Mechangelion

Asset Hunter Pro — unused asset detection, dependency graph, duplicate finder, project cleanup automation for Unity

Practical tools and validation methods for game balance — DPS calculators, EHP formulas, spreadsheet layouts, stat audits, difficulty spike detection

GDD structure, templates, and living documentation patterns for game projects — wiki pages, design docs, section layout, sync triggers

Game feel and juice — screen shake, hit stop, particles, animation curves, input responsiveness, feedback timing. Makes actions feel satisfying.

Mobile game design patterns — session design, retention mechanics, notification strategy, portrait/landscape, battery/thermal constraints, FTUE

Create or update TheOneKit agent .md files with canonical structure. Use when adding a new agent, updating maxTurns/model, or fixing frontmatter fields.

Answer technical questions with context-aware skill activation. Use for 'how does X work', 'what is the best way to', 'explain this pattern' queries.

Monitor a PR to green+merged. Use for: 'babysit pr', 'watch pr', 'monitor pr', 'flaky ci', 'auto merge'. Retries flaky CI, resolves simple conflicts, auto-merges when approved+green.

Generate ideas and explore solutions with context-aware skill activation. Use for 'how should I approach X', 'what are the options for Y', 'help me think through this'.

Context engineering for T1K workflows — optimize token usage, manage agent context, design skill injection, troubleshoot context degradation.

Implement features end-to-end: plan, code, test, review via registry agents. Use for 'implement X', 'build Y feature', 'add Z functionality'. Handles full workflow.

Investigate and diagnose errors via registry-routed debugger agent. Root cause first, no fixes until cause confirmed. Use for runtime errors, crashes, wrong output, test failures, performance issues, CI/CD failures, log analysis.

Create and update project documentation in docs/. Use for 'init docs', 'update docs after this change', 'generate a codebase summary', 'docs are out of date'.

Validate TheOneKit registry integrity across 20+ checks. Use for 'check kit health', 'something feels broken', 'validate before release', or after adding skills/agents.

Discover available skills by keyword search across all activation fragments and installed modules. Use when asking 'what skill handles X', 'how do I do Y', 'find skill for Z', or 'list all skills'.

ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.

Git operations with conventional commits. Stage, commit, push, PR, merge. Security scans for secrets. Auto-splits commits by scope.

Save and resume session context for handoffs between sessions or developers. Use for 'save session', 'hand off to', 'resume context', 'where did I leave off', 'context transfer'.

Display TheOneKit usage guide with live registry state. Use for 'what commands exist', 'which agents are registered', 'how do I use TheOneKit'.

Report skill/agent bugs to the owning kit repo on GitHub. Use when a skill has wrong patterns, missing gotchas, or needs an enhancement. Deduplicates before creating.

Maintain TheOneKit repos as a kit maintainer. Use for releasing kits, scaffolding new kits, cross-kit validation, schema migration, and E2E test runs.

Manage optional skill modules for modular kits. Use for 'install module X', 'remove module Y', 'list available modules', 'apply a preset', 'update modules', or auditing module health.

Create phased implementation plans with research and task breakdown. Use for 'plan this feature', 'how should we architect X', 'break this into phases before coding'.

5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.

View files/directories OR generate visual explanations, slides, diagrams (Markdown or self-contained HTML). Use for 'explain X visually', 'diagram the flow', 'make slides', 'show diff', or 'generate HTML report'.

Systematic problem-solving when stuck: complexity spirals, innovation blocks, recurring patterns, assumption constraints, scale uncertainty. Auto-activates after 3+ debug/fix failures.

Code review via registry-routed reviewer agent. Adversarial rigor with evidence-based claims. Supports input modes: pending changes, PR number, commit hash, codebase scan. Always-on red-team analysis finds security holes, false assumptions, and failure modes.

Generate exhaustive edge cases across 12 dimensions before implementation or testing. Use for 'edge cases for X', 'test scenarios', 'what could go wrong', 'boundary testing'.

Explore codebase with context-aware skill injection. Use for 'find where X is implemented', 'how is Y used', 'show all places that call Z' across source, skills, and docs.

Security audit using STRIDE threat model and OWASP Top 10 checklist. Use for 'security audit', 'security review', 'threat model', 'find vulnerabilities', 'OWASP check'.

One-command release pipeline: merge main, test, review, commit, push, PR. Single command from feature branch to PR URL. Use for 'ship', 'release branch', 'ready to merge', 'create PR with tests'.

Create or update TheOneKit skills with eval-driven iteration. Use for new skills, skill scripts, references, benchmark optimization, description optimization, eval testing, extending kit capabilities.

Push .claude/ skill/agent/rule edits back to their origin kit repos as PRs. Use after fixing a skill locally, updating a gotcha, or improving agent definitions.

Orchestrate Agent Teams with registry-routed teammates, module-aware context, and manifest-derived file ownership. Use for parallel research, implementation, review, and debug workflows.

Run tests via registry-routed tester agent. Compilation checks, coverage reports, failure analysis. Use for 'run tests', 'check coverage', 'why is this test failing'.

Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.

Triage GitHub issues and PRs across all kit repos. Fetches, classifies, and auto-implements actionable items. Use for 'review open issues', 'what needs fixing', 'process PR backlog'.

Summarize session progress: git history, task status, skill sync gaps, test coverage. Use at end of session, before standup, or 'what did we do today'.

Manage git worktrees: create, session, sync (rebase), envsync, diff, status, remove, merge. Parallel development in monorepos and standalone repos.

Addressable asset system — async loading, memory management, groups/labels, remote content delivery, migration from Resources.Load. Use when implementing asset management.