Articles, tutorials, and announcements
How Datarim's coworker-context skill gives an external LLM the exact conventions it needs to generate or edit task artifacts correctly — frontmatter, stage headers, snapshot fields, and more.
Read more →How Datarim's consilium skill assembles a structured panel of specialized agents to surface conflicts and trade-offs before committing to an architecture or design decision.
Read more →How Datarim's compliance skill detects the task type, applies the matching verification checklist, and routes findings to inline fixes or the backlog before the archive step.
Read more →How Datarim's brainstorming skill turns a rough idea into an approved design through structured dialogue, three-approach exploration, and a hard gate against premature implementation.
Read more →How Datarim's autonomous-mode skill suppresses unnecessary questions through a five-level resolution ladder and keeps hard-gated actions strictly under operator control.
Read more →How Datarim's ai-quality skill enforces decomposition, test-first, and architecture review at every pipeline stage to cut bugs by 40–50%.
Read more →Why /dr-continue still works, what it actually does when invoked, and why all new work should use /dr-next instead.
Read more →How /dr-plugin manages opt-in extensions for Datarim: the two-manifest architecture, datarim-core bootstrap, symlink-based installation, and the phased roadmap for enable/disable and rollback.
Read more →What /dr-help shows: the full pipeline, all command categories, the complexity routing table, the agent roster, and backlog navigation — in one place.
Read more →How /humanize scans for AI writing patterns across vocabulary, structure, and rhythm, then surgically removes them while keeping the author's message and voice intact.
Read more →