← ClaudeAtlas

artifacts-generatelisted

Generate engineering artifacts (READMEs, ADRs, design docs, diagrams, runbooks, postmortems, ERDs, etc.) from a previously-written `docs/artifacts-plan.md`. Supports two modes — **one at a time** (interview + preview/confirm + "continue?" per item, maximum oversight) and **batch** (pick a scope, interview each item, write directly, summarize at end, no per-item gates). Companion to the `artifacts-audit` skill — does NOT modify source code. Use when the user invokes `/artifacts-generate`, asks to "generate the next artifact", "execute the artifacts plan", "batch-generate this week's artifacts", "write the README / ADR / runbook from the plan", or otherwise wants to produce documented artifacts whose plan has already been audited.
ksdisch/claude-config · ★ 0 · AI & Automation · score 70
Install: claude install-skill ksdisch/claude-config
# Artifacts generation Companion to [[artifacts-audit]]. Reads `docs/artifacts-plan.md`, then walks through generating artifacts with the user. **Supports two modes** — the user picks upfront: - **One at a time** — interview, preview, confirm, write, then ask *continue?* before the next. Maximum oversight. Recommended for substantive artifacts (ADRs, design docs, postmortems) where Claude's draft genuinely benefits from a review pause. - **Batch** — pick a scope upfront (a priority tier or a custom list), interview each item, write directly, summarize all at end. Skips per-item preview-confirm and *continue?* prompts. Lower friction. Recommended for routine artifacts (CHANGELOG backfill, `.env.example`, several diagrams in one pass). Templates for structured artifacts (ADR, runbook, postmortem) live in [reference/templates/](reference/templates/). Default paths and naming conventions are in [reference/conventions.md](reference/conventions.md). ## When this skill fires - User types `/artifacts-generate` - User says: "generate the next artifact", "execute the artifacts plan", "batch-generate this week's artifacts", "do all the open items", "write the README / ADR / runbook from the plan", "what's next on my artifacts list?" ## What this skill does NOT do - **Does not autopilot, even in batch mode.** The per-item interview still happens — Claude can't write a meaningful ADR or design doc without the user's input on the decision, alternatives, and trade-offs. Batch mode sk