Scene Construction Scam
Builds scenes that are reported rather than generated, by running a four-slot SCAM qualification gate (Setting, Character, Action, Meaning) with a source required per slot, a scene floor and ceiling, the 1-of-20 telling-detail cut with a provenance veto, the RUE pass, and a scene/summary narrative-distance audit against per-form ratio targets. Every technique has a person variant and a system variant (market, protocol, institution, codebase, supply chain). Use when turning research notes into a scene, opening a section with a moment, deciding whether a passage is a scene or summary, or auditin
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill scene-construction-scamgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/scene-construction-scam ~/.claude/skills/scene-construction-scamPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Scene Construction (SCAM) ## Table of Contents - [Core Principles](#core-principles) - [Workflow](#workflow) - [The SCAM Gate](#the-scam-gate) - [Scene Floor and Ceiling](#scene-floor-and-ceiling) - [Scene or Summary: Distance Targets](#scene-or-summary-distance-targets) - [The Scene Provenance Ledger](#the-scene-provenance-ledger) - [Guardrails](#guardrails) - [Quick Reference](#quick-reference) **Related skills:** Use `narrative-fidelity-audit` for the interiority ladder and the bright lines, `narrative-arc-mapping` for where scenes sit in the whole piece, `narrative-opposition-web` for who the scene's actors oppose, `writing-structure-planner` for sequencing, `slop-detector` for the register pass that runs last. The fidelity audit owns the ladder and runs on a finished draft; this skill runs on a candidate scene before drafting. ## Core Principles 1. **Gate 4 decides everything**: Could this passage have been written without the source material? If yes, it is generated, not reported. Kill it. No other test in this skill outranks that one. 2. **An empty slot is a result, not a problem**: any unfilled SCAM slot means the passage is not a scene. Demote it to summary. Never fill a slot by inference, and never fill it because the piece needs a scene there. 3. **Sourced, never verified**: this skill tracks provenance. It cannot check whether a source is true. Write "sourced to X"; never write "verified" or "fact-checked".
Details
- Skill name
scene-construction-scam- Repository
- lyndonkl/claude
- Path
skills/scene-construction-scam/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Scene Construction Scam skill do?
Builds scenes that are reported rather than generated, by running a four-slot SCAM qualification gate (Setting, Character, Action, Meaning) with a source required per slot, a scene floor and ceiling, the 1-of-20 telling-detail cut with a provenance veto, the RUE pass, and a scene/summary narrative-distance audit against per-form ratio targets. Every technique has a person variant and a system variant (market, protocol, institution, codebase, supply chain). Use when turning research notes into a scene, opening a section with a moment, deciding whether a passage is a scene or summary, or auditin
How do I install the Scene Construction Scam skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Scene Construction Scam popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
Academic Letter Architect
200lyndonkl/claude
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
Adr Architecture
200lyndonkl/claude
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
Scientific Clarity Checker
200lyndonkl/claude
Reviews scientific documents for logical clarity, argument soundness, and rigor by auditing hypothesis-data alignment, claim-evidence chains, quantitative precision, hedging calibration, and terminology consistency across any document type. Use when reviewing scientific argumentation, checking claims vs evidence, auditing terminology, or when user mentions check clarity, review logic, scientific soundness, hypothesis-data alignment, or claims vs evidence.
Retrieval Search Orchestration
200lyndonkl/claude
Designs retrieval strategies for querying knowledge graphs in RAG systems, covering pattern selection (global-first, local-first, U-shaped hybrid), query decomposition for multi-hop reasoning, ranking and constraint configuration, and provenance tracking for citation. Use when designing retrieval pipelines, orchestrating search over knowledge graphs, or when user mentions retrieval strategy, search orchestration, query decomposition, multi-hop reasoning, provenance tracking, or citation in GraphRAG.
Scientific Email Polishing
200lyndonkl/claude
Composes and polishes professional scientific correspondence -- emails to collaborators, journal cover letters, and responses to peer reviewers -- ensuring clear communication, appropriate tone, explicit asks, and professional formatting for academic contexts. Use when writing or polishing scientific emails, cover letters to editors, reviewer responses, or when user mentions email to collaborator, cover letter to journal, reviewer response, or professional scientific correspondence.
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.