Research Methodology
Professional research process for a subagent. Three tracks based on the type of research:
- Journalistic — investigative pieces, primary source research, source-heavy narrative work
- Industry analysis — market research and strategy, signal detection
- Academic/Comprehensive — deep systematic research when depth matters most
All three share the same lifecycle (Scope → Gather → Evaluate → Analyze → Synthesize → Report) but differ in evidence standards, speed, and output format.
The Research Lifecycle
SCOPE → GATHER → EVALUATE → ANALYZE → SYNTHESIZE → REPORT
Durable Artifact Gate
Research is not complete when an agent has produced a plausible answer. It is complete when the reusable evidence and reasoning have been preserved in the durable format that is natural to the host system and its users.
Before reporting, make the preservation decision explicit:
- Identify the durable destination. Use the host's normal long-lived research surface: linked knowledge records, a tracked report package, a research database, a project document, or another user-visible artifact. Do not leave the only useful output in chat, a transient workspace, or an untracked scratch file.
- Extract at the source's natural granularity. Capture every distinct, reusable claim, data point, method, contradiction, and open question that materially changes future reasoning. Do not use a fixed atom, finding, or note count as a stopping rule. Continue until each retained source is accounted for in the extraction log.
- Preserve provenance and relationships. Each durable artifact must retain its source URL or citation, access date, evidence strength, and links to the question, related artifacts, and any synthesis that depends on it.
- Separate extraction from synthesis. A brief or report explains the conclusion; it does not replace the underlying evidence records. Preserve source-level records and reusable claims before compacting them into a synthesis.
- Record what was not preserved. If a source was rejected, too weak, inaccessible, redundant, or out of scope, record that decision in the research log. A future researcher must be able to distinguish an intentional exclusion from an overlooked source.
The right artifact shape depends on the environment. Do not assume a particular database, note-taking application, or orchestration system. The invariant is durable, navigable, evidence-linked research that a later user or agent can discover and build on.
Reference Files
Tracks
| Track |
Reference |
When to load |
| Journalistic |
references/journalistic-research.md |
You're researching an investigative piece — primary sources, interviews, documents, series management, pre-publication verification |
| Industry analysis |
references/industry-analysis.md |
You're researching an industry analysis piece — signal detection, corporate evidence, competitive intelligence, case study standards |
| Academic / Comprehensive |
references/research-lifecycle.md |
You're doing deep systematic research — question scoping, search strategy, inclusion/exclusion criteria |
Shared Methodology
| Reference |
When to load |
references/source-evaluation.md |
You need to judge whether a source is credible — CRAAP test, triangulation, reliability tiers |
references/structured-analytic-techniques.md |
You need to evaluate competing explanations — ACH, driving forces, pre-mortem, indicators |
references/synthesis-patterns.md |
You need to combine findings from multiple sources into synthesized conclusions |
references/technical-verification.md |
You need to test a technical claim by reproducing it — benchmarks, API behavior, configuration |
Assets
| Asset |
What it produces |
assets/research-brief.md |
Structured brief with findings, confidence assessment, evidence table, open questions |
assets/research-log.md |
Traceable record of searches, sources, and decisions |
Use both assets for every substantial investigation. Before closing the work, complete their durable-artifact sections and verify that retained sources and extracted claims are represented in the destination system.
Pre-Publication Gateway
For any piece that makes factual claims, load the relevant track's verification protocol before reporting back:
- Journalistic: 7-step pre-publication protocol from
references/journalistic-research.md
- Industry: 7-step research protocol from
references/industry-analysis.md
- Technical: 5-step reproduction protocol from
references/technical-verification.md
Portability
This skill is intentionally host-neutral. Use your agent's normal mechanisms to load the references, templates, and scripts listed here. Do not assume a particular profile system, task orchestrator, memory service, or response-handoff format.
1---2name: research-methodology3description: Plan, conduct, evaluate, and synthesize rigorous research. Use for journalistic, industry, or technical investigations that need credible evidence and a traceable method.4license: MIT5---6
7
8# Research Methodology
9
10Professional research process for a subagent. Three tracks based on the type of research:
11
12- **Journalistic** — investigative pieces, primary source research, source-heavy narrative work
13- **Industry analysis** — market research and strategy, signal detection
14- **Academic/Comprehensive** — deep systematic research when depth matters most
15
16All three share the same lifecycle (Scope → Gather → Evaluate → Analyze → Synthesize → Report) but differ in evidence standards, speed, and output format.
17
18## The Research Lifecycle
19
20```
21SCOPE → GATHER → EVALUATE → ANALYZE → SYNTHESIZE → REPORT
22```
23
24## Durable Artifact Gate
25
26Research is not complete when an agent has produced a plausible answer. It is complete when the reusable evidence and reasoning have been preserved in the durable format that is natural to the host system and its users.
27
28Before reporting, make the preservation decision explicit:
29
301. **Identify the durable destination.** Use the host's normal long-lived research surface: linked knowledge records, a tracked report package, a research database, a project document, or another user-visible artifact. Do not leave the only useful output in chat, a transient workspace, or an untracked scratch file.
312. **Extract at the source's natural granularity.** Capture every distinct, reusable claim, data point, method, contradiction, and open question that materially changes future reasoning. Do not use a fixed atom, finding, or note count as a stopping rule. Continue until each retained source is accounted for in the extraction log.
323. **Preserve provenance and relationships.** Each durable artifact must retain its source URL or citation, access date, evidence strength, and links to the question, related artifacts, and any synthesis that depends on it.
334. **Separate extraction from synthesis.** A brief or report explains the conclusion; it does not replace the underlying evidence records. Preserve source-level records and reusable claims before compacting them into a synthesis.
345. **Record what was not preserved.** If a source was rejected, too weak, inaccessible, redundant, or out of scope, record that decision in the research log. A future researcher must be able to distinguish an intentional exclusion from an overlooked source.
35
36The right artifact shape depends on the environment. Do not assume a particular database, note-taking application, or orchestration system. The invariant is durable, navigable, evidence-linked research that a later user or agent can discover and build on.
37
38## Reference Files
39
40### Tracks
41
42| Track | Reference | When to load |
43|-------|-----------|-------------|
44| **Journalistic** | `references/journalistic-research.md` | You're researching an investigative piece — primary sources, interviews, documents, series management, pre-publication verification |
45| **Industry analysis** | `references/industry-analysis.md` | You're researching an industry analysis piece — signal detection, corporate evidence, competitive intelligence, case study standards |
46| **Academic / Comprehensive** | `references/research-lifecycle.md` | You're doing deep systematic research — question scoping, search strategy, inclusion/exclusion criteria |
47
48### Shared Methodology
49
50| Reference | When to load |
51|-----------|-------------|
52| `references/source-evaluation.md` | You need to judge whether a source is credible — CRAAP test, triangulation, reliability tiers |
53| `references/structured-analytic-techniques.md` | You need to evaluate competing explanations — ACH, driving forces, pre-mortem, indicators |
54| `references/synthesis-patterns.md` | You need to combine findings from multiple sources into synthesized conclusions |
55| `references/technical-verification.md` | You need to test a technical claim by reproducing it — benchmarks, API behavior, configuration |
56
57### Assets
58
59| Asset | What it produces |
60|-------|-----------------|
61| `assets/research-brief.md` | Structured brief with findings, confidence assessment, evidence table, open questions |
62| `assets/research-log.md` | Traceable record of searches, sources, and decisions |
63
64Use both assets for every substantial investigation. Before closing the work, complete their durable-artifact sections and verify that retained sources and extracted claims are represented in the destination system.
65
66## Pre-Publication Gateway
67
68For any piece that makes factual claims, load the relevant track's verification protocol before reporting back:
69
70- **Journalistic:** 7-step pre-publication protocol from `references/journalistic-research.md`
71- **Industry:** 7-step research protocol from `references/industry-analysis.md`
72- **Technical:** 5-step reproduction protocol from `references/technical-verification.md`
73
74## Portability
75
76This skill is intentionally host-neutral. Use your agent's normal mechanisms to load the references, templates, and scripts listed here. Do not assume a particular profile system, task orchestrator, memory service, or response-handoff format.
theheavenlyd3mon