common-workflow-writing
Standardization rules for creating high-efficiency workflow and SKILL.md files.
Install
mkdir -p .claude/skills/common-workflow-writing && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15865" && unzip -o skill.zip -d .claude/skills/common-workflow-writing && rm skill.zipInstalls to .claude/skills/common-workflow-writing
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions. (triggers: .agent/workflows/*.md, SKILL.md, create workflow, write workflow, new skill, new workflow)Key capabilities
- →Enforce workflow structure
- →Limit file sizes for workflows and skills
- →Prevent verbose step preambles
- →Avoid pre-filled report rows
- →Merge sequential steps into one
How it works
The skill applies a set of core rules and size limits to ensure workflow and skill files are concise and token-efficient.
Inputs & outputs
When to use common-workflow-writing
- →Create new workflow file
- →Write new skill definition
- →Optimize existing agent files
About this skill
Workflow Writing Standard
Priority: P0 (CRITICAL)
Core Rules
- Templates, not examples: Workflows define structure, not pre-filled data. The agent generates data at runtime.
- No example rows in tables: Include headers + 1 skeleton row only. Never populate with fake data.
- No prose explanations: If a bullet or command achieves the same result, delete the paragraph.
- No pre-answered questions: Don't document what the agent will output — let it output it.
- Merge sequential steps: If two steps always happen together, they are one step.
Size Limits
| File type | Limit | If exceeded |
|---|---|---|
Workflow .md | 80 lines | Extract detail to references/ |
| SKILL.md | 100 lines | Extract examples to references/ |
| Table rows | 8 | Extract to references/ |
| Inline code block | 10 lines | Extract to references/ |
Workflow Structure (Required order)
1. Goal (1 sentence)
2. Steps (imperative verb → command or checklist)
3. Output template (headers only, no pre-filled rows)
Anti-Patterns
- No verbose step preambles:
"Before we start, it's important to understand..."→ Delete - No pre-filled report rows:
| Security | P0 | ✅ PASS | CLIENT_ID moved to env |→ Delete - No repeated examples: Same concept shown twice in different formats → Keep one
- No "How to do X" sections: The step IS the instruction
- No caution blocks for obvious rules: Reserve
> ⚠️for genuinely non-obvious risks
Quick Self-Check Before Saving
- Can the agent reconstruct any removed content at runtime from context? If yes → remove it
- Is every table row real structure, not example data?
- Are there any paragraphs a bullet list could replace?
- Would cutting this in half still give the agent enough to act on?
When not to use it
- →When including example rows in tables
- →When adding prose explanations instead of commands
- →When documenting what the agent will output
Limitations
- →Workflow .md files are limited to 80 lines
- →SKILL.md files are limited to 100 lines
- →Inline code blocks are limited to 10 lines
How it compares
This skill enforces strict structural and content rules for agent documentation, preventing over-building that requires costly optimization passes.
Compared to similar skills
common-workflow-writing side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| common-workflow-writing (this skill) | 0 | 4mo | No flags | Beginner |
| add-provider-doc | 6 | 3mo | Review | Beginner |
| update-release-notes | 1 | 1mo | Review | Advanced |
| higress-daily-report | 1 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by li-lance
View all by li-lance →You might also like
add-provider-doc
lobehub
Guide for adding new AI provider documentation. Use when adding documentation for a new AI provider (like OpenAI, Anthropic, etc.), including usage docs, environment variables, Docker config, and image resources. Triggers on provider documentation tasks.
update-release-notes
tldraw
Update the release notes file at `apps/docs/content/releases/next.mdx` based on PRs merged to main since the previous release, or archive `next.mdx` to a versioned file when a new version is published.
higress-daily-report
alibaba
生成 Higress 项目每日报告，追踪 issue/PR 动态，沉淀问题处理经验，驱动社区问题闭环。用于生成日报、跟进 issue、记录解决方案。
sop-creator
coleam00
Create runbooks, playbooks, and technical documentation for engineering teams. Use when the user wants to document a process, create a runbook, build operational docs, or formalize any repeatable technical procedure. Triggers on requests like "create a runbook for...", "document this process", "write a playbook", or any technical documentation request.
release-prep
massgen
Prepare release documentation including CHANGELOG entry, announcement text, and validation. Run before tagging a new release.
update-api-docs
Agenta-AI
Update the API reference documentation by downloading the latest OpenAPI spec from production and regenerating the Docusaurus API docs