Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 341 files from 1 736 authors, of which 61 700 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Extract 3 to 5 actionable design pillars from a game, feature, loop, or system based on what the design actually rewards and prioritizes. Use when a team can describe mechanics but cannot clearly articulate the principles those mechanics serve, when pillars are vague, generic, or contradictory, or when you need a sharper set of tradeoff-driven pillars that can guide decisions and cut features.
Extract the core player fantasy from a game, feature, loop, or pitch based on what the design actually lets the player do, feel, and become. Use when a team can describe mechanics but cannot clearly articulate the fantasy those mechanics are supposed to deliver, when a concept feels emotionally vague, when a pitch names features instead of a player promise, or when you need to test whether the claimed fantasy is real, weak, conflicted, or absent.
Audit a game, feature, failure loop, combat encounter, reward system, progression wall, or high-variance mechanic for perceived fairness and frustration. Use when diagnosing whether players feel cheated, whether difficulty feels deserved, whether randomness, feedback, and challenge interact badly, or why a design remains technically functional yet still produces anger, blame, or refusal to retry.
Generate and compare at least five game design solution options for a feature, system, UX issue, live-ops problem, or design challenge. Use when several ideas already exist, when a team needs broader comparison before choosing, or when one favorite answer is dominating too early and better alternatives may be getting ignored.
Audit a game, feature, encounter structure, roguelite run, puzzle sequence, onboarding path, or progression gate through the lens of its failure loop: what happens after the player fails, what they learn, what they lose, and why they would or would not try again. Use when diagnosing whether failure teaches, motivates, stalls, humiliates, exhausts, or ejects the player, or when tuning punishment, retry structure, and post-failure recovery.
Prioritize game design feature options by comparing expected impact, implementation cost, strategic fit, and roadmap context. Use when choosing between competing feature ideas, deciding what to do now versus later, ranking solution paths after ideation, or identifying which option is best immediately and which is better long-term.
Audit a game, feature, level sequence, combat loop, progression curve, onboarding path, event structure, or return-player journey through the lens of Flow theory. Use when evaluating whether challenge and skill stay aligned over time, diagnosing boredom, anxiety, frustration spikes, difficulty cliffs, dead zones, or pacing drift, or identifying where a design stops feeling absorbing and starts feeling exhausting or empty.
Audit a game, feature flow, economy path, onboarding journey, progression chain, or live-ops loop for friction quality and friction accumulation. Use when diagnosing where players stall, disengage, churn, or feel overloaded; when distinguishing productive challenge from harmful friction; or when evaluating whether constraints, waiting, confusion, resource pressure, or multi-step dependencies are creating strategy, tension, frustration, or deadlock.
Audit a game feature, flow, event, onboarding step, progression action, monetization surface, retention mechanic, or social prompt using the Fogg Behavior Model: Motivation, Ability, Prompt. Use when evaluating whether a design actually causes the intended player behavior, diagnosing weak feature adoption, identifying friction or mistimed prompts, or understanding why a feature that seems valuable is not being used.
Evaluate game features, feature pitches, live-ops ideas, UX changes, economy changes, roadmap choices, retention initiatives, monetization initiatives, and ambiguous design problems using the GROW model: Goal, Reality, Options, Will. Use when a team needs structure, clearer decision-making, better option generation, explicit tradeoff analysis, or a concrete recommendation and next-step plan instead of circular discussion.
Audit a game, feature, progression loop, return-player experience, metagame layer, or session structure for density of goals, immediacy of goals, safe stopping points, and return triggers. Use when evaluating whether players can quickly find something meaningful to do, whether the game offers enough short-term, mid-term, and long-term goals, whether session lengths are flexible enough for real player schedules, or why a game feels aimless, overwhelming, or unable to fit into fragmented playtime.
Audit a game's FTUE (First Time User Experience) through the lens of the Hero's Journey / monomyth. Use when reviewing onboarding, tutorial flow, first-session retention, first 30 seconds, early-session emotional hooks, mentor/tutorial character usage, first meaningful action, or whether an FTUE makes the player feel like the hero of the experience rather than a passive victim of UX chores.
Turn a vague feature idea or design direction into a clear game design goal with purpose, scope, fit, success criteria, and constraints. Use when a feature sounds promising but fuzzy, when a team cannot explain why something should exist, when success is unclear, or when a concept needs a stronger goal before ideation, evaluation, or prototyping.
Start from the ideal player-facing result and work backward to the design steps, systems, and decisions required to reach it. Use when a team knows the kind of experience it wants but not how to structure the path there, when redesigning a feature around a stronger destination, or when clarifying what must be true for a concept to feel successful.
Audit a game, feature, progression system, social system, live-ops loop, monetization surface, or onboarding flow through a granular player motivation taxonomy. Use when evaluating which player motivation archetypes a design strongly serves, neglects, or actively repels; when comparing a concept against segments such as Steady Advancers, Curious Solvers, Competitive Achievers, Imaginative Creators, Strategic Leaders, Immersed Storywriters, Reward Seekers, Passionate Belongers, and Category Enthusiasts; when translating player research into practical design recommendations; or when you need a more nuanced alternative to a simple Bartle-style motivation read.
Audit a game feature, roadmap candidate, UX improvement, support system, connective-tissue feature, or quality-of-life change for KPI coverage bias and measurement blind spots. Use when a team is overvaluing only directly attributable metrics, neglecting foundational work that is hard to measure, or struggling to justify features whose value is real but not cleanly tied to one headline KPI.
Audit an existing leaderboard or competitive ranking system in a game for stagnation risk, scale problems, goal density, motivation quality, reward bracket design, group composition fairness, and top-of-ladder sustainability. Use when evaluating a leaderboard that feels flat, unfair, or disengaging; when reviewing a competitive feature before launch; or when diagnosing why a leaderboard isn't driving expected engagement or retention.
Design a complete leaderboard system from scratch for a game, feature, or competitive mode. Covers group structure, league ladder, round cadence, reward brackets, score design, group composition, and top-of-ladder sustainability. Use when starting a new competitive feature, when a basic leaderboard needs a full redesign, or when a team needs a concrete leaderboard specification to build from. Always asks intake questions before designing — and offers sensible defaults if the designer doesn't have answers yet.
Create a concise one-page game design document and export it as both markdown and PDF. Use when a user wants a one-page design doc, one-pager, pitchable design summary, or compact game concept sheet that captures identity, pillars, summary, features, interface, aesthetic direction, sound, audience, platform, and milestone plan on a single page.
Stress-test a game concept, feature, system, or pitch through a deliberately provocative, ambition-seeking design lens inspired by Peter Molyneux-style overstatement. Use when a concept feels too safe, too polite, under-fantasized, mechanically competent but emotionally weak, or in need of sharp provocations that push fantasy, reactivity, and memorable moments before being grounded back into reality.
Audit a game, feature, live-ops layer, social system, or multiplayer concept for the quality and fit of its social design. Use when evaluating collaboration, competition, collaborate-to-compete structures, matchmaking, guilds/clubs, synchronous versus asynchronous play, realtime constraints, depth of social interaction, community formation, vanity/status systems, or how to add social play to a mostly single-player game.
Evaluate a game design, feature proposal, system concept, pitch, or prototype on the novelty spectrum between too familiar and too novel. Use when assessing whether a concept has enough differentiation, whether it violates player expectations too strongly, how it balances familiarity and innovation, or whether its innovation pattern is best understood as incremental innovation, recombination, simplification, or a more radical break from established mental models.
Identify the single highest-leverage thing to remove from a game design, feature, system, UX flow, pitch, roadmap item, or prototype in order to improve it significantly. Use when a design feels bloated, muddy, overengineered, overly tutorialized, friction-heavy, or diluted by low-value mechanics, and you want a subtractive critique with rationale, tradeoffs, and a cleaner alternative.
Generate multiple game design solution paths before committing to one direction. Use when a feature, live-ops idea, UX problem, economy issue, or design challenge feels too quickly narrowed, when a team is looping around one favorite answer, or when you need several credible options with tradeoffs instead of a single premature recommendation.
Audit a game, feature, session, level, event, onboarding flow, reward sequence, or return-player experience through the lens of the peak-end rule. Use when evaluating which moments players are most likely to remember, whether the emotional high points are strong enough, whether endings, exits, and completions leave the right aftertaste, or why an experience with decent average quality is still remembered as flat, frustrating, or unexpectedly great.
Audit a game, feature, live-ops system, onboarding flow, progression loop, social feature, monetization flow, or return loop for player need satisfaction using Self-Determination Theory and the PENS lens. Use when evaluating whether a design is actually fun beyond surface KPIs, diagnosing weak retention or shallow engagement, comparing variants, identifying where a system denies autonomy, competence, or relatedness, or understanding whether a game feels emotionally nourishing or quietly depleting.
Audit a game feature, combat system, loot table, reward loop, procedural system, chance mechanic, or uncertainty-driven design by how players are likely to perceive its randomness. Use when you need to evaluate whether a system will feel fair, streaky, rigged, sabotaging, manipulable, or skill-undermining; when players may misread independent events as patterned; or when randomness may sit too close to player action and create frustration. Analyze expectation gaps, gambler's-fallacy-style reactions, hidden pattern-seeking, input-versus-output randomness, perceived fairness, exploit risk, and ways to reshape presentation or mechanics.
Audit a video game pitch deck, publisher deck, funding deck, or investor-facing game presentation for clarity, structure, persuasiveness, visual readability, business-case completeness, and publisher-fit. Use when reviewing a pitch deck before sending to publishers, polishing a deck for meetings, checking whether the deck answers the essential questions about who, what, why, when, budget, and opportunity, or evaluating whether a deck sells both the game and the collaboration case rather than just dumping information.
Extract the ideal player persona and anti-persona for a game, feature, loop, or progression structure based on the design itself. Use when a team can describe mechanics but cannot clearly articulate who the design is truly for, which player motivations and tolerances it suits, which players it will alienate, or how audience fit should shape design decisions. Focus on behavioral and motivational personas first, and optionally add demographic or market-fit hypotheses when the user explicitly asks for that layer.
Audit a game, feature, live-ops system, progression loop, social feature, or monetization surface using a Self-Determination Theory-inspired motivation framework. Use when evaluating what kind of motivation a design creates, comparing alternative motivational profiles, diagnosing why a system feels sticky, hollow, exhausting, or dead, checking overreliance on rewards and grind, or assessing whether a feature supports short-term activation, medium-term habit, or long-term player identity.
Reframe a player's current situation to reveal new meaning, goals, roles, or playstyles without changing the underlying mechanics. Use when diagnosing stagnation, boredom, or mid/late-game disengagement; when designing re-engagement prompts, adaptive guidance, or dynamic missions; or when a player is technically able to continue but no longer sees the current state as interesting, valuable, or purposeful.
Audit a game feature, live update, roadmap item, event, or content drop by how different player segments are likely to perceive it. Use when a feature is aimed at one cohort but visible to others, when update messaging may create excitement for players who cannot meaningfully access the feature, or when you need to understand how new, mid, and elder players will read the same feature differently.
Infer a player's underlying values and motivational priorities from behavior, then translate those into design implications. Use when designing personalization, segmentation, dynamic guidance, live-ops targeting, adaptive missions, re-engagement strategies, or feature prioritization; when behavior suggests that what players actually care about differs from what the design assumes; or when a team needs a behavior-first player profile rather than a demographic or archetype-only model.
Audit an existing or proposed premium pass (battle pass, season pass) for value proposition integrity, progression health, free track balance, reward pacing, engagement loop quality, and economy impact. Use when evaluating a pass before launch, diagnosing why a pass is underperforming, reviewing a competitor's pass design, or stress-testing a proposed structure before committing to production.
Design or audit prosocial experiences in session-based multiplayer games using a three-phase chapter model built around Setup, Little Loops, and Long Tail. Use when evaluating co-op games, team shooters, MOBAs, mission-based multiplayer, or other repeat-session formats; when planning how to prime trust before play, reinforce repeatable prosocial actions during play, and carry positive social momentum across sessions; or when a multiplayer game feels socially flat, hostile, forgettable, or unable to turn one good match into another.
Audit a game feature, system concept, prototype plan, or preproduction proposal to determine whether the prototype is meant to sell the idea or reveal unknowns, and whether the prototype scope matches that intent. Use when teams are unclear about why they are prototyping, when a prototype risks becoming a demo in disguise, or when precious prototype time may be spent proving known strengths instead of testing real uncertainties.
Track game design prototype ideas, branching outcomes, dead ends, baselines, and next experiments, and optionally generate a simple SVG visualization of prototype evolution. Use when a prototype leads to several possible follow-up paths, when the team needs to backtrack without losing learned branches, when exploring unknowns through multiple iterations, or when you want both a written prototype log and a branch map of how the concept evolved over time.
Reframe a game design problem by isolating the main blocker, imagining it removed, and using that perspective to discover workaround paths. Use when a team is stuck on one obstacle, when discussion keeps collapsing into 'we can't because', or when a feature, system, or plan feels trapped by a single technical, UX, content, or production roadblock.
Audit game design goals, feature objectives, OKRs, initiative aims, or any stated design intent against the SMART criteria adapted for game design. Use when a user shares a design goal, player experience target, retention goal, or feature aim and wants it evaluated or rewritten. Trigger on phrases like "audit my design goals", "is this a good design objective", "my feature goal is...", "we want players to feel...", "our aim for this feature is...", or whenever someone states what a design should achieve and it feels vague or unmeasurable. Also trigger when a design document contains aims or success criteria that need stress-testing. Even soft goals like "players should feel powerful" are valid — apply the framework and return both the audit and a rewritten version.
Evaluate a game's social features and multiplayer elements by their potential to create social satisfaction versus social dissatisfaction. Use when auditing chat, voice, friend systems, gifting, lobbies, social hubs, guilds, reporting tools, cooperative mechanics, profile surfaces, or other social elements; when comparing which features are basic, critical, booster, or secondary; or when deciding where to reduce social risk, increase social stickiness, and prioritize improvements to multiplayer or community-facing systems.
Evaluate a game, feature, system, UX flow, progression loop, live-ops mechanic, monetization surface, or design concept on two axes: systematizing and empathizing. Use when you want to understand whether a design is structurally logic-driven or emotionally player-attuned, what kind of player personas it is likely to attract or repel, and what practical consequences follow from that positioning without assuming one quadrant is universally best.
Audit a game, feature, combat system, economy loop, onboarding flow, puzzle, UI, or design proposal through the lens of fast versus slow thinking inspired by Thinking, Fast and Slow. Use when evaluating whether a design relies on rapid intuitive judgment or deliberate analytical reasoning, whether the intended mode matches the actual demand, where cognitive overload or under-stimulation appears, or how badly the design handles shifts between instinctive and reflective play.
Solve game design problems by adapting, extending, recombining, or retuning what already exists instead of inventing from scratch. Use when building on live systems, reusing content pipelines, stretching feature value, reducing production cost, or finding a lower-risk way to achieve a new purpose with existing mechanics, UX, progression structures, or content.
Detect unknown unknowns in game design and decide what to prototype before committing to production. Use when a feature concept feels promising but underdefined, when the team disagrees about the real design problem, when a mechanic seems interesting but the source of interest is unclear, when a concept risks premature production commitment, or when the team needs to determine what should be prototyped, in what order, and why.
Audit a game, feature, task system, quest flow, event track, puzzle chain, progression layer, or return loop through the lens of the Zeigarnik effect: the tension created by incomplete, interrupted, or unresolved tasks. Use when evaluating whether a design creates healthy return motivation through open loops, whether it leaves players with productive unfinished business, or whether it turns incompletion into anxiety, clutter, guilt, or manipulative pressure.
Help a beginner or early-stage game team estimate the likely budget for a game concept based on scope, target milestone, current team, skill coverage, work model, and geography. Use when someone asks how much a game might cost, what budget range they should expect, whether their current team meaningfully reduces cost, what missing roles would add to budget, or how to estimate cost for a prototype, vertical slice, release, or live F2P project. Ask for missing information when concept, team, scope, or cost assumptions are unclear, then provide a rough budget range, main cost drivers, hidden cost buckets, and ways to reduce spend.
Help a beginner or early-stage indie team turn a game idea into a practical starting plan. Use when someone asks how to start making a game, what to build first, how to approach development order, how to scope a concept for a solo dev, duo, or small team, or how to turn a rough game idea into a sensible first prototype or pitchable vertical slice. Ask a few core questions about the concept, team size, skill mix, platform, scope, release intent, and constraints, then recommend a simple development strategy with build order, risks, what to postpone, and concrete next steps.
Help a beginner or early-stage game team figure out which roles, skills, or disciplines they are missing for a given game concept and target scope. Use when someone asks who they are missing, whether their current team can realistically build the project, what roles they still need, what the riskiest team gaps are, or what the minimum viable team would be if no team is described yet. Ask about the game concept, target platform, intended milestone or scope, team composition, and actual skillset, then identify likely gaps, role overlaps, risky weak spots, and the smallest workable team shape.
Help analyze recurring conflict patterns on software or game projects by identifying likely collaboration archetypes, behavior patterns, project risks, and practical response strategies. Use when someone describes a teammate, lead, founder, stakeholder, client, producer, or collaborator whose recurring behavior is creating friction, slowing decisions, damaging trust, or disrupting execution. Focus on observable behavior and project consequences, not clinical diagnosis, then suggest safer and more effective next moves.
Help a beginner or early-stage game team estimate the likely development time for a game concept based on scope, target milestone, current team, skill coverage, work model, and production constraints. Use when someone asks how long a game might take, whether their current team can hit a target date, what timeline range they should expect for a prototype, vertical slice, release, or live F2P project, or how missing roles and part-time availability change development time. Ask for missing information when concept, team, scope, or staffing assumptions are unclear, then provide a rough timeline range, main schedule drivers, hidden time sinks, and ways to shorten the path.
Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.
Extract a structured list of rules from all markdown files at the top level of a skill directory. Use this skill whenever you need to parse rules out of a skill for conflict checking, merging, or diffing.
Identify conflicting rules between two lists of extracted rules. Use this skill when comparing a skill's rules against another skill's rules or against agent config rules (CLAUDE.md, GEMINI.md, etc.).
Audit and clean Markdown documentation for context rot. Use when docs may contain completed-work logs, executed plans, stale claims, contradictions, dead paths, or drifted authorities, especially in agent-required reading.
Design and validate Hermes Agent profile distributions, including SOUL.md, distribution.yaml, skills, config, MCP stubs, and release readiness.
Turn a simple profile idea into a mature, production-quality Hermes profile prompt and generation brief.
> Pilot a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes. The canvas is a shared workspace visible in the browser; this skill gives you a live cursor on it. Use this skill whenever the user wants to interact with the canvas platform, asks to generate images or videos on canvas, mentions "canvas", "Neo", "Agent Neo", wants to draw/create/generate visual content on the spatial canvas, references past canvas work, or says anything that implies operating on the canvas. Also triggers on /canvas-cowork.
Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.
Самодиагностика и автолечение OpenClaw. Проверка gateway, WAL, памяти, кронов, токенов. Автоматическое исправление типичных проблем.
Telegram CLI for reading/searching messages, syncing archives, and sending or downloading files. Use when the user asks about Telegram chats, messages, contacts, groups, or files.
Claude Skills — questions
Answers built from the skills we actually parsed.