blog

# Blog Create a publishable blog post from `$ARGUMENTS`. This is a **task skill**: it may write files, localize assets, spawn delegates, and run target-site validation. Do not use it for casual copy edits. Arguments received: `$ARGUMENTS` ## Dispatch 1. If `$ARGUMENTS` is empty, ask for a one-line scenario and stop. 2. Parse any explicit flags: - `--source <path|url>` — raw notes, transcript, Loom URL, or source folder. - `--target <repo|path>` — blog repo or site root. Treat `/worktrees ...` as repo-relative `.oh/worktrees/...`, never filesystem root. - `--slug <slug>` — target post slug, lowercase kebab-case. - `--promo linkedin,x,channels` — also generate a reviewable promotion artifact for social posts and channel blasts; never publish. - `--dry-run` — perform audits and propose filename/outline only; write nothing. 3. Route to the first playbook, `references/loom-to-blog.md`, when the scenario mentions Loom, video, demo, transcript, screenshots, `demo.md`, or a source under `.claude/specs/`. 4. If no playbook fits, say the only implemented reference is `loom-to-blog` and ask whether to adapt it. ## Required first read For Loom/demo work, read and follow: - `${CLAUDE_SKILL_DIR}/references/loom-to-blog.md` That reference is authoritative for the workflow details. This `SKILL.md` only defines dispatch, boundaries, and shared completion rules. ## Shared rules - **Use Advisor before drafting.** For non-trivial source material, read `.oh/agents/advisor...