skills

Review or create a BepInEx Mono mod for C# project and module structure, plugin identity, game compatibility, dependency boundaries, repository-family alignment, GitHub CI and release automation, package readiness, release metadata, and verification. Use when implementing, reviewing, preparing a release for, diagnosing quality gaps in, or applying a minimal-difference peer rollout to a BepInEx 5 Mono plugin or its build and release workflow.

Set up and use an isolated Git worktree for repository implementation tasks. Use unless the user explicitly requests another workspace arrangement.

Quality-check repository pull requests and PR-thread communication. Use when creating, updating, reviewing, or validating PR titles, bodies, review comments, replies, thread notes, or GitHub squash-merge attribution and commit-message payloads.

Review Agent Skills for trigger clarity, focused scope, metadata alignment, progressive disclosure, and validation readiness. Use when creating, updating, reviewing, or splitting a skill's SKILL.md, references, scripts, assets, or agents/openai.yaml metadata.

Investigate version-specific Lethal Company mechanics using verified Unity-build evidence, seeded RNG, exhaustive or sampled computation, and runtime observation; produce reproducible, bounded gameplay reports. Use for mechanics questions, full-seed enumeration, sealed-result reuse, Terminal or HUD endpoint interpretation, version comparisons, statistical prediction, or playable-strategy evaluation. Use unity-game-analyze for the underlying decompiled-code and serialized-asset trace.

Roll out a validated canonical change from a designated primary repository to compatible peers with only necessary local differences. Use for shared Agent Skills, repository rules, workflows, or documentation conventions.

Select a reviewed APM CLI version, then set up, pin, deploy, audit, and update APM-managed agent dependencies safely. Use when creating or editing apm.yml or apm.lock.yaml, choosing or installing APM, adding an Agent Skill, plugin, or MCP dependency, validating a pinned deployment, or preparing a cooldown-aware update proposal.

Create, align, or review production-quality Python Flet applications across package and module architecture, presentation state, Flet controls, async lifecycle, persistence and I/O boundaries, uv dependency management, Ruff, strict mypy, pytest, 100% branch and statement coverage, GitHub Actions, Flet packaging, security, and developer documentation. Use for new Flet projects, large UI refactors, quality-baseline adoption, CI setup, release readiness, or reviews of pyproject.toml, uv.lock, src/tests layout, and Flet application code. Pair with software-documentation-maintenance for document ownership and with security-check for dependencies, secrets, and CI supply chain decisions.

Quality-check GitHub Actions workflows and composite actions. Use when creating, editing, reviewing, or documenting workflow triggers, permissions, runners, concurrency, action pins, secrets, or CI linting policy.

Quality-check repository GitHub issues and issue comments. Use when creating, updating, reviewing, or validating issue titles, bodies, replies, or thread notes.

Trace version-specific Unity game behavior through decompiled managed code, scenes, prefabs, prefab variants, ScriptableObjects, bundles, serialized references, and runtime mutation paths. Use when locating an implementation, reconciling code defaults with asset overrides, proving callback or object reachability, comparing Unity builds, or preparing code-and-asset evidence for a game-specific analysis or mod integration. Pair with a domain analysis skill for gameplay interpretation and with a mod quality skill for hook and implementation decisions.