# Processflow Critic > Red-team ONE ProcessFlow process from the customer's/Martin's critical lens — assume the concept was generated by a weaker AI without perfect context, and question everything. Use when told to "hinterfrage Prozess ", "kritische Analyse", "red-team this", "critique ", or when the wrapper processflow-run calls the critique step. Actively checks the process against the known Fehlermuster-Register (every real mistake we hit on ZIWA + Stütz), web-researches the proposed tools/pricing/technique, and SURFACES concrete issues (evidence + which guard + suggested fix). It does NOT fix — it produces the issue list that gets fed back into the rework. - Skill: `psquared-development/processflow-critic` (Agent Skill) - Install (CLI): `npx skillmds@latest add psquared-development/processflow-critic` - Raw SKILL.md: https://api.skillmd.com/api/skills/psquared-development/processflow-critic/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: psquared-development (https://skillmd.com/u/psquared-development) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/psquared-development/processflow-critic --- # ProcessFlow — Critic (the critical lens) Input: one process (name). Your job is to **find what's wrong**, not to be reassured. **Default assumption: the current concept was produced by a weaker AI without full context — so treat every claim as suspect until verified.** You do NOT edit anything; you output a prioritized issue list. ## How to critique 1. Pull the current canvas + report + score + diagrams (Chrome session token) and read the relevant transcript passages. Compare concept ↔ canvas ↔ diagrams ↔ transcript. 2. **Walk the Fehlermuster-Register** in `processflow-review/references/guardrails.md` (the table at the bottom) — for EACH pattern, actively check this process. The recurring killers: - Wrong company name / **invented tool / invented brand or device / invented ERP** (grep names vs transcript). - **Wrong industry** carried through all fields + diagrams. - **Wrong scenario** — the concept describes a different process than the transcript means. - **Rebuilds what the ERP/a product already does** (e.g. IPTOR native replenishment, IDP tools, Firefly, InboxMate) — Build-vs-Buy not considered. - **Wrong AI technique** (describing VLM instead of image-embeddings; heavy ML where the customer described rules; prompt-extraction instead of IDP). - **Price/"included/free" hallucination** (e.g. Firefly credits). - Over/under-motorized; hours too low; only Phase 1 has an analysis step; existing system assumed free (BMD); canvas≠concept≠diagram≠E)-compliance drift; roles as initials; diagram jargon/too complex/wrong story; OS-module framed as throwaway app; OS solution-class wrong; **score stale after rework**; agent-set approval/date. 3. **Web-research when the concept names a tool, price, or technique** — verify it's the right tool, the price/tier is real, and the technique is state-of-the-art (WebSearch/WebFetch). Cite sources. 4. **Smallest-solution + KI-First tension**: is this over-engineered, or under-motorized where the customer expects real KI? Does the KI actually make sense for THIS customer? ## Coordination Read the shared **Team-Update-Feed** first (`GET /api/updates?company=`) — other parallel agents may already have flagged the industry, invented tools, shared modules, or pricing facts you'd otherwise re-derive. If your critique surfaces something **cross-cutting** (affects other processes), note it so it gets posted to the feed (the wrapper/worker posts `POST /api/update`). ## Output — the issue list For each issue: **[severity] short title — evidence (quote/field) — which guardrail — concrete fix.** Group by severity. End with a one-line verdict: is the concept sound, or does it need rework (and on which axis). Be specific and honest; a clean "no blocking issues" is a valid result only after you actually walked the register. This list is meant to be fed straight back into `processflow-process`.