メニュー
Use when starting any session — maps contexts to behavioral skills that should be active
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Document a bug report with reproduction steps, severity, and expected behavior. Use when the user explicitly requests the Virtual Team bug workflow or when this workflow is the next stage of an active Virtual Team pipeline.
Quiz the developer on technical decisions in the current work. Use when the user explicitly requests the Virtual Team check workflow or when this workflow is the next stage of an active Virtual Team pipeline.
Create clean, atomic git commits following project conventions. Use when the user explicitly requests the Virtual Team commit workflow or when this workflow is the next stage of an active Virtual Team pipeline.
Extract, define, and validate API contracts as concrete schema files. Use when the user explicitly requests the Virtual Team contracts workflow or when this workflow is the next stage of an active Virtual Team pipeline.
Investigate a bug, reproduce it, trace the code, and document the root cause. Use when the user explicitly requests the Virtual Team debug workflow or when this workflow is the next stage of an active Virtual Team pipeline.
Query project conventions and architectural decisions with source references. Use when the user explicitly requests the Virtual Team decisions workflow or when this workflow is the next stage of an active Virtual Team pipeline.
| name | skill-awareness |
| description | Use when starting any session — maps contexts to behavioral skills that should be active |
Behavioral skills must be active when relevant, even in ad-hoc sessions without slash commands. This mapping tells you which skills to load based on what you're doing.
| Context | Skill to load | Trigger |
|---|---|---|
| Starting a pipeline | virtual-team:triage | Before /flow executes any step, or when /feature//implement need to determine ceremony level |
| Writing production code | virtual-team:test-driven-development | Before any Edit/Write to non-test files (reads stack.md tdd: field for mode: strict, recommended, off) |
| Writing production code | virtual-team:design-principles | Before writing function signatures, constructors, or service boundaries (reads stack.md design: field for mode: strict, recommended, off) |
| Claiming completion | virtual-team:verification-before-completion | Before saying "done", "complete", "passes" |
| Receiving review feedback | virtual-team:receiving-code-review | When processing review comments |
Executing multi-task plan with --sdd | virtual-team:subagent-driven-development | When /virtual-team:implement --sdd is active |
| User requests compressed output | virtual-team:token-efficient | User says "caveman mode", "terse", "compress", or similar activation phrase |
| Generating client-facing prose in /idea or /proposal | virtual-team:positive-framing | When /idea Round 5 or /proposal Phase 6 reaches the editorial step |
Project-provided domain and stack skills are NOT auto-triggered. They are discovered and loaded by /virtual-team:implement Layer 1 based on domain and stack frontmatter fields matching the current work.
SessionStart hook in hooks/hooks.jsonPreToolUse hook on Edit|Write calls (TDD + verification check)/virtual-team:implement (Layer 0, 1, 2)