Menu
Reconstruct Dazzle/HM judgement from stems before inventing structure
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Reconstruct Dazzle/HM judgement from stems before inventing structure
Run all quality checks on modified files — the on-demand pre-ship quality gate
Commit, verify, tag, and push with the repo's pre-flight gate suite (lint, type, drift gates, docs build)
Use when authoring or revising trial.toml scenarios for dazzle qa trial — puts an LLM in the shoes of a real business user evaluating a Dazzle app. Use when the user asks to "set up qa trials", "write a trial scenario", "evaluate this app as a user", or mentions qualitative/trial/business-user testing. Also use when a trial report is sparse or unhelpful — the scenario itself is usually the root cause.
Use when writing or editing Dazzle .dsl files — syntax rules, the mistakes agents actually make, and pointers to the drift-gated references. Complements (never replaces) CLAUDE.md's DSL Quick Reference.
Use when the user wants to generate a stakeholder-facing English specification document (SPECIFICATION.md) from a Dazzle DSL project — for investors, business leaders, founders, or non-technical decision-makers. Reverses the usual DSL→app flow into DSL→prose.
| name | stems |
| description | Reconstruct Dazzle/HM judgement from stems before inventing structure |
Use when starting non-trivial work on the monorepo, HaTchi-MaXchi, or an example app — architecture, new Hyperparts, DSL domain expansion, RBAC, or “should we build X like Y?”
stems/INDEX.md, then the stem that matches the task.packages/hatchi-maxchi/stems/INDEX.md if UI/Hyperparts.examples/<app>/stems/INDEX.md or project stems/INDEX.md.AGENTS.md (repo or package) for commands and playbooks.stems → AGENTS → ADRs/decisions → maps/tests → guides → gallery mocks
packages/hatchi-maxchi/docs/agent/