aoirint

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.

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.

Review or create a BepInEx Mono mod for C# project and module structure, plugin identity, game compatibility, dependency boundaries, GitHub CI and release automation, packaging, release metadata, and verification. Use when implementing, reviewing, preparing a release for, or diagnosing quality gaps in a BepInEx 5 Mono plugin or its build and release workflow.

Maintain a canonical developer changelog and versioned release history. Use when adding or correcting Keep a Changelog entries, prerelease history, compatibility context, or release-source material; not for user-facing release notes or publishing.

Review or draft repository commit messages for Conventional Commits format, accurate change summaries, breaking-change footers, and required attribution trailers. Use before creating, amending, or validating a commit.

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

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.

Create or update repository `.gitignore` rules, including pinned upstream template syncs. Use when changing ignored-file behavior or merging `github/gitignore` content.

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.

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

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.

Review or draft repository commit messages for Conventional Commits format, accurate change summaries, breaking-change footers, and required attribution trailers. Use before creating, amending, or validating a commit.

Maintain a canonical developer changelog and versioned release history. Use when adding or correcting Keep a Changelog entries, prerelease history, compatibility context, or release-source material; not for user-facing release notes or publishing.

Create or review channel-specific release notes from a canonical changelog. Use when checking destination history or publication readiness.

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.

Review or revise explanatory prose for readability, local structure, audience fit, and preserved nuance. Use for wording in documentation, comments, release notes, issues, pull requests, changelogs, handoff notes, and Agent Skills after the document's purpose and factual ownership are known. Use software-documentation-maintenance instead for repository-wide document maps, canonical ownership, technical evidence, coverage, or migration.

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.

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

Review or draft repository commit messages for Conventional Commits format, accurate change summaries, breaking-change footers, and required attribution trailers. Use before creating, amending, or validating a commit.

Maintain a canonical developer changelog and versioned release history. Use when adding or correcting Keep a Changelog entries, prerelease history, compatibility context, or release-source material; not for user-facing release notes or publishing.

Review implementation changes for readability, maintainability, design intent, and verification. Use for source code, tests, scripts, configuration, generated or vendored files, and dependencies; pair with security-check for security- or supply-chain-sensitive changes.

Create or update repository `.gitignore` rules, including pinned upstream template syncs. Use when changing ignored-file behavior or merging `github/gitignore` content.

Review or revise explanatory prose for readability, local structure, audience fit, and preserved nuance. Use for wording in documentation, comments, release notes, issues, pull requests, changelogs, handoff notes, and Agent Skills after the document's purpose and factual ownership are known. Use software-documentation-maintenance instead for repository-wide document maps, canonical ownership, technical evidence, coverage, or migration.

Create or review channel-specific release notes from a canonical changelog. Use when checking destination history or publication readiness.

Review repository changes for practical security and supply-chain risks. Use when work touches secrets, permissions, untrusted input, dependencies, executable or downloaded artifacts, CI or deployment configuration, containers, or vendored/generated files; skip documentation-only changes with no security-sensitive surface.

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, semantic UI tests, Flet packaging, platform artifacts, security, and developer documentation. Use for new Flet projects, large UI refactors, Flet architecture alignment, target packaging, release readiness, or reviews of Flet application code. Pair with python-quality-check for uv, Ruff, mypy, pytest, coverage, Python packaging, and CI quality gates.

Create, align, or review strict uv-managed installable Python projects hosted on GitHub across packaging, dependency locking, Ruff, mypy, pytest, statement and branch coverage, distribution artifacts, and CI parity. Use for Python applications, libraries, or CLIs with pyproject.toml, .python-version, uv.lock, src/tests layouts, dependency changes, quality-gate adoption, packaging, or GitHub Actions validation; pair with a framework-specific Skill when one applies.

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.

Quality-check GitHub Actions workflows, repository issues, pull requests, and their comments. Use when creating, editing, reviewing, or documenting CI automation, issue text, PR text, reviews, replies, or squash merges.

Design, restructure, and maintain a software repository's documentation system, including its required docs/domain, docs/architecture, and docs/operations map, canonical ownership, technical evidence, indexes, links, and change synchronization. Use when creating or migrating developer docs, documenting system behavior or design decisions, establishing documentation rules, or reviewing repository-wide documentation completeness. Pair with prose-quality-check for wording and with a domain skill for specialized technical correctness.