メニュー
SkillsMP は rbergman/dark-matter-marketplace から 44 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 44 件中 40 件を表示しています。
Use when designing how audio communicates game state, creates emotion, and serves as a feedback system. Activate for sound effect design, adaptive music systems, spatial audio, ambient soundscapes, audio priority and ducking, emotional audio design, and audio…
原文の言語: 英語
Tone, diction, and sensory palette for cosmic-horror game narrative — Lovecraftian, weird-fiction, eldritch, Arkham-adjacent, deep-time or deep-space dread. Use when writing or reviewing in-game text, story bibles, item descriptions, or interstitials for a…
原文の言語: 英語
Telemetry and analytics for games: event taxonomy and schema, engagement/progression/economy/balance/UX metrics, funnel analysis, A/B testing and when not to, cohort analysis, dashboard design, and the interpretation traps — Goodhart's Law, Simpson's paradox,…
原文の言語: 英語
Tone and diction for comedy-horror where an institution processes the impossible without noticing: corporate horror, bureaucratic dread, workplace supernatural, company-town folk horror, the memo that mentions the wolves. Use when writing in-game text, tips,…
原文の言語: 英語
Designing a resource economy from scratch: the source/sink/converter flow graph, currency architecture, sink quality, inflation and deflation, feedback loops, scarcity as a difficulty lever, and simulating it in a spreadsheet before writing code. Use when…
原文の言語: 英語
Encounters as the intersection of space, adversaries and resources — across genres, not just action games. Covers the translation table for horde survival, ARPG, RTS, card, CYOA and autonomous sims; space vocabulary, enemy archetypes and composition, AI…
原文の言語: 英語
Session-level engagement: core loop health, the experience triangle (mechanics, fiction, feedback), emotion layering, tension curves, pacing, and whether choices are meaningful. Use when designing or diagnosing the engagement loop, planning the emotional arc…
原文の言語: 英語
Numeric balance across objects with stats: cost curves, transitive versus intransitive systems, payoff matrices, dominant strategy detection, power creep, and buff-before-nerf remediation. Use when pricing items, weapons, units or upgrades, designing counter…
原文の言語: 英語
The hub and first pass on any single mechanic: the 5-Component Filter (Clarity, Motivation, Response, Satisfaction, Fit), the plugin-wide Numbers Policy, the state-machine checklist, and a symptom-to-skill debugging table. Use when designing or critiquing one…
原文の言語: 英語
Sentence- and passage-level prose craft for short-form game narrative: choice text, interstitials, vignettes, event text, quest copy, epilogues, story bibles, and any in-game writing the player actually reads. Use when writing or reviewing narrative prose for…
原文の言語: 英語
Keep large bodies of authored-at-volume content from converging: events, quests, items, barks, enemy variants, flavour text, procedural encounters, LLM-written narrative. Use when producing a content pack, when the tenth generated item feels like the third,…
原文の言語: 英語
Determine whether a game mechanic, displayed value, or currency actually affects outcomes, via a four-stage ablation: exercise, sensitivity, ablate, verdict. Use when asked whether a mechanic matters or earns its place, when a change produces no measurable…
原文の言語: 英語
Capture the player's felt reactions to play verbatim into an append-only docs/moments.md, at the time they happen. Use whenever someone reports an aesthetic, emotional, or semantic reaction to playing — 'feels chunky', 'that's satisfying', 'this doesn't read…
原文の言語: 英語
Why players return, and where the ethical lines are: Self-Determination Theory, the six motivation profiles, reinforcement schedules, pity and bad-luck protection, intrinsic versus extrinsic reward and the overjustification effect, loss aversion, collection…
原文の言語: 英語
Check the build against the project's written north star, pillars, or design brief. Two tiers: a 60-second GLANCE at the start of any session touching game systems, and a full AUDIT at milestone boundaries, before multi-session tuning or optimization passes,…
原文の言語: 英語
Cognitive load for players: perception, attention and memory limits, Gestalt principles for HUD and UI, signal-noise discipline, onboarding ramps, tooltips and affordances, and developer blindness. Use when designing or reviewing a HUD or UI layout, writing a…
原文の言語: 英語
Designing and reading playtests: what to observe versus what to ask, question generation, metrics to track, sample sizes, confirmation-bias protocol, and solo-developer validation when you have no testers. Use when planning a playtest or usability session,…
原文の言語: 英語
The math of growth over time: power curve shapes, XP formulas, the flow channel, felt versus actual power, the difficulty sandwich, adaptive difficulty, and unlock pacing. Use when designing XP curves, level-up formulas, difficulty ramps or unlock schedules,…
原文の言語: 英語
Design for games whose primary loop runs without a human input: self-playing simulations, AI-versus-AI matches, autonomous world sims, spectator games, and any game balanced by a bot rather than a playtester. Use when the game plays itself or has zero human…
原文の言語: 英語
Structural architecture of game systems: the interaction matrix, coupling analysis, emergence, possibility space, cursed problems, and build order. Use when choosing which systems a game needs, evaluating whether to add or cut one, planning build sequence, or…
原文の言語: 英語
Use when designing any player-facing feature, evaluating a game for accessibility, responding to accessibility feedback, designing difficulty or assist options, adding subtitle/caption systems, implementing input remapping, or when a player reports they can't…
原文の言語: 英語
Social and competitive design that does not require players to be online together: ghost/replay data, leaderboards, asynchronous PvP, offline vulnerability, and anti-snowball mechanics. Use when adding leaderboards or high-score tables, designing ghost races…
原文の言語: 英語
Juice, feedback layering, screen shake/particles/sound timing, the perception-action cycle, and 'why does this feel bad?' diagnostics. Use when implementing player actions, combat hits, collectibles, UI transitions, weapon impacts, jumps, dashes, or any…
原文の言語: 英語
Per-frame performance and GC-pressure optimization for JS/TS game code. Use when editing game loops, update functions, render passes, physics steps, particle systems, or any code that runs every frame; when diagnosing jank, frame drops, or stuttering; when…
原文の言語: 英語
Use when starting a new game project, pivoting a concept, evaluating whether an idea is worth building, or when prototyping has stalled without clarity. Provides a layered Vision Stack for going from raw concept to validated, structured design. Use BEFORE…
原文の言語: 英語
Idle, incremental, and clicker game design: exponential cost curves, growth-rate ratios, prestige and reset layers, offline progress, unlock cadence, and the wall. Use when building an idle or incremental game, adding an idle or offline layer to another…
原文の言語: 英語
Quest structure, branching narrative architecture, environmental storytelling, dialogue design, and narrative pacing. Use when designing quest systems, writing branching dialogue, structuring story arcs, when narrative feels disconnected from gameplay, when…
原文の言語: 英語
Bootstrap browser-based games with PixiJS 8 and a modern retro/vector aesthetic (Geometry Wars, Asteroids, Tempest, Tron). Use when creating a new game, starting a browser game project, building an arcade game, prototyping a game, setting up PixiJS, or when…
原文の言語: 英語
Patterns for setting up just (command runner) in projects. Use when creating build systems, setting up new repos, organizing build/test/lint recipes, or when the user asks about just/justfile configuration. Covers both simple single-project repos and…
原文の言語: 英語
"Boring Rust" — clone freely, simple control flow, max-strictness lints with mechanical enforcement, ownership-honest code that compiles and reads cleanly. Use when implementing, debugging, refactoring, or reviewing Rust code; resolving borrow checker errors;…
原文の言語: 英語
Strict TypeScript with zero-any tolerance, no-unsafe-* lints, floating-promise prevention, and disciplined type-system usage. Use when implementing, debugging, refactoring, or reviewing TypeScript code; resolving type errors; configuring…
原文の言語: 英語
Activate at session start when using Agent Teams for complex multi-agent work. Establishes team lead role with delegation protocols, teammate spawning, model selection, and beads integration. You coordinate the team; teammates implement.
原文の言語: 英語
Initialize a new repository with standard scaffolding - git, gitignore, AGENTS.md, justfile, mise, beads, and timbers. Use when starting a new project or setting up an existing repo for Claude Code workflows.
原文の言語: 英語
Idiomatic Go with proper error handling, concurrency patterns, slog, generics, and clean package design. Use when implementing, debugging, refactoring, or reviewing Go code; designing package boundaries; resolving race conditions or goroutine leaks; setting…
原文の言語: 英語
Modern Python with uv, ruff, pyright, strict typing, and clean module design. Use when implementing, debugging, refactoring, or reviewing Python code; designing module boundaries; setting up Python projects; resolving type errors; tightening pyproject.toml;…
原文の言語: 英語
Multi-perspective deliberation using Agent Teams. Spawn 3-5 teammates with different viewpoints and optionally different models to debate decisions, evaluate specs, or explore trade-offs. Inspired by karpathy/llm-council.
原文の言語: 英語
Collaborative code review using Agent Teams where reviewers discuss findings, challenge each other, and converge on a unified assessment. Evolves dm-work:review from isolated parallel reviewers to a review team.
原文の言語: 英語
Dev-tool and runtime version management with mise — the modern replacement for nvm, pyenv, goenv, rbenv, and asdf. Use when setting up a new repo, pinning Node/Python/Go/Rust/Bun versions, configuring per-project tool versions via .mise.toml or…
原文の言語: 英語
Reduce CLI output noise before it reaches LLM context. Use when setting up repos, troubleshooting context overflow from build/test/git output, or when Bash tool output exceeds limits. Covers RTK (zero-config baseline) and tokf (per-project customization).…
原文の言語: 英語
QA web applications using Chrome DevTools MCP. Use when testing running apps, verifying acceptance criteria against a live UI, checking for console errors, evaluating UI behavior, or running regression checks. Requires the chrome-devtools MCP server to be…
原文の言語: 英語