← ClaudeAtlas

controlflow-executability-verifierlisted

Use when a saved plan should be tested for cold-start executability before coding, especially for large tasks, weak-confidence plans, or plans whose early phases may be too vague for a fresh executor to follow without hidden context.
Smithbox-ai/ControlFlow · ★ 11 · AI & Automation · score 67
Install: claude install-skill Smithbox-ai/ControlFlow
# ControlFlow Executability Verifier ## Overview Simulate the plan as if a fresh session had only the saved artifact and the repository. This skill identifies whether the first tasks are specific enough to execute without invisible assumptions. Invoke this skill via `/controlflow-claude-code:controlflow-executability-verifier`. ## Workflow 1. Read the saved plan artifact first. 2. Simulate only the first few phases or tasks that matter for cold-start execution. 3. For each task, apply the 8-point checklist from [references/executability-checklist.md](references/executability-checklist.md): - what_clear - where_clear - how_clear - inputs_defined - outputs_defined - dependencies_met - verify_command_complete - test_specifics_concrete 4. Walk through the task using the TDD walk-through from the checklist: - open_file - read_existing_code - write_test_red - run_test - write_implementation_green - run_test_again - refactor 5. Stop at the first real blocker for a task and record exactly why it blocks execution. 6. Save the verdict to `plans/artifacts/<task-slug>/executability-verifier.md` using [../../templates/executability-verifier-report-template.md](../../templates/executability-verifier-report-template.md). 7. Return a structured verdict: - `PASS` - `FAIL` - `WARN` - `ABSTAIN` ## Output Shape - **Status** - **Tasks Simulated** - **Per-Task Checklist** - **Walkthrough Summary** - **Blocked Steps** - **Recomme