AgriciDaniel/claude-blog / skills/blog-flow
blog-flow
VerifiedFLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, adapted from FLOW under CC BY 4.0). Use when user says "FLOW framework", "blog flow", "/blog flow", "evidence-led blogging", or "find optimize win", or asks for stage-specific blog prompts. Not for generic prompt writing.
references/prompts/optimize/claude-prompt-2.md
View on GitHub<!-- (c) Daniel Agrici, FLOW (https://github.com/AgriciDaniel/flow), CC BY 4.0 -->
<!-- Synced from FLOW on 2026-04-27 -->
---
title: "Claude Prompt 2"
description: "Claude Prompt 2"
updated: 2026-04-25
tags:
- prompts
- optimize
---
# Claude Prompt 2
## Use This When
Refine a revised draft against the first diagnosis.
## Task Inputs
- initial diagnosis.
- revised draft.
- resolved and open evidence gaps.
- editor feedback.
## Decisions
- Mark each blocker resolved, partial, or open.
- Reject length without proof.
- Approve only sourced claims.
## Prompt
```text
Act as a senior blog strategist using the FLOW model.
Use only supplied evidence. Label assumptions and unverified claims. Complete these checks:
1. Compare draft with findings.
2. Test self-contained answers.
3. Inspect proof and transitions.
4. Define acceptance checks.
Return only the required output. Do not invent statistics, support, or private examples.
```
## Required Output
- Resolution matrix.
- Remaining issues.
- Targeted edits.
- Acceptance checklist.
## See Also
- [Prompt Library](../README.md)
- [FLOW Framework](../../flow-framework.md)
- [Bibliography](../../bibliography.md)
## Source Note
Adapted from the FLOW repository structure and rewritten for blog use with the repository evidence standard.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |