agentic-gamedev-skills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 72 files.

• adversarially-validating-game-repairs

  Stress-tests an already-written game bug fix with adversarial cases selected from the state, timing, identity, lifecycle, persistence, and input surfaces the patch can actually reach, then returns a PatchEvidence record covering fail-to-pass, relevant pass-to-pass, inverse-case, invariant, and untested-scope evidence. Use when a fix makes the reported symptom go away and it is still unknown wheth…

  .agents/skills/adversarially-validating-game-repairs/SKILL.md on GitHub (opens in a new tab)

• arcadifying-mini-games

  Converts a working mini-game into a complete arcade game by adding round structure, ceremony screens (READY / round clear / death / game over), a score economy (extends, round bonuses, initials entry, high-score table), and jingle/SE separation. Use when a playable game with a verified core loop still "feels like a minigame" and needs arcade completeness — rounds or waves, 1UP extends, name entry…

  .agents/skills/arcadifying-mini-games/SKILL.md on GitHub (opens in a new tab)

• auditing-gameplay-implementation-coverage

  Audits a stateful game's specification, phase/state machine, implementation, presentation, and tests for scenario-specific omissions such as one phase missing an input alias, one actor skipping a rule, a state change lacking HUD feedback, an event lacking audio, or a lifecycle boundary failing to reset or freeze state. Use when a game mostly works but may contain unimplemented sibling cases, inco…

  .agents/skills/auditing-gameplay-implementation-coverage/SKILL.md on GitHub (opens in a new tab)

• building-era-authentic-game-audio

  Designs, implements, and validates a complete game-specific procedural audio system inspired by late-1970s to mid-1980s arcade and console hardware, including BGM loops, adaptive cues, sound effects, jingles, event wiring, synthesis adapters, arbitration, and automated audio-contract tests. Use for tasks that include BGM or require an integrated BGM/SE subsystem across gameplay events. For an eng…

  .agents/skills/building-era-authentic-game-audio/SKILL.md on GitHub (opens in a new tab)

• creating-godot-procedural-audio

  Designs and implements procedural audio for Godot games. Use when creating runtime SFX with Godot built-in audio APIs, mapping game events to timbre, or avoiding external audio assets.

  .agents/skills/creating-godot-procedural-audio/SKILL.md on GitHub (opens in a new tab)

• critiquing-own-response

  Reviews the agent's own immediately preceding response as an advisory pass, surfacing assumptions, reasoning gaps, alternatives, and unverified claims. Use ONLY when the user explicitly asks for self-critique, critical thinking, or challenges to the agent's prior answer. Do not use for normal follow-ups, someone else's work, automatic checking, or independent quality assurance.

  .agents/skills/critiquing-own-response/SKILL.md on GitHub (opens in a new tab)

• curating-game-concept-portfolio

  Curates a supplied set of game ideas into a small mechanically diverse portfolio by normalizing prose into mechanism signatures, clustering structural duplicates, excluding demonstrated hard failures, comparing available evidence without treating missing data as zero, and selecting for coverage rather than one subjective score. Use for pitch triage, game-jam shortlist selection, prototype portfol…

  .agents/skills/curating-game-concept-portfolio/SKILL.md on GitHub (opens in a new tab)

• designing-mini-games

  Designs original, compact mini-games — rules, controls, scoring, hazards, and difficulty curves — for any input scheme, including one-button (tap / hold / release) games. Use when defining a new mini-game concept, converting creative constraints or seeds into mechanics, choosing an input scheme, checking state-variable necessity, or preventing idle, hold-only, or mashing play from becoming optima…

  .agents/skills/designing-mini-games/SKILL.md on GitHub (opens in a new tab)

• designing-minimal-game-rules

  Turns an abstract game-design seed into a minimal discrete-state rule system by generating conflict-axis candidates, stress-testing with Rule Breaker and Strategy Breaker roles, then reducing to the smallest surviving core. Use when designing a compact turn-based or step-based game that must work without numeric tuning, manual level design, or aesthetic polish.

  .agents/skills/designing-minimal-game-rules/SKILL.md on GitHub (opens in a new tab)

• designing-retro-arcade-sound-kits

  Designs and validates event-driven retro-arcade sound kits (SFX + jingles) where game code emits abstract event names and an adapter/synth layer maps and plays them. Use when authoring a per-game arcade sound set, deciding which moments need a one-shot SE vs a jingle vs no sound, keeping SEs from drifting into background music, or preserving a fixed-hardware audio character. Engine-agnostic; for…

  .agents/skills/designing-retro-arcade-sound-kits/SKILL.md on GitHub (opens in a new tab)

• developing-with-crisp-game-lib

  Creates or repairs browser mini-games specifically using crisp-game-lib. Use only when the user explicitly asks for crisp-game-lib or the existing project already uses it; skip for Godot, Unity, Phaser, canvas-only, or unspecified engine requests.

  .agents/skills/developing-with-crisp-game-lib/SKILL.md on GitHub (opens in a new tab)

• directing-game-visuals

  Directs readable, coherent game visuals. Use when defining visual hierarchy, palette roles, screen composition, event feedback, or reducing generic AI-looking game art without relying on HUD text.

  .agents/skills/directing-game-visuals/SKILL.md on GitHub (opens in a new tab)

• dispatching-agent-work

  Routes a user's request to a separate task, subagent, automation, or current agent with an appropriate model role, reasoning effort, and workspace isolation. Use when the user or an authoritative instruction asks to dispatch, delegate, orchestrate, enter dispatch mode, run work in another session, select an execution backend, or schedule work. While dispatch mode is active, proactively send subst…

  .agents/skills/dispatching-agent-work/SKILL.md on GitHub (opens in a new tab)

• evaluating-gameplay-balance

  Evaluates and improves gameplay balance from telemetry in any engine. Use when comparing monotonous vs exploratory play, diagnosing death/spawn/scoring/input issues, setting difficulty, timer, or pacing targets with human-limited simulated players, or proposing structural balance fixes instead of numeric tuning.

  .agents/skills/evaluating-gameplay-balance/SKILL.md on GitHub (opens in a new tab)

• exploring-game-design-space

  Explores a broad game-design space by generating structurally varied concepts, attacking obvious failures, mutating promising mechanisms, and returning a small set of distinct testable hypotheses without ranking speculative fun. Use for open-ended game ideation, mechanic-space exploration, game-jam concept search, or deriving multiple mechanical directions from a seed. Do not use merely to audit…

  .agents/skills/exploring-game-design-space/SKILL.md on GitHub (opens in a new tab)

• extracting-agent-skills

  Distills reusable agent procedures, validation loops, debugging methods, tool-use patterns, and decision rules from completed, paused, abandoned, or failed projects. Use when closing or archiving a project, reducing side-project sprawl, or when asked to harvest project knowledge into reusable agent capabilities. Gates candidates for trigger clarity, validation, and transferability to avoid weak s…

  .agents/skills/extracting-agent-skills/SKILL.md on GitHub (opens in a new tab)

• extracting-spec-design-ladders

  Reverse-engineers existing source code into a two-layer artifact ladder — a concrete reproduction spec (preserves behavior-affecting constants, same-tick ordering, input edges, collision/threshold semantics; drops cosmetics) and an abstract design doc (intentionally omits reproduction detail and records what is unspecified vs. safe-to-assume). Use to document or recover a program's intent and rep…

  .agents/skills/extracting-spec-design-ladders/SKILL.md on GitHub (opens in a new tab)

• gating-by-blind-restoration

  Validates that one abstraction layer (a spec, design doc, schema, contract, or generated artifact) is self-sufficient by spawning an ISOLATED sub-agent that sees only that layer and must reconstruct the adjacent layer, returning pass / weak-pass / fail. Use when checking whether an extracted or generated artifact preserves enough structure to be rebuilt or used without the original source, and to…

  .agents/skills/gating-by-blind-restoration/SKILL.md on GitHub (opens in a new tab)

• gating-expensive-batch-work

  Splits a batch of expensive per-item agent work into a cheap reversible pass over every item and an expensive irreversible pass, separated by a method-freeze checkpoint. Use when running one costly procedure over many items (evaluations, migrations, audits, labeling, benchmark or fixture construction) and the method — rubric, transform rules, criteria, instrument — could still turn out to be wron…

  .agents/skills/gating-expensive-batch-work/SKILL.md on GitHub (opens in a new tab)

• gating-intent-legibility

  Measures whether a player who was never told the rules can read a game's intent off the screen, by sampling scenes from a recorded run and having an isolated agent that has not seen the design or source name the goal, the options, and the risk. Use when a game runs and its mechanics are verified but it is unknown whether the screen communicates what to aim for without a tutorial or HUD text, or a…

  .agents/skills/gating-intent-legibility/SKILL.md on GitHub (opens in a new tab)

• generating-dot-assets

  Generates transparent pixel-art object assets from a subject and target pixel size using a host-provided image-generation tool, chroma-key removal, pixelization, exact canvas fitting, and PNG validation. Use for game objects, sprites, props, item icons, and diorama layers. Requires Codex's built-in `image_gen` (or an equivalent image-generation entry point) and ImageMagick `convert` on PATH.

  .agents/skills/generating-dot-assets/SKILL.md on GitHub (opens in a new tab)

• generating-retro-arcade-concepts

  Batch-generates, evaluates, and specs multiple fixed-screen arcade game concepts in the style of 1978-1985 cabinets (default profile: 1980-1983). Use for a concept slate or for turning era constraints into ranked concepts and implementation specs. For one already-chosen concept, use designing-mini-games instead.

  .agents/skills/generating-retro-arcade-concepts/SKILL.md on GitHub (opens in a new tab)

• generating-semantic-game-mutants

  Injects controlled, game-specific semantic defects — timing/order, identity and lifecycle, scoring and economy, persistence/save, RNG/determinism, input buffering, animation-gameplay sync, content/configuration — into a game or its trace reducer, and records a withheld manifest of intended defect mechanism, precondition, expected symptom, violated invariant, hidden oracle, equivalent-mutant risk,…

  .agents/skills/generating-semantic-game-mutants/SKILL.md on GitHub (opens in a new tab)

• implementing-gameplay-invariants

  Translates game design prose into engine-neutral implementation invariants and validation checks. Use when implementing or reviewing game mechanics where idle, hold-only, mashing, spam, safe waiting, or repeated scoring pulses must be prevented from dominating skilled play.

  .agents/skills/implementing-gameplay-invariants/SKILL.md on GitHub (opens in a new tab)

• localizing-game-state-divergence

  Localizes a reproducible gameplay defect to the first tick at which game state violates an invariant, by replaying a deterministic repro case and scanning a per-event observation trace (or bisecting only when replay is costly and the oracle is monotone), then reporting the first divergent event together with the state before and after it. Use when a game produces a wrong value, a duplicated or mi…

  .agents/skills/localizing-game-state-divergence/SKILL.md on GitHub (opens in a new tab)

• maximizing-game-feel

  Improves the tactile satisfaction ("game feel") of action games whose visuals are functional but flat. Use when a game runs correctly but feels lifeless; applies to players, enemies, obstacles, projectiles, and items.

  .agents/skills/maximizing-game-feel/SKILL.md on GitHub (opens in a new tab)

• migrating-agents-md-to-control-flow

  Audits repositories that rely heavily on AGENTS.md, CLAUDE.md, copilot instructions, or similar agent instruction files, then migrates repeatable workflows into skills, mandatory checks into scripts/hooks/CI, and leaves only stable repo context, policy, and workflow entrypoints in repo instructions. Use when the agent is asked to reduce long natural-language agent instructions, create agent skill…

  .agents/skills/migrating-agents-md-to-control-flow/SKILL.md on GitHub (opens in a new tab)

• probing-web-game-mechanics

  Verifies that implemented game mechanics match their spec by injecting game state into a live headless browser and asserting the resulting transitions (phase changes, scoring formulas, gates, resets). Use when a change actually reaches a mechanic whose spec conformance is unverified — a smoke test (runtime health) passes but the mechanic's own behavior has not been checked, or when a mechanic is…

  .agents/skills/probing-web-game-mechanics/SKILL.md on GitHub (opens in a new tab)

• refining-workflows-from-artifacts

  Refines a reusable agent workflow based on an actual execution result, review, failure, or simulation output. Classifies problem causes (task/execution/workflow/evaluation/capability-boundary/output-format/overconstraint) before proposing the smallest workflow diff. Use when the user wants to improve a workflow, prompt, rubric, or agent skill after applying it to a real task.

  .agents/skills/refining-workflows-from-artifacts/SKILL.md on GitHub (opens in a new tab)

• running-headless-godot

  Runs reproducible headless Godot 4.2+ workflows for CLI commands, exports, scripted scene edits, and tests. Use when running Godot CLI commands, editing .tscn via script, capturing logs, or exporting in headless mode.

  .agents/skills/running-headless-godot/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 181k stars · 19 skills