benjaminstelzer/scoville-code-anti-ai-slop
Skill Claude CodeCodex
Goal-first guardrail for planning, changing, testing, reviewing, or removing code and engineering artifacts. Preserve observable outcome, canonical ownership, risk, validation, and honest evidence without scope drift. Not for conceptual questions unrelated to a codebase.
benjaminstelzer/scoville-brainstorm
Skill Claude CodeCodex
Produce one direct brainstorm in the current agent context when explicitly invoked for benchmark comparison. Do not create or simulate independent agents.
benjaminstelzer/scoville-brainstorm
Skill Claude CodeCodex
Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10-year-old, $0 budget), scores, clusters, prunes traps, and deepens top survivors. Use on /adhd, "ADHD mode", brainstorm/ideate intents, or open-ended design, architecture…
benjaminstelzer/scoville-brainstorm
Skill Claude CodeCodex
Use only to explore materially different solution mechanisms before a choice, with isolated generation, bounded prior-art comparison, calibrated originality language, and a decision-ready shortlist. Activate for explicit Scoville Brainstorm, or when a task explicitly requests several materially different solution…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Use only to explore materially different solution mechanisms before a choice, with isolated generation, bounded prior-art comparison, calibrated originality language, and a decision-ready shortlist. Activate for explicit Scoville Brainstorm, or when a task explicitly requests several materially different solution…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Goal-first guardrail for planning, changing, testing, reviewing, or removing code and engineering artifacts. Preserve observable outcome, canonical ownership, risk, validation, and honest evidence without scope drift. Not for conceptual questions unrelated to a codebase.
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Transfer active work to another agent or session as one compact, factual, copy-ready continuation prompt with fixed Receiver Instructions, Objective, State, and Resume Steps. Use only when the user explicitly asks for Scoville Handoff, a compact/context/session handoff, a handoff to a new session, "Übergabe an neue…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Repository-native planning guardrail for creating, maintaining, resuming, auditing, and handing off durable project Plans, Work Items, and Decision records through direct Markdown and YAML edits only. Use when a task invokes Scoville Plan, requests repository-owned implementation planning or decision records, must…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Conduct source-backed web research for current multi-source questions, technology and implementation discovery, or literature synthesis, with GitHub-first Development routing, scholarly-source routing, contradiction checks, and optional durable deep-research artifacts. Use for explicit research, landscape…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Guardrail for prose, fidelity, and reader-facing interface text. Use for drafting, editing, summarizing, localizing, source-exact work, or audits. Preserve facts, meaning, terms, behavior, schemas, attribution, and exact text. Excludes code semantics, machine data, and uninvoked supplied-text insertion without a…
benjaminstelzer/scoville-scribe-anti-ai-slop
Skill Claude CodeCodex
Framework-aware guardrail for UI design, implementation, and audit. Use for hierarchy, layout, states, responsiveness, accessibility, usability, or clarity. Preserve the product design system and platform language. Excludes backend-only work and prose. Compose with Code for engineering and Scribe for variable UI…