see all defined workflows
4. **Check status** — call `mcp__claude-flow__workflow_status` to monitor a workflow
5. **Clean up** — call `mcp__claude-flow__workflow_delete` to remove unused workflows
Features: sequential/parallel steps, conditional branching, template inheritance, pause/resume approval gates.
## B — Native `.claude/workflows/*.js`
Write a `.js` file under `.claude/workflows/`. It MUST begin with a **pure-literal** `export const meta` block; the body runs inside an async wrapper (top-level `await`/`return` are legal) with these hooks injected:
| Hook | Purpose |
|------|---------|
| `agent(prompt, opts)` | Spawn one subagent; pass `opts.schema` (JSON Schema) to get validated structured output back |
| `parallel(thunks)` | Run thunks concurrently with a **barrier** — `.filter(Boolean)` the results |
| `pipeline(items, ...stages)` | Stream each item through stages independently — **prefer this** over a barrier |
| `phase(title)` / `log(msg)` | Progress grouping / narration |
```js
export const meta = {
name: 'my-workflow', // becomes the invocable name — must be a pure literal
description: 'one line',
phases: [{ title: 'Find' }, { title: 'Verify' }],
}
const SCHEMA = { type: 'object', required: ['ok'], properties: { ok: { type: 'boolean' } }, additionalProperties: false }
phase('Find')
const found = await agent('find the things', { schema: SCHEMA, agentType: 'tester' })
phase('Verify')
const checked = await parallel((found.items || []).map((it) => () =>
agent(`verify ${it}`, { schema: SCHEMA })))
return { found, checked: checked.filter(Boolean) }
```
Rules: `meta` is a pure literal (no variables/calls/interpolation); default to `pipeline` over `parallel`; never use `Date.now()`/`Math.random()` (they throw — vary by index instead). Validate syntax (the body is ESM-in-async-wrapper, not a bare module):
```bash
node -e 'const fs=require("fs");let s=fs.readFileSync(".claude/workflows/my-workflow.js","utf8").replace(/^export\s+const\s+meta/m,"const meta");fs.writeFileSync("/tmp/wf.mjs","let agent,parallel,pipeline,phase,log,args,budget,workflow;async function __wf(){\n"+s+"\n}")' \
&& node --check /tmp/wf.mjs && echo OK
```
Run it with the `workflow-run` skill or `Workflow({ name: 'my-workflow' })`. Reference: `.claude/workflows/plugin-contract-audit.js`. See [ADR-0002](../../docs/adrs/0002-native-workflow-orchestration.md).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.