Menü
Execute implementation with and without ARE documentation (experimental)
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
| name | are-implement |
| description | Execute implementation with and without ARE documentation (experimental) |
| disable-model-invocation | true |
Execute the implementation phase with and without ARE documentation to measure impact.
Run the implement command to execute code changes in both environments.Read version: Read .claude/ARE-VERSION → store as $VERSION. Show the user: agents-reverse-engineer v$VERSION
Run the implement command:
npx agents-reverse-engineer@$VERSION implement --backend claude $ARGUMENTS
Note: When --plan-id <id> is provided, the task description is loaded from the stored plan — no need to pass it explicitly.
Wait for completion — the command runs two sequential AI implementation sessions (without docs, then with docs) and outputs a comparison table.
On completion, summarize the comparison results:
--run-tests was used)--run-build / --run-lint was used)--eval was used)This re-uses branches created by /are-plan and executes the implementation in both worktrees:
The comparison measures how much ARE documentation improves implementation quality.
Options:
--eval: Run AI quality evaluator on both implementations--eval-model <name>: Model for the evaluator (default: same as --model)--model <name>: AI model to use for implementation--task-slug <slug>: Reference existing plan by slug (default: auto-generate from task)--plan-id <id>: Reference existing plan by ID (shown by are plan on completion)--run-tests: Execute test suite and include results in metrics--run-build: Execute build and verify success--run-lint: Run linter and include error/warning counts--dry-run: Show what would happen without executing--list: List all saved implementation comparisons--show <id>: View a previous comparison by date--force: Overwrite existing branches for the same task--debug: Show verbose AI execution details
Basierend auf der SOC-Berufsklassifikation
Show available ARE commands and usage guide
Show telemetry dashboard (costs, tokens, traces) (experimental)
Compare AI planning quality with and without ARE documentation (experimental)
Reconstruct project from specification documents (experimental)
Generate project specification from AGENTS.md docs (experimental)
Delete all generated documentation artifacts (.sum, AGENTS.md, plan)
