Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
quick-design
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.
Donchitos/Claude-Code-Game-Studios 8,725
-
story-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Donchitos/Claude-Code-Game-Studios 8,725
-
skill-test
Validate skill files for structural compliance and behavioral correctness. Three modes: static (linter), spec (behavioral), audit (coverage report).
Donchitos/Claude-Code-Game-Studios 8,725
-
team-release
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
Donchitos/Claude-Code-Game-Studios 8,725
-
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when starting a major feature.
Donchitos/Claude-Code-Game-Studios 8,725
-
team-ui
Orchestrate the UI team through the full UX pipeline: from UX spec authoring through visual design, implementation, review, and polish. Integrates with /ux-design, /ux-review, and studio UX templates.
Donchitos/Claude-Code-Game-Studios 8,725
-
onboard
Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant to the specified role or area.
Donchitos/Claude-Code-Game-Studios 8,725
-
regression-suite
Map test coverage to GDD critical paths, identify fixed bugs without regression tests, flag coverage drift from new features, and maintain tests/regression-suite.md. Run after implementing a bug fix or before a release gate.
Donchitos/Claude-Code-Game-Studios 8,725
-
skill-improve
Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests, and keeps or reverts based on score change.
Donchitos/Claude-Code-Game-Studios 8,725
-
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
Donchitos/Claude-Code-Game-Studios 8,725
-
dev-story
Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.
Donchitos/Claude-Code-Game-Studios 8,725
-
team-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Donchitos/Claude-Code-Game-Studios 8,725
-
sprint-plan
Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design backlogs.
Donchitos/Claude-Code-Game-Studios 8,725
-
team-narrative
Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.
Donchitos/Claude-Code-Game-Studios 8,725
-
architecture-decision
Creates an Architecture Decision Record (ADR) documenting a significant technical decision, its context, alternatives considered, and consequences. Every major technical choice should have an ADR.
Donchitos/Claude-Code-Game-Studios 8,725
-
understand-dashboard
Launch the interactive web dashboard to visualize a codebase's knowledge graph
Lum1104/Understand-Anything 8,185
-
understand-chat
Use when you need to ask questions about a codebase or understand code using a knowledge graph
Lum1104/Understand-Anything 8,185
-
understand
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships
Lum1104/Understand-Anything 8,185
-
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase
Lum1104/Understand-Anything 8,185
-
understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
Lum1104/Understand-Anything 8,185
-
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks
Lum1104/Understand-Anything 8,185
-
understand-onboard
Use when you need to generate an onboarding guide for new team members joining a project
Lum1104/Understand-Anything 8,185
-
understand-domain
Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.
Lum1104/Understand-Anything 8,185
-
proof
Use proof to capture test runs as shareable, replayable evidence artifacts. Invoke this skill whenever the user wants to preserve or share proof that tests passed — not just run tests, but document and share the results. Works from any language: standalone binary, TypeScript, Python, or Go SDKs. Key use cases: attaching terminal output to a PR so reviewers can replay the test session instead of trusting a screenshot; generating a markdown proof report to embed in PR descriptions or tickets; recording a browser test run as a self-contained HTML video to share with a PM or QA team; recording an iOS Simulator or Android emulator screen while XCUITest or Espresso tests run, with automatic tap indicator overlays; exporting terminal recordings as MP4 video for embedding inline in Linear or Jira comments; or creating an audit trail that ties passing tests to a specific git commit. Trigger on phrases like "attach evidence to PR", "save test output as artifact", "replayable test recording", "proof report", "record my test run", "share test results", "visual proof tests pass", "terminal recording of tests", "record iOS simulator", "record Android emulator", "capture mobile tests", "export as video", "embed in Linear", "embed in Jira", or whenever someone wants reviewers or stakeholders to see test execution without re-running it themselves. Also trigger when the user mentions proof, @automaze/proof, or automaze-proof directly.
automazeio/proof 38