mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-10-08 03:07:51 +00:00
9975cc9f9b
Ran the /update-docs pipeline post-v2.6.1 release. Most of the work was verification (docs already in sync from prior PRs #644, #649). Two real issues surfaced and fixed: 1. Codex sync bug (the headline fix) - scripts/sync-codex-skills.py used iterdir() which is single-level only - Missed the engineering/<plugin>/skills/<name>/SKILL.md pattern used by 4 Pocock plugins + many other standalone plugins restructured since PR #593 - Added Pattern 3 discovery: when <domain>/<plugin>/ contains a skills/ subdir with <name>/SKILL.md, recurse one level - Impact: Codex index 195 → 289 skills (+94 previously-hidden skills) - Gemini sync was already correct (uses recursive rglob) - OpenClaw was already correct (uses recursive find) 2. Stale skill counts in 2 user-facing docs - README.md: 268 → 272 (3 occurrences: tagline + badge + skills overview) - docs/getting-started.md: 246 → 272 (2 occurrences: meta description + FAQ) - All other files (CLAUDE.md, docs/index.md, mkdocs.yml site_description, marketplace.json) were already at 272 (refreshed in PRs #644 + #649) Other regenerations (no source changes — auto-updated from latest content): - docs/skills/engineering/*.md regenerated (picks up v2.6.1 description fixes) - docs/agents/*.md regenerated (no agent changes) - docs/commands/*.md regenerated (no command changes) - .codex/skills-index.json + 94 new symlinks (mostly Pocock + plugin-pattern skills that should have been there since PR #593) Verification: - All 5 user-facing docs (CLAUDE.md, README.md, docs/index.md, docs/getting-started.md, mkdocs.yml) show "272 skills" consistently - marketplace.json: v2.6.1, 43 plugins, 0 broken source paths - mkdocs build: 371 pages (280 skills + 58 agents + 33 commands), clean in 17.31s, no errors or new warnings - audit_skills.py: runs cleanly against 298 real skills No production code changes outside the Codex sync fix. This is a docs + tooling sweep, not a feature release. https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe
94 lines
3.1 KiB
Markdown
94 lines
3.1 KiB
Markdown
---
|
|
title: "Agent Workflow Designer — Agent Skill for Codex & OpenClaw"
|
|
description: "Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling. Agent skill for Claude Code, Codex CLI, Gemini CLI, OpenClaw."
|
|
---
|
|
|
|
# Agent Workflow Designer
|
|
|
|
<div class="page-meta" markdown>
|
|
<span class="meta-badge">:material-rocket-launch: Engineering - POWERFUL</span>
|
|
<span class="meta-badge">:material-identifier: `agent-workflow-designer`</span>
|
|
<span class="meta-badge">:material-github: <a href="https://github.com/alirezarezvani/claude-skills/tree/main/engineering/skills/agent-workflow-designer/SKILL.md">Source</a></span>
|
|
</div>
|
|
|
|
<div class="install-banner" markdown>
|
|
<span class="install-label">Install:</span> <code>claude /plugin install engineering-advanced-skills</code>
|
|
</div>
|
|
|
|
|
|
**Tier:** POWERFUL
|
|
**Category:** Engineering
|
|
**Domain:** Multi-Agent Systems / AI Orchestration
|
|
|
|
---
|
|
|
|
## Overview
|
|
|
|
Design production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls.
|
|
|
|
## Core Capabilities
|
|
|
|
- Workflow pattern selection for multi-step agent systems
|
|
- Skeleton config generation for fast workflow bootstrapping
|
|
- Context and cost discipline across long-running flows
|
|
- Error recovery and retry strategy scaffolding
|
|
- Documentation pointers for operational pattern tradeoffs
|
|
|
|
---
|
|
|
|
## When to Use
|
|
|
|
- A single prompt is insufficient for task complexity
|
|
- You need specialist agents with explicit boundaries
|
|
- You want deterministic workflow structure before implementation
|
|
- You need validation loops for quality or safety gates
|
|
|
|
---
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
# Generate a sequential workflow skeleton
|
|
python3 scripts/workflow_scaffolder.py sequential --name content-pipeline
|
|
|
|
# Generate an orchestrator workflow and save it
|
|
python3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json
|
|
```
|
|
|
|
---
|
|
|
|
## Pattern Map
|
|
|
|
- `sequential`: strict step-by-step dependency chain
|
|
- `parallel`: fan-out/fan-in for independent subtasks
|
|
- `router`: dispatch by intent/type with fallback
|
|
- `orchestrator`: planner coordinates specialists with dependencies
|
|
- `evaluator`: generator + quality gate loop
|
|
|
|
Detailed templates: `references/workflow-patterns.md`
|
|
|
|
---
|
|
|
|
## Recommended Workflow
|
|
|
|
1. Select pattern based on dependency shape and risk profile.
|
|
2. Scaffold config via `scripts/workflow_scaffolder.py`.
|
|
3. Define handoff contract fields for every edge.
|
|
4. Add retry/timeouts and output validation gates.
|
|
5. Dry-run with small context budgets before scaling.
|
|
|
|
---
|
|
|
|
## Common Pitfalls
|
|
|
|
- Over-orchestrating tasks solvable by one well-structured prompt
|
|
- Missing timeout/retry policies for external-model calls
|
|
- Passing full upstream context instead of targeted artifacts
|
|
- Ignoring per-step cost accumulation
|
|
|
|
## Best Practices
|
|
|
|
1. Start with the smallest pattern that can satisfy requirements.
|
|
2. Keep handoff payloads explicit and bounded.
|
|
3. Validate intermediate outputs before fan-in synthesis.
|
|
4. Enforce budget and timeout limits in every step.
|