worldsmith-methodology
Use when working in a project with a worldbuilding documentation ecosystem (docs/ or lore/ directory). Provides the documentation-first methodology: canonical hierarchy, doc roles (timeline, lore, characters, systems), propagation discipline, and the dual canonical and exploratory workflow.
What this skill does
# Worldsmith Methodology Rules and structure for documentation-first fiction worldbuilding. This skill provides what cannot be inferred from context alone: the editorial discipline, canonical hierarchy, propagation awareness, and character documentation standards that keep a worldbuilding project internally consistent as it grows. ## 1. Core Philosophy Treat documentation as the source of truth for the fictional world. The manuscript is one expression of the world; the docs define it. Docs and manuscript should stay consistent with each other, but recognize that creative work is messy — bidirectional updates happen naturally. A scene might introduce a detail that needs to flow back into the docs, or a doc revision might require manuscript changes. Both directions are legitimate. When docs and manuscript conflict, the docs are usually right — they represent deliberate editorial decisions. But exercise judgment. Sometimes the manuscript captures a better version of a detail that the docs haven't caught up with. The key discipline is noticing divergence and reconciling it, not enforcing rigid ordering. All documents are living documents, including the project's CLAUDE.md. As the world evolves through writing, update the docs. As the docs evolve, keep CLAUDE.md current — it is the most frequently read document in any session and serves as the entry point to the entire editorial system. A stale CLAUDE.md undermines every subsequent action. ## 2. The Document Ecosystem Worldbuilding projects organize their editorial knowledge across documents that serve specific roles. Think in terms of roles, not filenames — a project might call its timeline doc `timeline.md`, `chronology.md`, or `history-dates.md`. The role matters, not the name. Consult the project's CLAUDE.md for the mapping between roles and files. ### Document Roles - **Timeline Authority** — The authoritative source for dates, event sequences, character ages at specific points, and day-numbering within chapters. When any other doc or the manuscript disagrees with the timeline on a date or sequence, the timeline wins. - **Lore/History** — Mythology, founding stories, cultural context, historical events in narrative form. Contains the "why" behind the world's current state. Typically has both canonical sections (established history) and exploratory sections (myths being developed, histories not yet referenced in manuscript). - **Systems/Mechanics** — Magic systems, technology rules, geography and climate, economic structures, political systems. Specs with consequences: not just "how the system works" but "what it means for characters and plot." Typically has exploratory sections for systems under development. - **Character Tracking** — Character arcs, voice patterns, relationships, emotional trajectories, key scene anchors. The working reference during manuscript writing. See Section 5 for documentation standards. - **Style Conventions** — Prose principles, POV rules, tense conventions, intentional repetitions list, anti-cliche rules, consistency checklist. The guardrails for how the story is told, distinct from what it tells. - **Outline/Diagnostic Hub** — Scene-by-scene or chapter-by-chapter breakdown with cross-references to other docs. Functions as a control panel: what happens, which characters are present, which world elements are in play, what state things are in. The place to check "where does X appear?" - **Editorial Backlog** — Future ideas, sequel hooks, unexplored threads, deferred decisions. Ranked or prioritized by potential impact. A holding pen that prevents good ideas from being lost while keeping them out of canonical docs until they're ready. Typically has exploratory sections only. - **Themes/Anti-Cliche** — Thematic rules, philosophical framework, what patterns to avoid, what patterns to preserve. The project's aesthetic and intellectual commitments — what makes this story this story and not a generic version of itself. - **Feedback** — Date-stamped editorial reviews, reader feedback, revision notes with priorities. Progress tracking across revision cycles. A historical record of editorial decisions. - **Universe Bible** (optional, recommended for multi-work projects). A narrative-form synthesis of all canonical lore: history told as story, systems explained through their consequences, cultures described through the lives of the people in them. Think of it as the Silmarillion for this world. Not a database, but a readable document that tells the story of the world itself. Generated and maintained from canonical docs by the lore-writer. Updated when canonical lore changes. For single-work projects the lore docs themselves may suffice, but for a shared universe with multiple works, the universe bible is the single document that synthesizes everything into one coherent narrative. ### Canonical Hierarchy When sources disagree, resolve conflicts using this hierarchy (highest authority first): 1. **Canonical tables** (explicit CANONICAL markers in any doc) 2. **Timeline authority** (dates, sequences, ages) 3. **System specs** (mechanics, rules, geography) 4. **Character entries** (arcs, voice, relationships) 5. **Outline** (scene structure, cross-references) 6. **Manuscript** (the prose itself) Not every project will have all roles populated. Some projects may combine roles into fewer files. The hierarchy applies regardless of how many files exist. ## 3. Lore-First Workflow The Silmarillion approach: you do not write a novel and then document what you wrote. You build a world and then the novel emerges from it. The documentation IS the world. The manuscript is one expression of it. In practice, this means a specific creation order: 1. **Build lore first.** Before writing a scene, ensure the world it takes place in exists in canonical docs. The geography, the cultural context, the relevant systems, the political situation. If they do not exist yet, develop them before drafting prose. 2. **Derive the outline from lore.** The plot should follow from world constraints and character motivations, not be imposed on the world. If the outline requires something the lore does not support, update the lore first (or change the outline). 3. **Draft scenes grounded in lore.** Every scene draws on what the canonical docs establish. Characters speak from their documented voice patterns. Locations match their documented geography. Systems follow their documented rules. 4. **Verify scenes against lore.** After drafting, check that the scene does not contradict canonical docs. If it does, fix the scene (not the docs) unless the scene reveals a genuine lore error. 5. **Flow new facts back to lore.** A scene may introduce details that are not yet canonical (a character's offhand mention of a place name, a system interaction the docs did not anticipate). These flow back into the docs as canonical additions. This is the default workflow for new content. The bidirectional flow in step 5 is natural and expected. The discipline is in steps 1-2: build the world before you tell stories in it. ### Canonical Changes When modifying established facts (correcting a date, updating a character's arc after a chapter is written, revising a system rule), treat the change as canonical. Update the authoritative source doc first, then reconcile affected docs and manuscript passages. Follow the canonical hierarchy: if the change originates in a lower-authority source, verify it against higher-authority sources before propagating. ### Exploratory Ideas When developing new material (drafting mythology, sketching a future plot thread, experimenting with a system extension), treat it as exploratory. Write to exploratory or provisional sections of the appropriate doc. Mark the content as provisional or speculative. Do not update the manuscript based on exploratory content. Do not propagate exploratory content to other canonical sections. ### Promotion When exploratory content is ready to become ca
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.