staruhub/ClaudeSkills / skills/Geek-skills-deep-research
deep-research
VerifiedUse this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, summarizing one document the user already provided, plan-only requests where the user explicitly defers the actual research, or when the user wants a short answer with no need for cited evidence (a short but evidence-backed conclusion is still a brief memo, which this skill covers). Chinese trigger examples: "帮我调研", "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.0 KB |
| assets/report_template.md | markdown | 1006 B |
| evals/routing-evals.json | config | 3.8 KB |
| evals/runbook.md | markdown | 967 B |
| references/evaluator-prompt.md | markdown | 4.0 KB |
| references/handoff-format.md | markdown | 3.9 KB |
| references/landscape-scan.md | markdown | 1.2 KB |
| references/methodology.md | markdown | 5.7 KB |
| references/observability.md | markdown | 3.0 KB |
| references/quality-gates.md | markdown | 5.5 KB |
| references/report-assembly.md | markdown | 3.4 KB |
| references/research-notes-format.md | markdown | 2.2 KB |
| references/subagent-prompt.md | markdown | 1.7 KB |
| references/tension-discovery.md | markdown | 1.2 KB |
| scripts/emit_run_summary.py | script | 5.0 KB |
| scripts/source_evaluator.py | script | 11.9 KB |
| scripts/verify_citations.py | script | 10.7 KB |
references/research-notes-format.md
View on GitHub# Research Notes Format V8
Research notes are the bridge between investigation and synthesis.
They must be compact enough to merge, but strong enough to defend the final claims.
## Workspace structure
```text
workspace/
research-plan.md
research-notes/
task-a.md
task-b.md
task-c.md
task-f1.md
registry.md
outline.md
draft.md
evaluation.md
run-summary.json
handoff-1.md
handoff-2.md
```
## Required note structure
Each `task-*.md` should follow this structure.
```markdown
---
task_id: a
role: Policy Analyst
objective: Compare policy approaches to X
status: complete
confidence: medium
sources_found: 5
acceptance_met: yes
---
## Sources
[1] Title | URL | Aut:8 Rec:9 Rel:9 Dep:8 = 8.5 | META_ANALYSIS | 2025-11
[2] Title | URL | Aut:9 Rec:8 Rel:8 Dep:9 = 8.5 | OFFICIAL / PRIMARY | 2024-06
...
## Findings (facts only)
- Specific fact with source number. [1]
- Specific fact with source number. [2]
## Analysis (your synthesis)
- What these findings mean for the thread objective. [1][2]
- What appears overstated / understated / uncertain. [2][3]
## Support snippets / paraphrases for top claims
- Claim: {important claim}
Source: [2]
Support: {1-2 sentence paraphrase or short excerpt-level summary of what the source says}
- Claim: {important claim}
Source: [1]
Support: {support}
## Conflicts / unresolved issues
- Source [1] and [3] disagree on ...
- Still unresolved because ...
## Leads discovered
- Entity / document / standard / vendor / paper / law worth follow-up
## Gaps
- What you searched for but could not establish confidently
- What evidence would most reduce uncertainty
```
## Rules
### In Findings
- keep them factual
- one claim per bullet when possible
- include source numbers
- avoid vague filler like “many experts believe”
### In Analysis
- separate your synthesis from the source facts
- it is fine to infer, but make it obvious that it is your inference
### In Support snippets / paraphrases
- keep them short
- include only the few claims most likely to matter later
- use paraphrase when copyright or quoting constraints are a concern
### In Gaps
- be honest
- gaps are not failure; hidden gaps are failure
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |