agentsclimarketplace

Research methodology

Skill magnus919/agent-skills/research-methodology

Plan, conduct, evaluate, and synthesize rigorous research. Use for journalistic, industry, or technical investigations that need credible evidence and a traceable method.From its SKILL.md

Install
npx -y skills add magnus919/agent-skills --skill research-methodology

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 21 stars21 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.4 KB, 996 tokens by cl100k_base, as published. Nobody here has run it

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:

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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

TrackReferenceWhen to load
Journalisticreferences/journalistic-research.mdYou're researching an investigative piece — primary sources, interviews, documents, series management, pre-publication verification
Industry analysisreferences/industry-analysis.mdYou're researching an industry analysis piece — signal detection, corporate evidence, competitive intelligence, case study standards
Academic / Comprehensivereferences/research-lifecycle.mdYou're doing deep systematic research — question scoping, search strategy, inclusion/exclusion criteria

Shared Methodology

ReferenceWhen to load
references/source-evaluation.mdYou need to judge whether a source is credible — CRAAP test, triangulation, reliability tiers
references/structured-analytic-techniques.mdYou need to evaluate competing explanations — ACH, driving forces, pre-mortem, indicators
references/synthesis-patterns.mdYou need to combine findings from multiple sources into synthesized conclusions
references/technical-verification.mdYou need to test a technical claim by reproducing it — benchmarks, API behavior, configuration

Assets

AssetWhat it produces
assets/research-brief.mdStructured brief with findings, confidence assessment, evidence table, open questions
assets/research-log.mdTraceable 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.

What ships with it: 11 files

41.6 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,970. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.