メニュー
Execute an implementation plan by dispatching fresh subagents per task with two-stage review (spec compliance, then code quality). Use for ad-hoc plan execution outside the full triforce ceremony.
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
Post-implementation business assessment by Prometeo (PM). Verifies success metrics achievement, scope compliance, acceptance criteria business interpretation, risk materialization, and product decision closure. Outputs structured report with verdict and confidence score.
Analyzes checklist effectiveness by tracking hit rates, identifying stale items, and finding coverage gaps. Generates evolution suggestions following Boorman's principles. Use periodically to keep checklists field-tested and relevant.
Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Use periodically or before releases to maintain code hygiene.
Creates a complete product feature specification. Use when defining new features, writing user stories, or planning product work. Generates structured specs in docs/specs/.
Generates test cases for a module or function following FIRST principles and Arrange-Act-Assert pattern. Detects test framework from project config. Use to bootstrap test coverage for existing code or as the Red phase of TDD.
Create and manage git worktrees for isolated feature work. Use when starting implementation that should not touch the main workspace, or for parallel development. Handles creation, baseline verification, and cleanup.
| name | subagent-orchestration |
| description | Execute an implementation plan by dispatching fresh subagents per task with two-stage review (spec compliance, then code quality). Use for ad-hoc plan execution outside the full triforce ceremony. |
Execute the plan at: $ARGUMENTS
.claude/agents/forja-prompts/implementer-prompt.md
c. Handle implementer status (DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED)
d. Dispatch spec-reviewer subagent using .claude/agents/forja-prompts/spec-reviewer-prompt.md
e. If spec review fails: implementer fixes, re-review (loop until PASS)
f. Dispatch code-quality-reviewer subagent using .claude/agents/forja-prompts/code-quality-reviewer-prompt.md
g. If quality review fails: implementer fixes Critical/Important issues, re-review
h. Mark task complete| Task Signals | Model | Examples |
|---|---|---|
| 1-2 files, complete spec, mechanical | haiku | Add a field, write a test, rename |
| Multi-file, integration, judgment needed | sonnet | Wire up endpoint, refactor module |
| Architecture, design, broad codebase | opus | Design subsystem, complex debug |