ia-agents-skills

Coordinate high-risk or clearly parallelizable multi-agent work through a created goal, native subagent roles, risk-based independent verification, and a persistent complete .agent-hive/PLAN-PROGRESS-{context-id}.md file. Use when the user explicitly asks to orchestrate agents/subagents, or when a task has multiple independent workstreams that can run concurrently, high-risk phases that benefit from independent verification, or a long migration/research/review effort where orchestration reduces net time or risk. When this skill is selected and its throughput gate passes, treat that as the user's standing authorization to use subagents; the user does not need to restate subagent/delegation intent. Avoid for small, localized, or single-threaded tasks where coordination overhead would exceed benefits.

Analyze C# and .NET performance using workload context, profiling or benchmark evidence, and targeted static inspection. Use for slow or allocation-heavy code, hot paths, async or thread-pool issues, regex, collections, serialization, I/O bottlenecks, or a requested .NET performance audit. Do not use for speculative optimization of cold code or database-only problems.

Run a conversational Plan Mode for code implementation work before editing code. Use when the user asks for "/plan", plan mode, Code Planner, an implementation plan, planning before coding, or a pre-edit technical approach. The skill requires non-mutating environment exploration, mandatory questions for unresolved material ambiguity, intent clarification, implementation clarification, risks, assumptions, verification checkpoints, and a final decision-complete Markdown plan. Also use before substantial or risky codebase changes where execution should wait for a complete plan.

Perform an evidence-based, read-only maintainability audit of a branch, pull request, commit, diff, or selected files. Use only when the user explicitly invokes $thermo-nuclear-code-quality-review or asks for a thermonuclear, especially strict, or deep code-quality review. Do not use for routine reviews, implementation, or style-only feedback.

Generate or edit raster images through the OpenAI Images API using the gpt-image-2 model. Use when Codex should create image files with explicit API/model control, save outputs to local paths, generate website or product assets, create concept art, produce mockups, or edit existing bitmap images with gpt-image-2 rather than the built-in image_gen tool. Requires OPENAI_API_KEY for live generation.

Interview mode for stress-testing a plan against the existing domain model, terminology, CONTEXT-{context-id}.md, and ADRs. Ask one question at a time and do not implement code unless explicitly approved after the grilling session.