← ClaudeAtlas

gold-standardlisted

World-class completeness audit — score a project's rules/standards/features against best-in-class exemplars, name the gaps, fill missing rules, adopt as binding, then offer to conform existing code. Triggers on keywords: "/gold-standard", "gold-standard", "audit rules", "are we world-class", "fill gaps", "complete our rules", "conform old code".
HetCreep/CoalMine · ★ 11 · Code & Development · score 79
Install: claude install-skill HetCreep/CoalMine
# Gold Standard <!-- SHARED:LANGUAGE_HEADER --> Answer: **"For a project that does THIS — are rules/standards/features 100% vs world-class? If not, what's missing?"** Four acts: **AUDIT** → **FILL** → **ADOPT** → **CONFORM**. Stop at any. **Manual `/gold-standard` = interactive setup:** read `references/wizard.md` (dual-audience — layman 1-question default · programmer order→bill→pay). The auto/keyword path (the Triggers table) skips it. ## Triggers | Keyword | Act | |---|---| | "audit rules" / "gold-standard" / "are we world-class" | AUDIT | | "fill gaps" / "complete our rules" | FILL | | "work by these rules" / "follow from now on" | ADOPT | | "conform old code" / "retrofit" | CONFORM | | "fill and adopt" / `ACTION=fill-adopt` | AUDIT → FILL → summary → ADOPT → offer CONFORM | ## Consent gates (G1–G6, declared) | # | what it gates | when it fires | Agent lane | Hook lane | |---|---|---|---|---| | G1 | model tier | before work starts | `ask_question`, 3 tiers, wait for pick | suppressed — auto-Light, no tier question | | G2 | ADOPT | before treating the ruleset as binding | `ask_question` | `ask_question` | | G3 | CONFORM fix | before each fix | `ask_question` | `ask_question` | | G4 | RE-VALIDATE change | any re-stamp / rewrite / delete / consistency-fix | `ask_question` | `ask_question` | | G5 | entanglement hand-off | after the report, cross-domain finding | `ask_question`, once | `ask_question`, once | | G6 | self error-report | skill misbehaves | offer, never auto