메뉴
Use when you have a written implementation plan to execute inline in the current session with review checkpoints. Prefer subagent-driven-development when sub-agent dispatch is available.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
The Arbor research-coordinator protocol: the OBSERVE -> IDEATE -> SELECT -> DISPATCH -> DECIDE cycle over a durable Idea Tree. Preloaded automatically on /auto-research sessions. The coordinator never edits code or runs commands — executors do that in isolated worktrees; the coordinator steers the tree with idea_tree / dispatch_experiments / merge_experiment.
The Arbor executor workflow: clone the repo from the git bundle your brief hands you, implement and evaluate exactly ONE hypothesis with the file tools, then report structured results via worker_complete. Preloaded automatically on arbor-executor task workers. Never touch the held-out test split.
DECIDE-phase doctrine for an Arbor research run: when to merge, prune, combine, or finalize; how the held-out merge gate works; and the rule that the final report uses TEST scores. Load before deciding what to do with completed experiments.
Hard-gated ideation for an Arbor research run. Load at the START of every IDEATE round, before drafting any hypothesis. Enforces the PI mindset (mechanism over knob), the four-question first-principles probe, the kill-filter, and the four-line hypothesis format. Ported from Arbor's idea_drafting + first_principles_probe.
Intake for an autonomous research run (Arbor). Use when the user wants to optimize a metric in a repo over many isolated experiments — 'optimize this benchmark', 'improve the model F1 overnight', 'beat the leaderboard'. Discovers the repo/eval/splits, measures the baseline, confirms a Research Contract, then emits a ready-to-send /auto-research command. Does NOT start the run itself.
Pitfalls, examples, and edge cases for workers executing a Surogates subagent task. Loaded automatically when the dispatcher spawns a session bound to a Task (Session.task_id is set).
| name | executing-plans |
| description | Use when you have a written implementation plan to execute inline in the current session with review checkpoints. Prefer subagent-driven-development when sub-agent dispatch is available. |
| version | 1.0.0 |
| author | Surogate Agent (adapted from obra/superpowers) |
| license | MIT |
| tags | ["process","implementation","execution"] |
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Note: This skill drives task-by-task execution inline in the current session. If your platform supports sub-agent dispatch (delegate_task, spawn_worker), the subagent-driven-development skill produces higher-quality results with two-stage review and isolated contexts. Use this skill when sub-agent dispatch is not available or your human partner explicitly chose inline execution.
read_file.todo per task and proceed.For each task:
todo as in_progress.todo as completed only when the step's verification passes.After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers — stop and ask.
skill_view).Related skills:
writing-plans — Creates the plan this skill executes.subagent-driven-development — Higher-quality alternative when sub-agent dispatch is available.systematic-debugging — Use when a verification fails and the cause isn't obvious.