Menu
Template for thorough open-ended research reports. Loaded by the Researcher agent — not user-invocable.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Capture what was done in the current conversation as a repeatable, well-structured skill (SKILL.md). Interviews the user to clarify intent, scope, and edge cases before writing.
Generate a high-level architecture design document from a requirements document. Covers technology choices, compute platforms, databases, data models, data flows, and security posture — no code snippets or code structure.
Generate a low-level design specification from requirements and high-level design documents. Covers class diagrams, package structure, class interactions, and testing strategy — the bridge between architecture and implementation.
Implement a specific task from the implementation plan using strict TDD. Writes failing tests first, then minimal code to pass, with human approval before committing. Tracks status in plan/{prefix}-plan.md.
Generate an implementation task plan from design documents. Breaks a low-level design into ordered, dependency-aware tasks with explicit parallelization analysis. Use when you have a completed low-level design and need to plan the implementation work.
Diagnose and fix test coverage gaps. Identifies uncovered code paths, adds targeted tests, refactors untestable code, and introduces mocking where needed. Never lowers thresholds.
| name | generic-deep-research |
| description | Template for thorough open-ended research reports. Loaded by the Researcher agent — not user-invocable. |
| user-invocable | false |
Use this template when the user wants to understand a topic thoroughly. This is the catch-all for any research request that doesn't fit a more specific template. It covers: deep dives, surveys, explanations, investigations, and exploratory research.
Your report MUST follow this exact structure. Every section is required. Do not skip or reorder sections.
# <Research Topic>
## Executive Summary
Brief overview of the key findings in 3-5 sentences. A busy reader should be able to read only this section and understand the main takeaways.
## Background & Context
Why this topic matters. What prompted the research. Any relevant history or context that frames the findings.
## Findings
### <Subtopic 1>
Detailed findings on the first major aspect of the topic.
### <Subtopic 2>
Detailed findings on the next aspect.
### <Subtopic N>
(Continue with as many subtopics as needed. Organize by theme, chronology, or logical grouping — choose whichever structure best serves comprehension.)
## Analysis
Cross-cutting observations, patterns, and implications that span multiple findings. This is where you synthesize — connect the dots between findings, identify trends, and draw out what the findings mean in context.
## Open Questions & Gaps
- What couldn't be determined from available sources.
- Areas where confidence is low and why.
- Suggested follow-up research that would fill gaps.
## Sources
1. [Source Name](URL) — Brief description of what this source contributed.
2. [Source Name](URL) — Brief description.
(Number all sources. Include URLs where available.)
Before delivering the report, verify:
research-agent-deep/deep-research/type/deep-researchsource_agent: researcherWhen publishing to the Grimoire, do not include YAML frontmatter in the file. The CLI manages frontmatter via create-file-metadata. Include descriptive topic tags alongside the type tag.