LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
Agent skill
Phack Eval Harness
by brycewang-stanford in brycewang-stanford/Auto-Empirical-Research-Skills
Run and score the agent p-hacking benchmark. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
Install Phack Eval Harness
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harness --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .claude/skills/phack-eval-harness && rm -rf skills-srcUse ~/.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/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .claude/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harnessType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harness --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .agents/skills/phack-eval-harness && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .agents/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harness --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .cursor/skills/phack-eval-harness && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .cursor/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git --path skills/73-brycewang-p-hacking-skills/skills/08-eval-harness--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harness --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .gemini/skills/phack-eval-harness && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .gemini/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harnessInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .github/skills/phack-eval-harness && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .github/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Auto-Empirical-Research-Skills phack-eval-harness --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness .opencode/skills/phack-eval-harness && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "phack-eval-harness" agent skill from https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/73-brycewang-p-hacking-skills/skills/08-eval-harness into .opencode/skills/phack-eval-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phack-eval-harness", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
phack-eval-harness- GitHub stars
- 4.5k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 718 words
- Files
- 1
- Skills in repo
- 383
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Run and score the agent p-hacking benchmark. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
- Benchmarking whether an AI agent p-hacks
- SKILL.md covers Design, Ground truth, Running and Scoring, plus 4 more sections
- Calls python
- Comparing models
What it does
Phack Eval Harness is an agent skill from brycewang-stanford/Auto-Empirical-Research-Skills. Run and score the agent p-hacking benchmark. Composes prompt cells across research framing and significance pressure, drives an agent through them, and scores each run into a P-Hacking Intensity index decomposed into selection, search breadth, estimate inflation, inference gap, pre-registration departure and disclosure. Use when benchmarking whether an AI agent p-hacks, comparing models or tool stacks on statistical integrity, scoring a single agent analysis run, or designing an evaluation of statistical…
Its SKILL.md is about 1.6k 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 AI & LLM Engineering, covering LLM evaluation. The repository describes itself as: 🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…
When your agent uses it
- Benchmarking whether an AI agent p-hacks
- Comparing models
- Tool stacks on statistical integrity
- Scoring a single agent analysis run
Example prompts
- “/phack-eval-harness”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 9fa87d8. 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
Shell commands in SKILL.md call:
python
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
Phack Eval Harness loads about 1.6k tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 718 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 718 words (~1,641 tokens).
“A cell is framing × nudge × task, run k times.”
- name
- phack-eval-harness
Files
Just SKILL.md in skills/73-brycewang-p-hacking-skills/skills/08-eval-harness of brycewang-stanford/Auto-Empirical-Research-Skills.
Open the folder on GitHubat commit 9fa87d8
Compare with similar skills
Phack Eval Harness 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Phack Eval Harness this skillbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Looperksimback/looper | 710 | — | ~2.7k | Automated safety check: Notes | MIT | |
| Agent Eval Engineeringlangchain-ai/langchain-skills | 1.3k | — | ~4k | Automated safety check: Pass | MIT | |
| Quality FlywheelGoogleCloudPlatform/vertex-ai-samples | 792 | — | ~2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
- Official
Agent Eval Engineering
langchain-ai/langchain-skills
Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.
Quality Flywheel
GoogleCloudPlatform/vertex-ai-samples
Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK.
Eval Harness
cloudnative-co/claude-code-starter-kit
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
More from brycewang-stanford/Auto-Empirical-Research-Skills
All 383 skills in this repoAer Consistency
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when auditing a finished or near-finished AER, AER:Insights, or AEJ manuscript for internal consistency: headline numbers across abstract, introduction, results, and tables…
Latex Paper En
brycewang-stanford/Auto-Empirical-Research-Skills
English LaTeX academic paper assistant for existing .tex projects.
Bayesian Workflow
brycewang-stanford/Auto-Empirical-Research-Skills
Opinionated Bayesian modeling workflow with PyMC and ArviZ. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
Daily Paper Generator
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when the user asks to "generate daily paper", "search arXiv for EEG papers", "find EEG decoding papers", "review brain-computer interface papers", or wants to create paper…
Five Questions
brycewang-stanford/Auto-Empirical-Research-Skills
Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.
Kaggle Research
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when a research task needs reproducible Kaggle discovery, metadata inspection, bounded public-data downloads, competition or kernel discovery, model discovery, or an…
Related
Categories
Questions about Phack Eval Harness
What does Phack Eval Harness do?
Run and score the agent p-hacking benchmark. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills. Phack Eval Harness is an agent skill from brycewang-stanford/Auto-Empirical-Research-Skills. Run and score the agent p-hacking benchmark.
When should I use Phack Eval Harness?
Phack Eval Harness fits situations like: benchmarking whether an AI agent p-hacks; comparing models; tool stacks on statistical integrity; scoring a single agent analysis run.
How do I install Phack Eval Harness in Claude Code?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a claude-code`. Or copy the skill folder (skills/73-brycewang-p-hacking-skills/skills/08-eval-harness in brycewang-stanford/Auto-Empirical-Research-Skills) into .claude/skills/phack-eval-harness in your project. Claude Code loads it when a task matches its description.
How do I install Phack Eval Harness in Codex?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill phack-eval-harness -a codex`. Or copy the skill folder (skills/73-brycewang-p-hacking-skills/skills/08-eval-harness in brycewang-stanford/Auto-Empirical-Research-Skills) into .agents/skills/phack-eval-harness in your project. Codex loads it when a task matches its description.
Can I use Phack Eval Harness 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/Auto-Empirical-Research-Skills --skill phack-eval-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/phack-eval-harness, .gemini/skills/phack-eval-harness, .github/skills/phack-eval-harness and .opencode/skills/phack-eval-harness in your project.
What does Phack Eval Harness need to run?
Going by SKILL.md and its folder, Phack Eval Harness needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Phack Eval Harness 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 Phack Eval Harness 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 Phack Eval Harness use?
Phack Eval Harness has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Phack Eval Harness use?
About 1.6k tokens (SKILL.md is roughly 6.6k 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 Phack Eval Harness?
Skills that share tags, products or a category with Phack Eval Harness: LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), Looper (ksimback/looper, 710 stars) and Agent Eval Engineering (langchain-ai/langchain-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Phack Eval Harness?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Auto-Empirical-Research-Skills, which has 4,542 GitHub stars. The repository holds 383 skills in this directory. The repository was last updated on October 5, 2026.
Source: brycewang-stanford/Auto-Empirical-Research-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.