Research strategy and project design

Skill jjfroehlich/agent-skills-for-academic-research/skills/research-strategy-and-project-design

Agent skills for academia research: writing, dataviz, publishing, communication, career, and more.

Install

npx -y skills add jjfroehlich/agent-skills-for-academic-research --skill research-strategy-and-project-design

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

One thing to look at

1 stars1 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 author says it does

Copied from the file, not written here

Use this skill when a scientist is deciding what research question, project, hypothesis, experiment strategy, or portfolio bet to pursue, pause, pivot, or stop. Trigger on candidate project ideas, stuck research directions, unexpected observations, novelty/feasibility tradeoffs, decisive uncertainty, cheap de-risking tests, kill criteria, and stop/go decisions. Do not trigger for protocol details, statistical implementation, manuscript polishing, grant packaging, figure design, journal choice, or people-management issues unless the main need is project strategy.

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

3.8 KB, as published. Nobody here has run it

Research Strategy And Project Design

Purpose

Help the user turn unclear research possibilities into sharper questions, tractable project designs, explicit tradeoffs, and near-term decisions.

Use this skill when

Use this skill when the user needs to choose among project ideas, decide whether to continue a project, design the next decisive test, generate hypotheses, or rebalance a research portfolio.

Do not use this skill when

Do not use it for protocol details, statistical implementation, manuscript polishing, grant packaging, or personnel management unless those tasks hinge on the underlying project strategy.

Core workflow

Clarify the candidate question, expected knowledge gain, feasibility, current evidence, constraints, and decision horizon.
Separate idea generation from idea selection: explore broadly first, then test rigorously.
Route to the narrowest playbook needed.
Name the decisive uncertainty and the cheapest credible way to reduce it.
Recommend a next action, stop/go review, or comparison table rather than giving only abstract advice.

Output formats

Short strategy memo with recommendation, rationale, decisive uncertainty, and next test.
Project comparison table with feasibility, expected knowledge gain, timeline, stage fit, kill test, and stop/go recommendation.
Hypothesis-generation plan that separates exploratory moves from confirmatory tests.
Risk register with continuation criteria, failure modes, and review date.

Reference routing

Open references/choosing-problems.md when the user is choosing a problem, comparing novelty and tractability, or asking what makes a scientific question worth pursuing.
Open references/project-triage.md when the user has one or more project ideas and needs a pursue, pause, pivot, or quit decision.
Open references/risk-and-kill-criteria.md when the user needs a cheap decisive test, continuation threshold, feared control, or bias-resistant review.
Open references/experiment-types.md when the strategic question depends on what kind of evidence, scale, or experiment type should come next.
Open references/hypothesis-generation.md when the user is stuck, needs new hypotheses, is interpreting unexpected observations, or wants more creative routes into a problem.

Quick checklist

Before answering, check whether the user has supplied enough context about the question, field constraints, available tools/data, time horizon, career or portfolio stage, and what decision the advice must support. If not, ask only for the missing inputs that would change the recommendation.

Common pitfalls

Do not treat exciting, novel, or difficult ideas as automatically worth pursuing.
Do not let sunk costs, identity, or external encouragement replace current evidence.
Do not use exploratory observations as confirmatory evidence without a follow-up test.
Do not expose source provenance, bibliographies, or internal normalization notes in user-facing answers.

Quality bar

Make tradeoffs visible instead of treating every idea as equally good.
State feasibility checks and kill criteria explicitly.
Separate exciting from executable.
End with a next decision or test.