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.
references/README.md
View on GitHub# References
This folder is the evidence spine for Claude Blog Brain. It turns dated sources
into usable requirements without letting unsupported SEO or GEO claims leak into
deliverables.
## Evidence Spine Map
- `source-ledger.json` is the canonical source registry. It records source URL,
source type, dates, retrieval metadata, confidence, evidence tier,
methodology, limitations, supported claims, and raw snapshot status. Lifecycle
distinguishes active support from retired provenance and unverified claims.
- `claim-ledger.md` is the adversarial claim register. It maps volatile claims
to research questions, verdicts, confidence, primary source URL and date,
second-source status, and refresh due dates.
- `CONFIDENCE_TAGS.md` defines how to classify official evidence, practitioner
research, contested findings, and unsupported folklore.
- `canon/` holds stable source-led notes for recurring Google, schema, QRG,
Core Web Vitals, AI Search, and policy claims.
- `current-requirements.md` summarizes the current operating requirements that
are allowed to guide blog recommendations after ledger support exists.
- `market-research.md` summarizes buyer, market, and demand evidence with
practitioner caveats where needed.
- `adapter-manifest.json` records adapter maturity truth. It remains
governed by implementation and test gates separately from source review.
## No Source In Prose Only
Do not add a source only to Markdown prose. Release-counted evidence must be in
`source-ledger.json` first, then summarized in the relevant note. If a working
claim needs a source that is not yet in `source-ledger.json`, mark it as a
`source-ledger gap` in `claim-ledger.md` and do not use it as release-satisfying
evidence until the ledger is backfilled.
## Rules
- Do not reuse an official source URL for third-party impact, named-site, CTR,
traffic, or AI citation claims.
- Do not promote a practitioner study to official evidence.
- Do not use a month-only or year-only date without `date_precision`.
- Do not quote dynamic datasets without data window, geography, platform or
device filter, and retrieval date.
- Do not use deprecated tactics, including FAQ rich results, HowTo rich
results, or FID, as current recommendations.
- Do not call the brain market-ready until local raw snapshots and hashes,
external source URL and retrieval metadata, citations, adapter tests, and the
release audit all pass.
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 |