Help Center Article Writer
Specifying screenshot descriptions and reading level produces articles that are genuinely helpful, not just technically accurate.
Write a help center article for {{product_name}}.\n\nTopic: {{topic}}\nArticle type: {{article_type}} (tutorial / how-to / reference / troubleshooting)\nAudience technical level: {{technical_level}}\nProduct area: {{product_area}}\n\nExisting style reference:\n{{style_reference}}\n\nThe article should include:\n1. Title (clear, searchable — start with a verb for how-tos)\n2. One-sentence summary (appears in search results)\n3. Prerequisites (if any)\n4. Step-by-step instructions with numbered steps\n5. Screenshots/visual callouts (describe what each screenshot should show)\n6. Common issues section with solutions\n7. Related articles to link to: {{related_topics}}\n\nWrite at a {{reading_level}} reading level. Use short paragraphs and scannable formatting.
Variables to customize
Why this prompt works
Specifying screenshot descriptions and reading level produces articles that are genuinely helpful, not just technically accurate.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.