Read-only AI-led QA for recipe markdown quality, including weekly date-based batch review with parallel workers.
Use this skill to evaluate recipe quality without writing files or mutating Todoist.
mep sl sync apply ....mep CLI help, this repo AGENTS.md, and docs/mep-ai-led-qa.md as the canonical contract for this QA workflow.mep recipe import-url ... (writes markdown)mep recipe upgrade ... (rewrites markdown)mep sl add-recipe ... (writes desired/plan/apply state)mep sl sync apply ... (mutates Todoist)recipes_dir (path containing recipe markdown files)this_week (query by frontmatter added date)qa_depth: quick or releasethis_week selector.added from each *.md in recipes_dir.added is within the window (inclusive).added, then filename.## Ingredients pipe lines## Method stepsadded date ascendingFor each recipe:
PASS or FAILcritical: missing core ingredients, hallucinations, major quantity errorsmajor: label issues, significant method driftminor: small formatting/consistency issuesAggregate summary:
mep-cli/prompts/recipe-extraction.mdxmlmep-cli/src/commands/sl.rs$MEP_CONFIG_DIR/cooking.tomlcargo run --manifest-path ~/development/ai/clai/Cargo.toml -- validate skill mep-ai-led-qa --scope project --project-root ~/development/mise-en-place and expect no [Error] lines.PASS or FAIL, severity-tagged findings, and concrete evidence.mep recipe import-url, mep recipe upgrade, mep sl add-recipe, or mep sl sync apply.cargo run --manifest-path ~/development/ai/clai/Cargo.toml -- validate all --scope project --project-root ~/development/mise-en-place and expect this skill to introduce no new hard validation failures.cargo run --manifest-path ~/development/ai/clai/Cargo.toml -- sync --dry-run --scope project --project-root ~/development/mise-en-place and expect .claude/skills and .config/opencode/skills to mirror .agents/skills.