Agent skill
write-blog
End-to-end blog creation pipeline from topic to publish-ready draft. Orchestrates research, planning, diagram generation, and writing in sequence with approval checkpoints. Use when user wants to create a complete blog post from scratch on a given topic.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/write-blog
SKILL.md
Full Blog Pipeline Orchestrator
Input
$ARGUMENTS = the topic in natural language (e.g., "sliding window attention", "mixture of experts", "flash attention")
Pipeline
Execute these phases IN ORDER. Each phase must complete before the next begins. Include approval checkpoints at critical stages.
Phase 1: Deep Research
Goal: Understand the topic thoroughly.
- Run the research-topic skill with the given topic.
- Wait for completion.
- Verify research/.md exists and is substantial.
- Report to user:
- Number of sources found
- Key concepts identified
- Number of visual opportunities found
- Ask: "Research complete. Ready to proceed to planning?"
- STOP and wait for user approval.
Phase 2: Article Planning
Goal: Create a detailed outline with diagram specifications.
- Run the plan-article skill.
- Wait for completion.
- Verify plan/_outline.md exists.
- Show the user:
- Complete section outline
- List of all planned diagrams (with count)
- The running example that will be used
- Ask: "Here is the article outline with X planned diagrams. Happy with this? Any sections to add, remove, or reorder?"
- STOP and wait for user approval.
- If user requests changes, update the plan and re-present.
Phase 3: Diagram Generation
Goal: Create all visual assets using PaperBanana.
- Run the generate-diagrams skill.
- Wait for completion.
- Show user the generation report:
- How many diagrams generated successfully
- Any failures or quality concerns
- Ask: "All diagrams generated. Want to review any specific diagram or regenerate any?"
- STOP and wait for user approval.
- If user requests regeneration, update .txt and retry.
Phase 4: Article Writing
Goal: Write the full article following the style guide.
- Run the write-article skill.
- Wait for completion.
- Verify drafts/.md exists.
- Show user:
- Title and word count
- Figure count
- First 3 paragraphs as preview
- Self-review checklist results
- Ask: "Draft complete. Please review the full article at drafts/.md. Any changes needed?"
- STOP and wait for user feedback.
- If user requests edits, make them and re-present.
Phase 5: Publish Preparation
Goal: Format and prepare for final publishing.
- Run the publish skill.
- This will present the final article to the user.
- STOP. Wait for explicit user approval before any publishing.
Important Notes
- This skill runs the FULL pipeline. It may take significant time.
- Each phase has its own approval checkpoint.
- The user can interrupt at any phase to make changes.
- If context gets large, suggest clearing between phases.
- Never skip the approval checkpoints.
- Never publish without explicit "yes, publish" from the user.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?