メニュー
Answer a question about a target by fanning out parallel readers over derived angles, then synthesizing a cited answer. Use to understand a subsystem, research a question, or trace how/where something works. Run via the workflow tool by name.
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
Use this skill when the user wants a memory feed — a scheduled automation that fetches targeted data from their integrations (gmail/calendar/slack/web) and keeps ONE memory page current, updated in place. Examples; "track my PR queue", "keep an invoices page", "week-ahead brief".
Implement a spec end-to-end — recon readers map the codebase, an architect pins every cross-file contract in a blueprint, parallel builders implement disjoint workstreams from it, adversarial review, then a final test gate. Use for multi-file feature work. Run via the workflow tool by name.
Find -> adversarially verify -> rank issues over a target (a diff, dir, file, or glob). Use for code review, a scoped bug hunt, a security or perf pass. Run via the workflow tool by name.
Decide between approaches — generate N diverse proposals from different lenses, score each against criteria with independent judges, then synthesize a decisive recommendation. Use for design choices, tradeoff calls, "which approach should we take". Run via the workflow tool by name.
Use this skill when the user wants to turn the current conversation into a scheduled automation. Analyze the session and call create_automation to propose one — the user reviews the full prompt + schedule in the approval card before it's saved.
Create a custom user tool in ~/.ntrp/tools/ using the current tool(...) API.
| name | investigate |
| description | Answer a question about a target by fanning out parallel readers over derived angles, then synthesizing a cited answer. Use to understand a subsystem, research a question, or trace how/where something works. Run via the workflow tool by name. |
| kind | workflow |
| source | builtin |
A workflow preset. Run it with the workflow tool:
workflow(name="investigate", args={"target": "apps/server/ntrp", "question": "How does the event/SSE pipeline work end to end?", "breadth": "normal"})
It derives N distinct investigation angles, sends a reader at each in parallel (each citing sources, not dumping files), then synthesizes one direct, cited answer to your question.
args
target (str, default ".") — the dir/repo/area to examine (can also be a topic for web research).question (str) — what you want answered.breadth ("focused" | "normal" | "wide", default "normal") — number of parallel readers.reader_model / synth_model (str, optional) — model overrides; omit to inherit the run's model.