easy-cheese

Triage a PR's review comments and failing CI (plus merge conflicts) through the /age lens, deciding which claims are worth acting on. Use when the user says "respond to PR comments", "handle review feedback", "affinage the PR", "/affinage <pr>", "fix the failing build", "resolve the conflicts and respond". Fetches inline + review-body comments via `gh` and CI failures via `affinage.pyz pr-status`, grades each through the ten age dimensions, and writes a report at `.cheese/affinage/pr-<n>.md`. Resolves merge conflicts via `/melt` and routes build/CI failures to fixes through `/cure`. When invoked standalone (no upstream `handoff_context`) it also runs `/age` over the PR diff and folds fresh findings in; when chained, it skips that pass. By default it auto-applies the recommended set via `/cure` and posts the drafted replies, gating only on sprawling/structural fixes or conflicts; `--safe` re-gates. Supports `--auto --stake <floor>`. Before `/cure`; parallel to `/age`.

Review a diff, PR, branch, or path across ten orthogonal dimensions (correctness, security, encapsulation, spec, complexity, deslop, assertions, NIH, efficiency, telemetry) and emit a severity-grouped findings report. Use when the user wants a code review — phrases like "review this", "/age", "is this safe to merge", "find bugs", "spot security issues", "check for slop", "review my PR", "look for problems", "what's wrong with this code". Report (`## Blocker /

Research questions external to the codebase across library docs (Context7), the web (Tavily), local code (cheez-search), and GitHub examples (gh), then synthesize with explicit confidence. Use whenever the user asks to research, look up, compare, or investigate something — phrases like "research X", "look up the API for Y", "compare libraries", "what does the doc say about Z", "find examples of how to do W", "is this library maintained", or "before I implement, what's the right approach". Use even when the user only mentions a library name without saying "research" — when in doubt, briesearch first so the spec or implementation is informed, not speculative.

Parallelize an approved spec across 5+ independent behavioural curds into reviewable PRs, running the whole pipeline fanned out at once. Use when the user has such a spec — phrases like "/cheese-factory .cheese/specs/<slug>.md", "send through the factory", "parallelize this spec", "many curds", "fan out the implementation", "cheese-factory this". Runs inline and spawns full-peer general-purpose sub-agents per phase (decomposer, per-curd workers, wiring, post-merge review, PR planner), ending in 1–N reviewable PRs via `/pr-stack`. Use even when the user mentions `/fromagerie` — `/cheese-factory` is the portable harness-agnostic sibling. Supports `--hard` propagation and `--resume <slug>` to continue a crashed pipeline. Do NOT use for single coherent specs (`/cook`, `/ultracook`), fuzzy planning (`/mold`), review-only work (`/age`), or specs with fewer than 5 curds (`/ultracook`).

Route any dropped-in input — idea, spec path, file path, PR or issue, stack trace, bug report, or bare `/cheese` — to the right workflow skill and dispatch it immediately. Use as the unified entry point — phrases include "/cheese", "what should I do with this", "help me get started", "route this", "figure out what skill I need", or any opening message that does not already name a downstream skill. Classifies the input into an intent shape, announces the target and reason in a short three-line block (Intent / Reason / Target), then runs the chosen skill with the exact command and context packet. Add `--safe` to gate dispatch behind a confirmation prompt; otherwise cheese decides and acts. Before any other workflow skill.