/research-methodology
Methodology for market research and data collection, ensuring data quality and source traceability
$ npx -y skills add chekusu/wanman --skill research-methodology --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/research-methodology
Context preview
The summary Claude sees to decide when to auto-load this skill.
Methodology for market research and data collection, ensuring data quality and source traceability
SKILL.md
research-methodology.SKILL.mdname: research-methodology
description: Methodology for market research and data collection, ensuring data quality and source traceability
Research Methodology
Core Principles
**Every data point must have a source and confidence score.** Estimates are not facts — label them as estimates.
Data Source Hierarchy
| Tier | Source Type | Confidence Range | Examples | |------|-----------|-----------------|---------| | 1 | Official public data | 0.85-0.95 | Government statistics, public company filings, industry association reports | | 2 | Authoritative media | 0.70-0.85 | Major financial media, industry analysis reports | | 3 | Web search results | 0.50-0.70 | Blogs, forums, review sites | | 4 | Model inference/estimates | 0.20-0.50 | Extrapolations from known data, analogical estimates | | 5 | Training data memory | 0.10-0.30 | Data from model memory (may be outdated) |
Search Strategy
1. **Search before estimating**: Do not guess from training data if the information can be searched 2. **Cross-validate**: Confirm key data from at least 2 independent sources 3. **Label timeliness**: Note the time range of data (e.g., "2024 data") 4. **Distinguish facts from opinions**: Clearly label when quoting
Data Recording Format
Use `wanman artifact put` to record each research data point:
# Good recording practice
wanman artifact put --kind market_data --path "competitors/cafe_a/pricing" \
--meta '{"source":"web_search:dianping.com","confidence":0.65,"data_date":"2024-12","avg_price":35,"currency":"CNY","category":"specialty_coffee"}'
# Bad practice (missing source and confidence)
wanman artifact put --kind market_data --path "competitors/pricing" \
--meta '{"avg_price":35}'Common Pitfalls
- **Survivorship bias**: Successful cases found via search do not represent the full industry picture
- **Outdated data**: Rent and foot traffic data from 2 years ago may have changed significantly
- **Regional differences**: Tier-1 city data cannot be directly applied to tier-2 or tier-3 cities
- **Currency/unit confusion**: Always label currency and measurement units
Read more
name: research-methodology description: Methodology for market research and data collection, ensuring data quality and source traceability
Research Methodology
Core Principles
**Every data point must have a source and confidence score.** Estimates are not facts — label them as estimates.
Data Source Hierarchy
| Tier | Source Type | Confidence Range | Examples | |------|-----------|-----------------|---------| | 1 | Official public data | 0.85-0.95 | Government statistics, public company filings, industry association reports | | 2 | Authoritative media | 0.70-0.85 | Major financial media, industry analysis reports | | 3 | Web search results | 0.50-0.70 | Blogs, forums, review sites | | 4 | Model inference/estimates | 0.20-0.50 | Extrapolations from known data, analogical estimates | | 5 | Training data memory | 0.10-0.30 | Data from model memory (may be outdated) |
Search Strategy
1. **Search before estimating**: Do not guess from training data if the information can be searched 2. **Cross-validate**: Confirm key data from at least 2 independent sources 3. **Label timeliness**: Note the time range of data (e.g., "2024 data") 4. **Distinguish facts from opinions**: Clearly label when quoting
Data Recording Format
Use `wanman artifact put` to record each research data point:
# Good recording practice
wanman artifact put --kind market_data --path "competitors/cafe_a/pricing" \
--meta '{"source":"web_search:dianping.com","confidence":0.65,"data_date":"2024-12","avg_price":35,"currency":"CNY","category":"specialty_coffee"}'
# Bad practice (missing source and confidence)
wanman artifact put --kind market_data --path "competitors/pricing" \
--meta '{"avg_price":35}'Common Pitfalls
- **Survivorship bias**: Successful cases found via search do not represent the full industry picture
- **Outdated data**: Rent and foot traffic data from 2 years ago may have changed significantly
- **Regional differences**: Tier-1 city data cannot be directly applied to tier-2 or tier-3 cities
- **Currency/unit confusion**: Always label currency and measurement units
Agent Matrix framework — run a supervised network of Claude Code or Codex agents that collaborate on your machine. wanman is an open-source local-mode agent matrix framework.
Repo: chekusu/wanman
Other skills on wanman.
- /artifact-naming
Naming conventions for artifact kind and path, ensuring data can be aggregated and analyzed
Open skill - /artifact-quality
Quality standards for structured deliverables, ensuring data is verifiable and traceable
Open skill - /cross-validation
CEO checks consistency of agent outputs during post-completion review
Open skill - /wanman-cli
wanman CLI command reference — inter-agent communication, task management, artifact storage
Open skill - /workspace-conventions
File and output conventions for agent workspaces
Open skill

