Agent skills by donchitos

Configure engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data.

Improve a skill via a test-fix-retest loop — static checks, targeted fixes, keep or revert on score change.

Validate skill files for structural compliance and behavioral correctness. Four modes: static linter, spec, category rubric, audit.

Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.

Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.

New or updated sprint plan from the current milestone, completed work, and available capacity.

Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'

First-time onboarding — asks where you are, then guides you to the right workflow.

End-of-story completion review — verifies each acceptance criterion, checks GDD/ADR deviations, prompts code review, updates status.

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

Orchestrate the audio team — audio-director, sound-designer, technical-artist, gameplay-programmer — direction through implementation.

Orchestrate the combat team — game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester — design through implement and validate.

Orchestrate the level team — level-designer, narrative-director, world-builder, art-director, systems-designer, qa-tester — for complete area creation.

Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.

Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.

Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.

Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.

Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

Orchestrate the UI team through the UX pipeline — authoring, visual design, implementation, review, polish. Uses /ux-design, /ux-review, studio templates.

Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.

Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.

Generate engine-specific test helper libraries — assertion utilities, factory functions, mocks in the engine's test folder. Reduces boilerplate.

Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.