Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.
100
100%
Does it follow best practices?
Impact
100%
1.13xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
The canonical home for this skill is deep-research in daymade/claude-code-skills
Create high-fidelity research reports with strict format control, evidence mapping, and multi-pass synthesis.
Copy this checklist and track progress:
Deep Research Progress:
- [ ] Step 1: Intake and format contract
- [ ] Step 2: Research plan and query set
- [ ] Step 3: Evidence collection (deepresearch tool)
- [ ] Step 4: Source triage and evidence table
- [ ] Step 5: Outline and section map
- [ ] Step 6: Multi-pass full drafting (parallel subagents)
- [ ] Step 7: UNION merge and format compliance
- [ ] Step 8: Evidence and citation verification
- [ ] Step 9: Present draft for human review and iterateEstablish the report requirements before any research:
Create a concise report spec file:
Report Spec:
- Audience:
- Purpose:
- Scope:
- Time Range:
- Geography:
- Required Sections:
- Section Formatting Rules:
- Citation Style:
- Output Format:
- Length Targets:
- Tone:
- Must-Include Sources:
- Must-Exclude Topics:If a user provides a template or an example report, treat it as a hard constraint and mirror the structure.
Define the research strategy before calling tools:
Use references/research_plan_checklist.md for guidance.
Use the deepresearch tool to collect evidence and citations.
File structure (recommended):
<output_dir>/research/<topic-name>/
deepresearch_pass1.md
deepresearch_pass2.md
deepresearch_pass3.mdIf deepresearch is unavailable, rely on user-provided sources only and state limitations explicitly.
Normalize and score sources before drafting:
Evidence table minimum columns:
Create an outline that enforces the format contract:
Avoid single-pass drafting; generate multiple complete reports, then merge.
Use the Task tool to spawn parallel subagents with isolated context. Each subagent must:
Implementation pattern:
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.mdWrite drafts to files, not conversation context:
<output_dir>/intermediate/<topic-name>/version1.md
<output_dir>/intermediate/<topic-name>/version2.md
<output_dir>/intermediate/<topic-name>/version3.mdMerge using UNION, never remove content without evidence-based justification:
Verify traceability:
Use references/completeness_review_checklist.md.
Present the draft as a reviewable version:
| File | When to Load |
|---|---|
| research_report_template.md | Build outline and draft structure |
| formatting_rules.md | Enforce section formatting and citation rules |
| source_quality_rubric.md | Score and triage sources |
| research_plan_checklist.md | Build research plan and query set |
| completeness_review_checklist.md | Review for coverage, citations, and compliance |
4f0eae8
Canonical home
since Jan 28, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.