deep-research

スター11

フォーク3

更新日2026年3月18日 12:40

Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.

インストール

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。

ソース

Threat-Vector-Security

Threat-Vector-Security/guardian-agent

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Deep Research

Use this skill when the task needs investigation before implementation.

Workflow:

Define the exact question being answered.
Inspect the smallest relevant file and symbol set first.
Compare competing code paths, old vs new behavior, or proposal vs implementation.
Produce a concise synthesis: what is true, what is inferred, what is still unknown.

Guardrails:

Do not start editing until the research question is answered.
Keep notes compact and decision-oriented.
If the investigation branches, summarize each branch separately before merging conclusions.

Gotchas

Do not drift from investigation into implementation just because a likely fix becomes obvious.
Do not mix confirmed observations and inferred conclusions into one bullet list.
Do not read the whole repo when a narrow symbol/file comparison can answer the question.

Template

Use templates/research-brief.md when the findings need to be handed off or saved as a durable brief.

このリポジトリの他の Skills

同じリポジトリ

skill-creator

Threat-Vector-Security/guardian-agent

Guide for creating new skills, improving existing skills, and evaluating skill quality. Use this whenever the user wants to turn a workflow into a skill, revise a skill, improve triggering behavior, or add evals and benchmarks for a skill.

2026-04-1911

code-review

Threat-Vector-Security/guardian-agent

Use when reviewing a diff, PR, or patch for bugs, regressions, missing tests, architecture risk, security risk, or reviewability concerns before merge.

2026-04-1311

context-engineering

Threat-Vector-Security/guardian-agent

Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs, relevant files, examples, and current errors.

2026-04-1311

source-driven-development

Threat-Vector-Security/guardian-agent

Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples rather than memory.

2026-04-1311

coding-backend-orchestration

Threat-Vector-Security/guardian-agent

Use when the user explicitly asks Guardian to launch or check an external coding assistant such as Codex, Claude Code, Gemini CLI, or Aider.

2026-04-1111

coding-workspace

Threat-Vector-Security/guardian-agent

Use when the request is about a repo, codebase, implementation, bugfix, or backend-owned coding session that should stay anchored to the active workspace.

2026-04-1111

name	deep-research
description	Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.

Deep Research

Use this skill when the task needs investigation before implementation.

Workflow:

Define the exact question being answered.
Inspect the smallest relevant file and symbol set first.
Compare competing code paths, old vs new behavior, or proposal vs implementation.
Produce a concise synthesis: what is true, what is inferred, what is still unknown.

Guardrails:

Do not start editing until the research question is answered.
Keep notes compact and decision-oriented.
If the investigation branches, summarize each branch separately before merging conclusions.

Gotchas

Do not drift from investigation into implementation just because a likely fix becomes obvious.
Do not mix confirmed observations and inferred conclusions into one bullet list.
Do not read the whole repo when a narrow symbol/file comparison can answer the question.

Template

Use templates/research-brief.md when the findings need to be handed off or saved as a durable brief.