AgriciDaniel/claude-blog / brain
claude-blog-brain
UnverifiedScaffold and operate Claude Blog Brain, a source-cited Obsidian brain for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill. Use when the user says "claude-blog-brain", "Claude Blog Brain", "create a blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill.
examples/sample-vault/wiki/flows/Reporting Workflow.md
View on GitHub---
type: "flow"
title: "Reporting Workflow"
created: "2026-08-25"
updated: "2026-08-25"
status: "active"
domain: "Blog Content Brain"
tags: [flows, reports, active]
---
# Reporting Workflow
1. Read [[Health Scorecard]] and [[Action Roadmap]].
2. Confirm every claim points to a source note or raw hash.
3. Render [[Weekly Report]].
4. Remove local paths and private data before sharing.
Related: [[Weekly Report]] | [[Approval Queue]]
## Reporting trigger
Run reporting on the agreed cadence, after a material gate changes, or before a
handoff. A report describes evidence and decisions, not activity volume.
## Inputs
| Input | Minimum record |
|---|---|
| Scorecard | Status, evidence, date, owner |
| Roadmap | Current action and next checkpoint |
| Approval queue | Pending consequential decisions |
| Source manifest | New and refreshed evidence |
| Verification log | Commands, exit states, counts |
| Incident notes | Failures and rollback state |
| External status | Directly verified live state only |
| Human review | Reviewer, scope, outcome |
## Preparation steps
1. Freeze the reporting period and timezone.
2. Read the previous report.
3. Sample scorecard evidence links.
4. Re-run volatile checks when due.
5. Reconcile roadmap states with verification.
6. Separate implemented, verified, accepted, and released.
7. Identify new blockers.
8. Record pre-existing failures separately.
9. Remove secrets and personal identifiers.
10. Draft the summary last.
## Claim language
| Evidence | Allowed wording |
|---|---|
| Local diff | implemented locally |
| Focused test | focused test passed |
| Full suite | repository suite passed |
| Isolated package | package built and scanned |
| Human review | accepted by named reviewer |
| Live URL | live state verified at a date |
| Missing gate | not verified |
| External dependency | awaiting owner or provider |
## Report structure
### Outcome
Lead with what changed for the operator or buyer.
### Evidence
List direct commands, artifacts, source decisions, and review dates.
### Risks
Name blast radius, remaining uncertainty, and rollback.
### Decisions
Present only choices that require the owner.
### Open items
Keep genuine gaps visible. Do not move them into vague future work.
## Quality checks
- Every number has a denominator or test count.
- Every source claim has a date.
- Every status matches its gate.
- Every blocker names a dependency.
- Every external claim has direct evidence.
- Every skipped check is stated.
- Every recommendation names a tradeoff.
- Every local path is removed from public prose.
- Every rights-sensitive artifact is excluded.
- Every secret scan reports no raw value.
## Failure patterns
- Reporting files changed instead of outcomes.
- “All good” hides skipped checks.
- Authorization is described as execution.
- A stale source date is copied forward.
- A failing gate is called pre-existing without evidence.
- A market statistic is presented as property data.
- A generated artifact is assumed deterministic.
- A long chronology hides the current decision.
## Review handoff
The report owner compares [[Weekly Report]] to [[Health Scorecard]] and
[[Action Roadmap]]. The decision owner sees [[Approval Queue]] separately.
## Rollback
If the report overstates evidence, correct it immediately, preserve the reason,
and notify only the same audience that received the incorrect report. Do not
change the underlying evidence to make the report appear right.
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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |