$npx skillfedfor your agent

Designing Workflow Skills

Master the architecture of workflow-based skills through essential principles covering phased execution, tool alignment, progressive disclosure, and scalable patterns. This guide teaches you how to structure multi-step processes with numbered phases, entry/exit criteria, and appropriate freedom levels for each task type.

Designing Workflow Skills teaches you how to architect reliable multi-step agent workflows using structural patterns and phased execution.

AI-generated summary based on this skill's SKILL.md

6,292 543 CC-BY-SA-4.0updated by trailofbits

Install

trailofbits/skills/designing-workflow-skills · repository language: Python

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I design workflow skills?

Designing Workflow Skills teaches you to structure multi-step processes using phased execution, where each phase has clear entry/exit criteria. Start by aligning your skill's tools to specific workflow stages, apply progressive disclosure to reveal complexity only when needed, and establish appropriate freedom levels for each task type. This architecture ensures your workflow skill scales effectively across different automation scenarios.

What are workflow skill design best practices?

Designing Workflow Skills emphasizes several core practices: organize tasks into numbered phases with defined transitions, match tool capabilities to workflow stages, use progressive disclosure to avoid overwhelming users, and set freedom levels appropriate to each task's requirements. These patterns create reusable skills that adapt across multiple agent systems while maintaining clarity and control.

How do I create workflow skills from scratch?

Designing Workflow Skills guides you through building from the ground up by first mapping your process into phases, establishing entry and exit criteria for each phase, then selecting tools that align with those stages. Apply progressive disclosure so users see only relevant options at each step, and calibrate freedom levels—from constrained to open-ended—based on task complexity and risk tolerance.

What is workflow skill architecture?

Designing Workflow Skills defines architecture as the systematic arrangement of phases, tool alignment, and progressive disclosure mechanisms. Phased execution breaks workflows into logical steps with clear transitions. Tool alignment ensures each phase has appropriate capabilities. Progressive disclosure manages complexity, and freedom levels control how much autonomy agents have at each stage. Together, these elements create scalable, maintainable workflow skills.

How do I design reusable workflow skills?

Designing Workflow Skills teaches composition and design patterns that maximize reusability. Structure skills with modular phases that can be combined or reordered, align tools flexibly to support multiple workflow contexts, and use progressive disclosure to adapt the interface to different user expertise levels. This approach lets you build skills once and deploy them across varied agent systems and automation scenarios.

What design methodology helps build scalable workflow skills?

Designing Workflow Skills presents a methodology centered on phased execution, tool alignment, progressive disclosure, and calibrated freedom levels. Start by decomposing your workflow into numbered phases with clear criteria, match tools to each phase's requirements, reveal complexity progressively, and set freedom levels appropriate to task type and risk. This systematic approach ensures your skills remain maintainable and adaptable as complexity grows.

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Learn how to design and structure workflow skills for agent systems”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Claude Agent Sdk
by rysweet · rysweet/amplihack

Claude Agent SDK is Anthropic's framework for building autonomous agents that iteratively use tools to complete tasks. It handles the agent loop, context management, and tool orchestration automatically, with support for custom tools, MCP servers, permissions, and lifecycle hooks. Available in Python and TypeScript.

no license declared → metadata onlyfor claude-codeupdated Jul 2026
★ 68repo stars
compound-learnings
by parcadei · parcadei/Continuous-Claude-v3

Extract patterns from recent sessions and convert them into persistent capabilities—rules for heuristics, skills for workflows, and hooks for automation. The skill guides you through gathering learnings, consolidating similar patterns, detecting meta-themes, and proposing artifacts with appropriate signal thresholds before creation.

MITfor claude-codeupdated Jan 2026
★ 3,875repo stars
Skill Developer
by silvainfm · silvainfm/claude-skills

Skill Developer is a comprehensive guide for creating and managing Claude Code skills with auto-activation. It covers skill structure, YAML frontmatter, trigger types, enforcement levels, hook mechanisms, and the 500-line rule. Use it when building new skills, modifying skill-rules.json, debugging activation issues, or implementing progressive disclosure patterns.

no license declared → metadata onlyupdated Jan 2026
★ 2repo stars
skill-developer
by parcadei · parcadei/Continuous-Claude-v3

Skill Developer is a meta-skill for building new Claude Code skills from the ground up or converting existing scripts. It provides templates, step-by-step guidance for wrapping MCP pipelines, and configuration patterns to enable Claude's automatic skill discovery.

MITfor claude-codeupdated Jan 2026
★ 3,875repo stars
skill-generator
by catlog22 · catlog22/Claude-Code-Workflow

Skill Generator is a meta-skill that scaffolds new Claude Code skills with your choice of execution model. Select sequential mode for linear pipelines with fixed dependencies, or autonomous mode for dynamic, context-aware routing. It generates a complete skill package including directory structure, phase files, and specification templates.

MITfor claude-codeupdated Jun 2026
★ 2,142repo stars
dynamic-workflows
by TheBeardedBearSAS · TheBeardedBearSAS/claude-craft

Dynamic-workflows is a comprehensive orchestration framework that enables teams to coordinate multiple specialized agents across diverse technology stacks. Built for Claude Code adoption at scale, it combines sprint-based workflows, automated browser testing, and intelligent code review systems to streamline development cycles and reduce rework.

MITfor claude-codeupdated Jul 2026
★ 99repo stars

More skills Skill Generator (unlicensed) · ccw-chain (MIT)

Tags
skill-architectureworkflow-automationdesign-patternsagent-developmentskill-compositionimplementation-guideorchestration-frameworkcapability-modeling