Free, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-Hub/claude-blog; public releases ship here.
Python agent-skillsaiai-citationsai-contentai-marketingai-marketing-hubblogblog-writingclaude-codeclaude-code-skillclaude-pluginclaude-skillcontent-creationcontent-optimizationcontent-strategyeeatgeomultilingualopen-sourceseo
Claude Blog Brain Agent Instructions
The canonical agent entrypoint is SKILL.md; this file exists for agent
runtimes that load project-level AGENTS.md instructions.
Read Order
SKILL.mdREADME.mddocs/OPERATOR_KIT.mddocs/PRODUCT_BOUNDARIES.mdreferences/product-spec.mdreferences/source-ledger.jsonreferences/adapter-manifest.json
Operating Rules
- Do not call this brain market-ready unless
scripts/audit_brain.py --require market-readypasses. - A scaffold is not a finished brain.
- Domain-specific claims require dated trustworthy sources.
- Research evidence must be recorded in
references/source-ledger.json. - Adapter completion must be recorded in
references/adapter-manifest.json. - Preserve
.raw/as immutable source material. - Keep Obsidian
wiki/,CODEX.md, dashboards, canvases, frontmatter, wikilinks, graph hygiene, and source citations healthy. - V1 is advisory and read-only unless a future release defines approval and rollback for mutations.
Verification
python -m compileall scripts claude_blog_brain tests
python tests/test_pipeline.py --skip-release
python scripts/lint_vault.py
python scripts/audit_brain.py --json
python scripts/package_release.py --version 0.2.0
The first four commands are read-only verification. The package command writes release artifacts and belongs to release preparation, not routine inspection.