@jwynia

revision diagnoses manuscript-level problems across six passes (structural, scene, character, dialogue, prose, polish), addresses psychological blocks (overwhelm, perfectionism, deletion anxiety), and routes writers through systematic top-down editing keyed to their specific revision state.

drafting helps writers diagnose and work through specific blocks (blank page, middle stall, perfectionism) by identifying which state they're in, checking for internal editor interference, and applying concrete methods like zero drafts, placeholders, and daily quotas to keep momentum forward.

code-review provides structured diagnostic guidance across correctness, maintainability, performance, and security. includes checklists, complexity thresholds, and anti-pattern recognition to catch defects before merge.

presentation-design covers audience-centered design frameworks, visual structure (assertion-evidence), cognitive load management, and evaluation rubrics. applicable across presentation tools with explicit anti-patterns and implementation checklists.

story-idea-generator provides a genre-first framework for developing story concepts, starting with desired emotional impact and aligning setting, character, and plot elements to deliver that experience across 11 elemental genres.

competency-builder diagnoses where capability development stalls using eleven diagnostic states, from missing frameworks through operational maturity. it guides teams backward from failure modes to observable competencies, then forward through scenario design, audience mapping, and feedback loops.

requirements-analysis guides developers from vague intent to validated needs through state-based diagnosis, focusing on distinguishing real problems from solution-first thinking and uncovering hidden constraints before design work begins.

story-sense diagnoses narrative problems across a seven-state continuum, matching symptoms to interventions via decision tree. routes writers to targeted skills rather than solving directly.

scene-sequencing teaches the scene-sequel rhythm for narrative pacing. it diagnoses flat or exhausting stories by checking goal clarity, conflict escalation, disaster quality, and processing time between action beats.

frontend-design provides analysis and generation tools for building intentional, production-grade interfaces. covers style auditing, token extraction, palette and typography generation, and multi-framework component templating with explicit anti-slop design philosophy.

worldbuilding diagnoses why fictional settings feel thin or unconvincing by identifying missing systemic depth, then routes to specialized skills for intervention. covers seven failure modes from backdrop worlds to shallow belief systems.

security-scan detects code vulnerabilities across owasp top 10, secrets, and misconfigurations with multiple scan modes and configurable severity thresholds. pattern-based detection covers injection, crypto weaknesses, and hardcoded credentials with actionable remediation guidance.

genre-conventions diagnoses misaligned emotional promises and generates fixes through eight genre states. covers elemental genres as reader experience, not shelf categories, with explicit hierarchies for hybrid work and intervention strategies keyed to specific failure modes.

media-adaptation provides a four-phase framework for extracting functional elements from existing stories and recreating them in new contexts. maps emotional appeal, power dynamics, and conflict architecture before systematically translating setting-dependent elements while validating systemic consistency.

revealjs-presenter provides templated html slide generation with color-coordinated section breaks, card layouts, and stat display patterns. theme-driven content strategy enforces word limits and slide ratios. foundation is comprehensive but lacks guidance on failure modes and recovering from malformed input.

architecture-decision provides frameworks for evaluating trade-offs and documenting decisions via the adr template, with context-pattern mappings and refactoring strategies. lacks concrete procedural steps and edge case handling.

oblique-worldbuilding guides writers to craft chapter epigraphs using documentary voices with limited perspective. it emphasizes systemic blindness over temporal distance, providing frameworks for connecting documents to narrative themes through irony and inference rather than direct commentary.

npm-package covers bun-based library authoring, build setup, and npm publishing. addresses esm/cjs interop and exports configuration for single-package repos.

character-arc guides writers through designing internal transformations by diagnosing stalled arcs, mapping lie-to-truth journeys, and identifying resistance beats. covers positive, negative, and flat arc types with concrete anti-patterns and story-to-arc beat alignment.

summarization covers matching summary type to purpose, audience, and context. provides taxonomy of approaches (reduction, structural, purpose-oriented) with execution patterns and quality checks for different condensing tasks.

outline-collaborator proposes story structure collaboratively, generating scene beats and character arcs. scope is clear but execution guidance remains abstract, and actual trigger conditions for when to apply each mode are underspecified.

docx-generator handles word document creation, template population, content extraction, and placeholder replacement through programmatic api access. templating preserves corporate styling while automating common workflows like reports and contracts.

cliche-transcendence provides a framework for identifying and transforming predictable story elements by rotating them across four axes (form, knowledge, goal, role) rather than inverting them. the eight-step process guides writers from enumeration through downstream consequence mapping.

chapter-drafter orchestrates iterative editorial passes on prose scenes, applying a fixed revision hierarchy (structure, character, originality, dialogue, prose). requires pre-existing outline and character work before invocation.

context-network provides high-level framing for organizing project knowledge across sessions, but lacks concrete procedural steps. covers diagnosis and scaffolding generation without detailing how execution happens.

web-search-tavily wraps the tavily api for structured web search with relevance scoring and optional ai summaries. requires explicit api key provisioning and designed for real-time lookups outside training data.

task-decomposition identifies when a task is too large or unclearly scoped, then provides trigger phrases to recognize decomposition opportunities. lacks procedural clarity and failure mode handling.

web-search provides basic real-time web queries via built-in websearch without api keys, suitable for fact verification and current events, but lacks detailed procedural steps and advanced filtering capabilities.

flash-fiction maps nine diagnostic states to common craft failures in stories under 1500 words, helping writers identify which dimension (structure, character, subtext, imagery, language) needs repair.

brainstorming helps escape convergent ideation by diagnosing whether you're stuck in repetition or expanding an early seed, then routing to appropriate expansion or escape protocols.

godot-asset-generator bridges ai image apis (dall-e, replicate, fal.ai) and godot 4.x, automating sprite and tileset generation from prompts through import-ready preparation. scope is 2d assets only.

gentle-teaching provides a framework for ai-assisted instruction emphasizing learner empowerment and independence through scaffolded support, structured feedback, and guided discovery over direct answers.

godot-best-practices outlines gdsript coding standards and architecture patterns for godot 4.x, covering scene organization, state machines, and common game systems, but lacks concrete procedures and failure handling.

agile-workflow orchestrates git-based development sequences with checkpoint control, pausing at decision points. covers standup, task progression, sprint ceremonies, and work resumption across platform-agnostic repositories.

story-zoom flags consistency gaps across fiction abstraction layers (pitch, structure, scenes, entities, prose) and surfaces which levels need updating when a change propagates, but lacks concrete sync procedures.

claim-investigation decomposes social media claims into atomic assertions, verifies components independently, and distinguishes confirmed facts from narrative interpretation for fact-checking workflows.

system-design guides solo developers through architecture decisions by surfacing requirements clarity and trade-offs, but lacks complete procedures for translating validated needs into concrete component designs.

world-fates introduces probabilistic pressure on long-term power structures to maintain world dynamism. it generates fate-shift proposals for entities accumulating temporal risk, requiring human approval before applying changes to a shared world bible.

shared-world organizes canonical fiction data in wiki format for multi-author consistency. lacks concrete procedures for contradiction detection, version control, or contributor workflows despite framing potential.

prose-style diagnoses sentence-level craft failures in fiction by examining diction, syntax, rhythm, and voice. it frames style as structural content rather than decoration and anchors guidance in concision and intentionality.

joke-engineering applies systems thinking to diagnose why humor misfires and recommend targeted structural improvements. it models jokes as measurable systems with nine calibrable properties: setup clarity, frame collision, misdirection, cognitive load, timing, audience alignment, surprise, emotional stakes, and resolution speed.

identity-denial provides a thematic framework for constructing character arcs where protagonists resist acknowledging their own transformation, mapping denial intensity across spectrum stages. useful for writers; not actionable for systems.

novel-revision provides a conceptual framework for tracking narrative changes across thematic, structural, and prose layers, but lacks actionable procedures and concrete decision criteria for managing cascade effects.

dna-extraction identifies underlying functional patterns in existing creative works to enable principled adaptation, isolating what makes narrative mechanics work rather than their surface forms.

fact-check provides conceptual framework for verification-as-separate-pass but lacks concrete procedure, trigger definitions, and failure handling. remains largely theoretical.

language-evolution establishes principles for realistic linguistic development in fictional worlds, covering phonological change, social stratification, and contact effects, but lacks procedural depth and actionable workflow.

game-facilitator provides narrative rpg game mastering guidance for collaborative storytelling, emphasizing emergent plots, player agency, and world responsiveness. philosophical framework rather than operational skill.

character-naming diagnoses llm name clustering and applies external entropy to generate diverse character names. addresses the statistical median problem where models repeat chen, patel, marcus across generations.

belief-systems provides conceptual grounding in how real religions function (experiential, ecological, social, institutional, narrative, ritual) but lacks procedural clarity on applying these principles to actual worldbuilding. useful reference framework, incomplete skill.

memetic-depth is a worldbuilding texture framework for writers seeking to craft fictional cultures with implied historical depth. it uses cognitive triangulation (recognizable, inferrable, inscrutable elements) to create reader perception of independent cultural evolution. the skill is conceptual rather than procedural.

multi-order-evolution guides systematic societal development across generations by layering environmental pressures and institutional drift, producing divergent cultures with compound adaptations that resist simple extrapolation.

typescript-best-practices frames guidance for ts code generation and review, but lacks concrete procedural steps, failure mode analysis, and actionable decision logic to execute on its stated scope.

systemic-worldbuilding guides writers through consequence mapping when introducing speculative changes, tracing cascading effects across domains. framework begins well but lacks actionable depth and completion.

governance-systems outlines eight abstract principles for designing fictional political entities, but lacks actionable procedure, concrete examples, and decision logic to guide actual world-building work.

endings diagnoses why fiction fails at resolution by articulating that good endings balance inevitability with surprise, but offers almost no actionable method to apply this insight.

pdf-generator — an installable skill for AI agents, published by jwynia/agent-skills.

Act as an active writing partner who contributes content alongside the human writer. Use when the writer wants a collaborator who generates prose, dialogue,…

Extract and document a writer's distinctive voice patterns for consistent reproduction. Use when you need to capture writing voice, analyze writing style,…

Systematically evaluate completed short stories or novel chapters to identify strengths, weaknesses, and improvement opportunities. Use after drafting to…

Diagnose research quality and guide systematic query expansion. Use when starting research on any topic, when stuck in research, or when unsure if research is…

Diagnose flat dialogue, same-voice characters, and lack of subtext. Use when conversations feel wooden, characters sound alike, or dialogue only does one thing…

Create and manipulate PowerPoint PPTX files programmatically. Use when the user needs to generate presentations, modify PPTX templates, extract slide content,…

Build new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.

Diagnose why names don't work and guide creation of names that do. Use for brand names, product names, character names, place names, and titles when something…

Orchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow',…

Act as an assistive writing coach who guides but never writes for the user. Use when helping someone develop their own writing through questions, diagnosis,…

Transform comprehensive written content into purposeful spoken guidance. Use when adapting for speech, converting to spoken format, optimizing for listening,…

Diagnose branching narrative problems. Use when choices feel meaningless, when branching is unmanageable, when player agency conflicts with authored story, or…

Generate correct shadcn/Tailwind layouts by applying CSS mental models. This skill should be used when the user asks to 'create a shadcn layout', 'fix layout…

Analyze agent-user interaction transcripts to identify context network maintenance needs and guidance improvements. Use after significant agent interactions or…

Diagnose and calibrate tonal delivery for tabletop RPG sessions. Use when narration feels flat, tone shifts jarringly, descriptions overwhelm play, or energy…

Generate speculative fiction stories about systemic exploitation by collapsing comfortable moral distances. Use when exploring how privilege and harm are…

Diagnose lyric problems across prosody, rhyme, meaning, register, sound, and structure. Use when AI-generated or human lyrics feel flat, cliched, awkward, or…

Write stories designed to help listeners fall asleep. Use for bedtime podcasts, meditation content, calming narratives, or any content where the goal is gentle…

Evaluate representation and flag potential harm concerns. Use when writing characters from marginalized groups, depicting sensitive subject matter, or wanting…

Diagnose competitive product analysis state and guide through systematic market evaluation. Use when analyzing a product category, building feature…

Reverse-engineer published books into structured scene-by-scene outlines for study. Use when analyzing craft, learning story structure from masters, or…

Diagnose book marketing copy problems and generate platform-optimized blurbs, descriptions, taglines, and query pitches. Use when marketing copy feels weak,…

Guide AI agents to generate complete PageObject pattern web scraper projects using Playwright and TypeScript with Docker deployment. Supports agent-browser…

Help neurodivergent users break down overwhelming tasks into manageable steps. Use when tasks feel paralyzing, when executive function is struggling, when…

Design cities, towns, and settlements for fictional worlds. Use when creating urban environments, mapping city districts, or when settlements need realistic…

Design economic systems for fictional worlds. Use when worldbuilding needs currencies, trade networks, resource economies, or when economic pressures should…

Diagnose thinking failures and maintain process-sovereignty by auditing cognitive orientation and operation balance.

ebook-analysis — an installable skill for AI agents, published by jwynia/agent-skills.

xlsx-generator — an installable skill for AI agents, published by jwynia/agent-skills.

Structure stories around essential emotional moments using Rodriguez's approach integrated with elemental genres. Use when plotting feels mechanical, when…

musical-dna — an installable skill for AI agents, published by jwynia/agent-skills.

pwa-development — an installable skill for AI agents, published by jwynia/agent-skills.

outline-coach — an installable skill for AI agents, published by jwynia/agent-skills.

Guide agents through structured research including planning, multi-query execution, source analysis, and synthesis. Use for comprehensive topic research, deep…

Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and…