New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hri Experiments

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly…

MITAuto-check passedData & Analytics

Install Hri Experiments

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hri-experiments -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills hri-experiments --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/HRI-Skills/skills/hri-experiments .claude/skills/hri-experiments && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hri-experiments
GitHub stars
1.2k
Token cost
~1.9k tokens
SKILL.md length
884 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly…

  • Auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs
  • SKILL.md covers Match the evidence to the claim, Choose the design deliberately, Wizard-of-Oz, done honestly and Power, sample size, and analysis, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Running Wizard-of-Oz honestly

What it does

Hri Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly, powering the sample, reporting statistics with effect sizes and qualitative rigor, selecting validated scales, adding manipulation checks, pre-registering, and meeting HRI's human-participants ethics obligations.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Statistics. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • Auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs
  • Running Wizard-of-Oz honestly
  • Powering the sample
  • Reporting statistics with effect sizes and qualitative rigor

Example prompts

  • “/hri-experiments”

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hri Experiments loads about 1.9k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 884 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 884 words, ~1,894 tokens.

Download SKILL.mdSave it as .claude/skills/hri-experiments/SKILL.md (or your agent's skills folder).
name
hri-experiments
description
Use when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly, powering the sample, reporting statistics with effect sizes and qualitative rigor, selecting validated scales, adding manipulation checks, pre-registering, and meeting HRI's human-participants ethics obligations.

HRI Experiments

The human-subjects study is HRI's currency. A brilliant robot behavior with a broken study fails; a modest behavior with an airtight study can win a Best Paper. HRI reviewers — drawn from psychology and HCI as well as robotics — hold study design to a standard closer to experimental psychology than to a robotics benchmark. This skill covers the design decisions that decide the paper, and HRI's specific ethics obligations. It pairs with the shared reporting kit in ../../resources/code/README.md.

Match the evidence to the claim

Decide what kind of claim you are making, then design to it:

Claim shapeEvidence HRI expects
"Robot behavior X changes outcome Y" (causal)A controlled experiment manipulating X, measuring Y, with a manipulation check and effect sizes
"People experience the robot as Z" (perception)A validated instrument for Z, adequate power, and honest CIs
"This interaction/design works better"A comparison with a fair baseline and a behavioral or task outcome, ideally shown on video
"Here is how people make sense of robots" (qualitative)A rigorous qualitative method (thematic/grounded), reflexivity, transferable insight — not counts
"This method/measure is valid" (methods)Psychometric or methodological evidence, not a single-use demo

A mismatch — e.g., claiming behavior change but measuring only a liking scale — is the most common reason an HRI study is judged inadequate.

Choose the design deliberately

  • Between-subjects — each participant sees one condition. Cleaner (no carryover, no demand from seeing the manipulation) but needs more participants for the same power. Default when exposure to the robot changes people.
  • Within-subjects — each participant sees all conditions. More powerful per participant, but risks order effects (counterbalance) and demand characteristics (participants guess the hypothesis).
  • Mixed — a between factor (e.g., robot type) crossed with a within factor (e.g., task phase).
  • Justify the choice in the paper; reviewers will ask why. State counterbalancing and how you controlled order/demand for within-subjects designs.

Wizard-of-Oz, done honestly

Wizard-of-Oz (WoZ) — a human covertly controlling some robot behavior — is a legitimate and common HRI method, but it is a credibility minefield if mishandled:

  • Disclose it. State clearly what was autonomous and what the wizard controlled. Presenting teleoperated behavior as autonomous is a serious integrity problem reviewers actively probe.
  • Constrain and log the wizard. Define the wizard's action space, script or protocol, and report wizard error rates and training; an unconstrained wizard makes the stimulus irreproducible and the condition ill-defined.
  • Watch consistency. Wizard behavior must be consistent across participants and conditions, or the "manipulation" is really wizard variance.
  • Cite and follow the community's WoZ reporting guidance (a well-known systematic review lives in the JHRI journal — see the exemplars-library guard; it is a journal work, cite it as such).

Power, sample size, and analysis

  • Power the study. Estimate sample size from an expected effect size (from pilots or prior HRI work) before collecting data; an underpowered null is uninformative. Report the basis for N.
  • Report effect sizes and confidence intervals, always — Cohen's d, η², odds ratios, or the appropriate measure — not just p-values. HRI reviewers increasingly treat "significant, no effect size" as incomplete.
  • Correct for multiple comparisons when you run many tests; a scale battery with no correction invites the "garden of forking paths" critique.
  • Pre-register the primary hypothesis and analysis where you can, and clearly separate confirmatory from exploratory results. Label post-hoc findings as post-hoc.
  • Check assumptions and use methods appropriate to your data (ordinal Likert data, repeated measures, nested/mixed models for multi-trial designs).
Show full SKILL.md (320 more words)Show less

Validated scales and constructs

Prefer established, validated instruments over homemade items so results are comparable and the construct is defensible:

  • Robot-perception constructs commonly use published scales for anthropomorphism/animacy/likeability, warmth and competence, trust, negative attitudes toward robots, and similar. Cite the scale to its source and report reliability (e.g., Cronbach's α) for your sample.
  • If you must build a measure, justify it, pilot it, and report its properties — reviewers distrust an ad hoc single item for a rich construct.
  • Include a manipulation check so you can show the intended difference was actually perceived.

Qualitative and mixed methods

HRI values qualitative rigor, not just experiments:

  • Name the method (thematic analysis, grounded theory, interaction analysis) and follow it; report coding process, and inter-rater reliability where the method calls for it (not all do).
  • Practice reflexivity — who coded, their stance, how themes were derived — instead of implying a false objectivity or a fake "n."
  • In mixed-methods work, say how the strands integrate (triangulation, explanation, expansion), not just that both exist.

Ethics is not optional at HRI

Submitting binds you to ACM's Policy on Research Involving Human Participants and Subjects:

  • Obtain and state IRB/ethics approval (or a documented exemption rationale); report informed consent.
  • If the study uses deception (common with WoZ or staged robot failures), justify it and describe debriefing.
  • Protect participants and data: de-identify, secure recordings, and mind vulnerable populations (children, older adults, clinical) with extra care.
  • Anonymize ethics details for review (institution names can leak identity — see hri-submission), but do not omit that approval exists.

Anti-patterns HRI reviewers flag

  • Undisclosed or unconstrained Wizard-of-Oz.
  • Underpowered study with a null spun as evidence of no effect.
  • Scale battery + no correction + no pre-registration (fishing).
  • Liking/rating as a stand-in for the behavioral or theory-linked outcome the claim needs.
  • Missing manipulation check — no evidence the manipulation worked.
  • No effect sizes; p < .05 treated as the whole result.
  • Qualitative work reported as frequencies with no method named.

Output format

text
[Claim ↔ evidence] claim shape and whether the design measures it
[Design] between/within/mixed · justified · counterbalanced?
[WoZ] used? autonomy vs wizard disclosed · wizard constrained + error reported?
[Power/stats] N basis · effect sizes + CIs · multiple-comparison correction · pre-registered?
[Measures] validated scales cited + reliability · manipulation check present?
[Qualitative] method named · reflexivity · integration (if mixed)?
[Ethics] IRB/consent stated · deception justified + debriefed?
[Fix queue] <ordered, design fixes before data collection where possible>

© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in HRI-Skills/skills/hri-experiments of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Hri Experiments next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hri Experiments compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hri Experiments this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.9kAutomated safety check: PassMIT
Sandbox Benchvercel/next.js143k—~4.1kAutomated safety check: PassMIT
Statistical Analysisspacering-net/codeg3.9k3 repos~5kAutomated safety check: PassMIT
StatsmodelszLanqing/codex-claude-academic-skills4.7k15 repos~4.9kAutomated safety check: PassBSD-3-Clause
AI Daily DigestvigorX777/ai-daily-digest1.6k—~1.3kAutomated safety check: PassNone
Statistical Powerspacering-net/codeg3.9k1 repos~3.6kAutomated safety check: NotesMIT

Similar skills

  • Sandbox Bench

    vercel/next.js

    Official

    Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app…

    143k GitHub stars~4.1k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Statistical Analysis

    spacering-net/codeg

    Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting.

    3.9k GitHub starsUsed in 3 repos~5k tokens
    Data & AnalyticsAuto-check passed

  • Statsmodels

    zLanqing/codex-claude-academic-skills

    Statistical models library for Python. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 15 repos~4.9k tokens
    Data & AnalyticsAuto-check passed

  • AI Daily Digest

    vigorX777/ai-daily-digest

    Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category…

    1.6k GitHub stars~1.3k tokensUpdated 7 mo ago
    Data & AnalyticsAuto-check passed

  • Statistical Power

    spacering-net/codeg

    Sample-size and statistical power calculations for planning studies.

    3.9k GitHub starsUsed in 1 repo~3.6k tokens
    Data & AnalyticsAuto-check: notes

  • Agent Session Monitor

    higress-group/higress

    Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage.

    9.5k GitHub stars~3.3k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed

  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed

  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 12 days ago
    Auto-check passed

Categories

Questions about Hri Experiments

What does Hri Experiments do?

A skill your agent uses when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly…. Hri Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs, running Wizard-of-Oz honestly, powering the sample, reporting statistics with effect sizes and qualitative rigor, selecting validated scales, adding manipulation checks, pre-registering, and meeting HRI's human-participants ethics obligations.

When should I use Hri Experiments?

Hri Experiments fits situations like: auditing the human-subjects study at the heart of an ACM/IEEE HRI full paper — choosing between/within-subjects designs; running Wizard-of-Oz honestly; powering the sample; reporting statistics with effect sizes and qualitative rigor.

How do I install Hri Experiments in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hri-experiments -a claude-code`. Or copy the skill folder (HRI-Skills/skills/hri-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/hri-experiments in your project. Claude Code loads it when a task matches its description.

How do I install Hri Experiments in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hri-experiments -a codex`. Or copy the skill folder (HRI-Skills/skills/hri-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/hri-experiments in your project. Codex loads it when a task matches its description.

Can I use Hri Experiments in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hri-experiments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hri-experiments, .gemini/skills/hri-experiments, .github/skills/hri-experiments and .opencode/skills/hri-experiments in your project.

What does Hri Experiments need to run?

SKILL.md names no scripts, command-line tools or credentials: Hri Experiments is instructions for the agent only.

Does Hri Experiments access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hri Experiments safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hri Experiments use?

Hri Experiments is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hri Experiments use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hri Experiments?

Skills that share tags, products or a category with Hri Experiments: Sandbox Bench (vercel/next.js, 143k stars), Statistical Analysis (spacering-net/codeg, 3.9k stars), Statsmodels (zLanqing/codex-claude-academic-skills, 4.7k stars) and AI Daily Digest (vigorX777/ai-daily-digest, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hri Experiments?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,228 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.