research-design
Use when debating hypotheses, turning claims into predictions, planning experiments, or checking causal and empirical designs.
Skill by AbubakarAmin
Chalk Labs
Need help deploying research-design?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/abubakaramin-research-design
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/research-design
What's inside
- Skill name
research-design- Description
- Use when debating hypotheses, turning claims into predictions, planning experiments, or checking causal and empirical designs.
- License
- MIT
- Metadata
- scholargraph-roles: HypothesisDebateSystem, PlannerAgent · scholargraph-stage: hypothesis-and-planning
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Falsifiable Research Design ## Procedure 1. Turn each claim into an observable prediction with outcome, comparator, population/data, and decision window. 2. Define support, falsification, and inconclusive outcomes before seeing results. 3. Name the strongest rival explanation and the baseline/control that tests it. 4. Match measures, sample/seed plan, uncertainty, test, and multiplicity correction to the prediction; never choose tests for significance. 5. For causal claims, state estimand, identification assumptions, confounding risks, and robustness checks. Otherwise use associational scope. 6. Check dataset, compute, sandbox, and contract feasibility; expose blockers. ## Output Check Every contribution has a falsifiable prediction, failure condition, relevant controls, and feasible measurement plan.
From AbubakarAmin/scholargraph-harness, MIT.
More from AbubakarAmin/scholargraph-harness
- 0.582score
peer-review
AbubakarAmin
Use when screening or reviewing research, checking manuscript claims, or proposing a bounded repair after review feedback.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
evidence-synthesis
AbubakarAmin
Use when discovering research gaps, screening literature, extracting evidence, or building evidence-grounded thesis claims.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
statistical-interpretation
AbubakarAmin
Use when summarizing experiment results, interpreting uncertainty, reviewing quantitative claims, or connecting statistical reports to manuscript text.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
operator-handoff
AbubakarAmin
Use when answering an operator about a live research run, assessing system performance, or recommending the next run action.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
writer-number-policy
AbubakarAmin
Use when drafting or repairing manuscript text with quantitative results, citations, or causal claims.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
experimental-reproducibility
AbubakarAmin
Use when generating, refining, or reviewing experiment code and when tying execution artifacts to a research plan.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
sandbox-fix-hints
AbubakarAmin
Use when repairing experiment code failures involving timeouts, imports, sandbox restrictions, or output JSON.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
debate-rubric
AbubakarAmin
Use during adversarial hypothesis debate, objection resolution, and moderation of research claims.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AbubakarAmin
- 0.582score
peer-review
AbubakarAmin
Use when screening or reviewing research, checking manuscript claims, or proposing a bounded repair after review feedback.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
evidence-synthesis
AbubakarAmin
Use when discovering research gaps, screening literature, extracting evidence, or building evidence-grounded thesis claims.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
statistical-interpretation
AbubakarAmin
Use when summarizing experiment results, interpreting uncertainty, reviewing quantitative claims, or connecting statistical reports to manuscript text.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
operator-handoff
AbubakarAmin
Use when answering an operator about a live research run, assessing system performance, or recommending the next run action.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
writer-number-policy
AbubakarAmin
Use when drafting or repairing manuscript text with quantitative results, citations, or causal claims.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
experimental-reproducibility
AbubakarAmin
Use when generating, refining, or reviewing experiment code and when tying execution artifacts to a research plan.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get research-design running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
research-design skill. Agent Mart. https://agentmart.dev/skills/abubakaramin-research-design (last updated 2026-10-24)