Agent Prompt Quality Bar
mastra-ai/mastra
Universal quality bar and final audit rubric for any agent system prompt.
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.
Install Experiments
$ npx skills add Arize-ai/phoenix --skill experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Arize-ai/phoenix experiments --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/Arize-ai/phoenix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .claude/skills/experiments && 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 "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .claude/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experimentsType 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 Arize-ai/phoenix --skill experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Arize-ai/phoenix experiments --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arize-ai/phoenix.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .agents/skills/experiments && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .agents/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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 Arize-ai/phoenix --skill experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Arize-ai/phoenix experiments --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arize-ai/phoenix.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .cursor/skills/experiments && 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 "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .cursor/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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/Arize-ai/phoenix.git --path src/phoenix/server/agents/prompts/skills/experiments--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 Arize-ai/phoenix --skill experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Arize-ai/phoenix experiments --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arize-ai/phoenix.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .gemini/skills/experiments && 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 "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .gemini/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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 Arize-ai/phoenix experimentsInstalls 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 Arize-ai/phoenix --skill experiments -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Arize-ai/phoenix.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .github/skills/experiments && 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 "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .github/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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 Arize-ai/phoenix --skill experiments -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Arize-ai/phoenix experiments --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arize-ai/phoenix.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/phoenix/server/agents/prompts/skills/experiments .opencode/skills/experiments && 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 "experiments" agent skill from https://github.com/Arize-ai/phoenix/tree/main/src/phoenix/server/agents/prompts/skills/experiments into .opencode/skills/experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiments", 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
experiments- GitHub stars
- 12k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 911 words
- Files
- 1
- Skills in repo
- 39
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.
- Works in 9 steps: Confirm the dataset represents the task:… → Make sure the starting prompt is well… → Run the prompt over the dataset as a… → …
- The user wants to iterate over a dataset with experiments
- SKILL.md covers Before You Start: Read What…, Workflow: Iterate Over A Dataset, Recording What You Learned and Boundaries, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Experiments is an agent skill from Arize-ai/phoenix. Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a dataset with experiments, compare experiment runs, read experiment quality/latency/cost, or decide whether a change actually helped. Running a prompt over a dataset is implicitly an experiment — load this skill when dataset-backed work begins, before authoring evaluators for the experiment and before starting the recorded run, not only when reading results. Do…
Its SKILL.md is about 1.8k 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 observability and Quizzes and assessments. The repository describes itself as: AI Observability & Evaluation.
When your agent uses it
- The user wants to iterate over a dataset with experiments
- Compare experiment runs
- Read experiment quality/latency/cost
- Decide whether a change actually helped
Example prompts
- “/experiments”
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- Confirm the dataset represents the task: the input fields the run consumes, the expected outputs,
- Make sure the starting prompt is well formed before running it — task, variables, output format,
- Run the prompt over the dataset as a recorded experiment, staging the scaffold (hypothesis,
- Read the results across all three axes together — output quality (evaluator annotations, including
- Score what you observe. Anything example-level and scorable defaults to an evaluator at the moment
- Form one specific hypothesis for the next candidate — a named failure mode and the single change
- Compare the new experiment against its baseline per-example and aligned, not by aggregate means
- Report what the comparison showed: a verdict on the hypothesis, a summary across quality, latency,
- Continue hypothesis → run → compare → report until the evidence meets the stated goal, then save
What it can do on your machine
Read from SKILL.md and the folder at commit 3383f07. 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
Experiments loads about 1.8k tokens when it runs. Until then it costs about 201 tokens; SKILL.md has 911 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 911 words (~1,760 tokens).
“An experiment is one run of a prompt or pipeline over every example in a dataset, captured with its outputs and any evaluator annotations so it can be reviewed and compared later. Experiments turn "this prompt feels better" into evidence…”
- name
- experiments
- summary
- Iterate over a dataset with experiments — run, read results across quality, latency, and cost, and compare candidates to drive improvement.
Files
Just SKILL.md in src/phoenix/server/agents/prompts/skills/experiments of Arize-ai/phoenix.
Open the folder on GitHubat commit 3383f07
Compare with similar skills
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Experiments this skillArize-ai/phoenix | 12k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Agent Prompt Quality Barmastra-ai/mastra | 29k | — | ~2k | Automated safety check: Pass | Custom licence | |
| Advanced Evaluationguanyang/open-agent-hub | 973 | 2 repos | ~4.2k | Automated safety check: Pass | MIT | |
| Agentic Evalgithub/awesome-copilot | 40k | 4 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Clawpathy AutoresearchClawBio/ClawBio | 1.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Agentsop Metric Designagentsope/SkillAlchemy | 457 | — | ~6.4k | Automated safety check: Pass | MIT |
Similar skills
Advanced Evaluation
guanyang/open-agent-hub
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated…
- Official
Agentic Eval
github/awesome-copilot
Patterns and techniques for evaluating and improving AI agent outputs.
Clawpathy Autoresearch
ClawBio/ClawBio
Eval-driven skill tuning. An agent skill from ClawBio/ClawBio.
Agentsop Metric Design
agentsope/SkillAlchemy
Decomposed, multi-criteria metric design for LLM pipelines. An agent skill from agentsope/SkillAlchemy.
Suede AI Eval
JasonColapietro/suede-creator-skills
Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates.
More from Arize-ai/phoenix
All 39 skills in this repoHarbor Exec
Arize-ai/phoenix
A skill your agent uses when working with Harbor's harbor exec CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only…
Mintlify
Arize-ai/phoenix
Build and maintain documentation sites with Mintlify. An agent skill from Arize-ai/phoenix.
Phoenix Frontend
Arize-ai/phoenix
Frontend development guidelines for the Phoenix AI observability platform.
Phoenix Graphql
Arize-ai/phoenix
Write efficient GraphQL queries against the Phoenix API. An agent skill from Arize-ai/phoenix.
Phoenix Server
Arize-ai/phoenix
Backend development guide for the Phoenix AI observability platform (Strawberry GraphQL, SQLAlchemy async, FastAPI).
Phoenix Storybook
Arize-ai/phoenix
Conventions for creating, modifying, and reviewing production-faithful Storybook stories in the Phoenix frontend (js/app/stories, js/app/.storybook).
Related
Categories
Questions about Experiments
What does Experiments do?
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Experiments is an agent skill from Arize-ai/phoenix. Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.
When should I use Experiments?
Experiments fits situations like: the user wants to iterate over a dataset with experiments; compare experiment runs; read experiment quality/latency/cost; decide whether a change actually helped.
How do I install Experiments in Claude Code?
Run `npx skills add Arize-ai/phoenix --skill experiments -a claude-code`. Or copy the skill folder (src/phoenix/server/agents/prompts/skills/experiments in Arize-ai/phoenix) into .claude/skills/experiments in your project. Claude Code loads it when a task matches its description.
How do I install Experiments in Codex?
Run `npx skills add Arize-ai/phoenix --skill experiments -a codex`. Or copy the skill folder (src/phoenix/server/agents/prompts/skills/experiments in Arize-ai/phoenix) into .agents/skills/experiments in your project. Codex loads it when a task matches its description.
Can I use 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 Arize-ai/phoenix --skill 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/experiments, .gemini/skills/experiments, .github/skills/experiments and .opencode/skills/experiments in your project.
What does Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Experiments is instructions for the agent only.
Does 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 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 Experiments use?
Experiments 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 Experiments use?
About 1.8k tokens (SKILL.md is roughly 7k 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 Experiments?
Skills that share tags, products or a category with Experiments: Agent Prompt Quality Bar (mastra-ai/mastra, 29k stars), Advanced Evaluation (guanyang/open-agent-hub, 973 stars), Agentic Eval (github/awesome-copilot, 40k stars) and Clawpathy Autoresearch (ClawBio/ClawBio, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Experiments?
Arize-ai (a GitHub organization) maintains it in Arize-ai/phoenix, which has 11,738 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 7, 2026.
Source: Arize-ai/phoenix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.