Research Workflow

What it does

When your agent uses it

• Comprehensive topic research
• Deep investigation
• Creating research reports

Example prompts

• “/research-workflow”

Requirements

• Compatibility (from SKILL.md): Designed for Claude Code and similar products. Web search capability required.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Planning
2. 2Execution
3. 3Analysis
4. 4Synthesis

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code and similar products. Web search capability required.

  From compatibility in the SKILL.md frontmatter.

Context cost

Research Workflow loads about 2.4k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 714 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 714 words, ~2,442 tokens.

name

research-workflow

description

Guide agents through structured research including planning, multi-query execution, source analysis, and synthesis. Use for comprehensive topic research, deep investigation, or creating research reports. Keywords: research, investigate, deep dive, comprehensive, analysis, synthesis, report.

compatibility

Designed for Claude Code and similar products. Web search capability required.

license

MIT

metadata.author

agent-skills

metadata.version

1.0

metadata.type

orchestrator

metadata.mode

assistive

metadata.domain

research

┌─────────────────────────────────────────────────────────────┐
│                    RESEARCH WORKFLOW                        │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  1. PLANNING          2. EXECUTION                          │
│  ┌──────────────┐    ┌──────────────┐                       │
│  │ Define       │    │ Run searches │                       │
│  │ questions    │───>│ Evaluate     │                       │
│  │ Plan queries │    │ sources      │                       │
│  └──────────────┘    └──────────────┘                       │
│         │                   │                               │
│         v                   v                               │
│  3. ANALYSIS          4. SYNTHESIS                          │
│  ┌──────────────┐    ┌──────────────┐                       │
│  │ Organize     │    │ Create       │                       │
│  │ findings     │───>│ coherent     │                       │
│  │ Find patterns│    │ output       │                       │
│  └──────────────┘    └──────────────┘                       │
│                                                             │
└─────────────────────────────────────────────────────────────┘

# Broad overview
web-search "AI in healthcare overview 2024"

# Specific deep dive
web-search "AI diagnostic imaging applications" --depth advanced

# Current news
web-search "AI healthcare regulations 2024" --topic news --time month

Research Question: What are the best practices for API versioning?

Sub-questions:
1. What versioning strategies exist?
2. What are pros/cons of each?
3. What do major companies use?
4. What do experts recommend?

Search Plan:
- "API versioning strategies comparison"
- "REST API versioning best practices 2024"
- "API versioning header vs URL vs query parameter"
- "large companies API versioning approach"

Query 1: "API versioning strategies comparison"
- Found: URL versioning, header versioning, query parameter
- Key insight: URL versioning most common, header more "RESTful"
- Sources: REST API tutorial, Martin Fowler blog

Query 2: "REST API versioning best practices 2024"
- Found: Semantic versioning principles apply
- Key insight: Version only when breaking changes
- Sources: API design guides, Stack Overflow discussions

Consensus Points:
- Version only for breaking changes
- Be consistent within an API
- Document version lifecycle

Conflicts:
- URL vs header placement (no clear winner)
- When to deprecate old versions

Gaps:
- Limited data on performance impact
- Few studies on developer experience

Key Findings:
1. Three main strategies exist (URL, header, query param)
2. URL versioning is most common and discoverable
3. Header versioning is considered more "pure" REST
4. Version only on breaking changes
5. Major companies split between approaches

Recommendations:
- Use URL versioning for public APIs (discoverability)
- Consider header versioning for internal APIs
- Document deprecation timeline clearly
- Use semantic versioning principles

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references, assets) in skills/general/research/methodology/research-workflow of jwynia/agent-skills.

• SKILL.md
• assets/research-plan-template.md
• assets/research-report-template.md
• assets/source-evaluation-checklist.md
• references/methodology.md
• references/output-formats.md

Open the folder on GitHubat commit e02ec7e