Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Claude Blog Brain — measured AI agent skill | DecimalAI

agricidaniel/claude-blog-brain

SkillScore86Maintained

Scaffold 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 contrac

marketingby agricidaniel

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull agricidaniel-claude-blog-brain

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agricidaniel-claude-blog-brain/SKILL.md

Raw file: /s/agricidaniel-claude-blog-brain/SKILL.md ↗ · machine-readable summary at /s/agricidaniel-claude-blog-brain.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-16% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	4%	0%
case-07	✗→✓	▲ Improved	-40%	0%
case-08	✗→✓	▲ Improved	-44%	0%
case-09	✗→✓	▲ Improved	-1%	0%
case-16	✗→✓	▲ Improved	-14%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agricidaniel / claude-blog

brain/SKILL.md

View on GitHub ↗

License Custom licenseImported 8/3/2026Version v1Bundled 32 files · scripts

Skill contents

scripts/

references/

SKILL.md

Claude Blog Brain

Operate the vault first. Read CODEX.md, wiki/hot.md, and wiki/index.md before changing notes.

Commands

bash
/claude-blog-brain new <client-slug> --owner <name>
/claude-blog-brain demo
/claude-blog-brain ingest --vault <path> --file <source>
/claude-blog-brain synthesize --vault <path>
/claude-blog-brain report --vault <path>
/claude-blog-brain visuals --vault <path>
/claude-blog-brain lint --vault <path>
/claude-blog-brain next --vault <path>

Source checkout equivalent:

bash
claude-blog-brain new <client-slug> --owner <name>
claude-blog-brain demo
claude-blog-brain ingest --vault <path> --file <source>
claude-blog-brain synthesize --vault <path>
claude-blog-brain report --vault <path> --html-only

Required Operating Rules

Read <vault>/CODEX.md.
Read <vault>/wiki/hot.md.
Read <vault>/wiki/index.md.
Preserve .raw/ as immutable source material.
Never store credentials in the vault.
Never make domain-specific claims without dated trustworthy sources.
Keep hot, index, overview, and log current.
Record research evidence in references/source-ledger.json.
Record domain adapter completion in references/adapter-manifest.json.

Script Mapping

new -> python scripts/scaffold_vault.py
demo -> python scripts/build_demo_vault.py
ingest -> python scripts/ingest_source.py
synthesize -> python scripts/synthesize_brain.py
report -> python scripts/render_brain_report.py
visuals -> python scripts/generate_vault_visuals.py
lint -> python scripts/lint_vault.py
next -> python scripts/guide_next_action.py

Quality Gates

No ranking or traffic guarantee; content outcomes are probabilistic and never certain
No credentials, tokens, API keys, or private client content in repo artifacts
No mutation of a CMS, GSC, GA4, or publishing platform; the brain is advisory and read-only
No recommendation without a dated source, confidence level, and rollback note
No deprecated advice (HowTo schema, retired FAQ rich results, FID) presented as current
No fabricated or unsourced statistics and no generic, unsupported, or low-quality generated filler presented as fact

Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. A scaffold is not a finished brain.

Research Refresh

monthly for Google algorithm updates and Search Central policy; before every release for E-E-A-T framing, schema deprecations, and GEO/AEO citation claims; on-changelog for the claude-blog skill

Community

Use public project Discussions for questions and support: https://github.com/AgriciDaniel/claude-blog/discussions. Report reproducible defects through public Issues: https://github.com/AgriciDaniel/claude-blog/issues.

Want to see if agricidaniel/claude-blog-brain would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.