Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
A skill your agent uses when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.
Install Experiment Iteration Loop
$ npx skills add BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BingHanOfUESTC/open_agent_team experiment-iteration-loop --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/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .claude/skills/experiment-iteration-loop && 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 "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .claude/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loopType 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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BingHanOfUESTC/open_agent_team experiment-iteration-loop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .agents/skills/experiment-iteration-loop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .agents/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BingHanOfUESTC/open_agent_team experiment-iteration-loop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .cursor/skills/experiment-iteration-loop && 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 "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .cursor/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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/BingHanOfUESTC/open_agent_team.git --path teams/auto_research_team/skills/experiment-iteration-loop--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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BingHanOfUESTC/open_agent_team experiment-iteration-loop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .gemini/skills/experiment-iteration-loop && 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 "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .gemini/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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 BingHanOfUESTC/open_agent_team experiment-iteration-loopInstalls 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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .github/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .github/skills/experiment-iteration-loop && 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 "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .github/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BingHanOfUESTC/open_agent_team experiment-iteration-loop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/teams/auto_research_team/skills/experiment-iteration-loop .opencode/skills/experiment-iteration-loop && 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 "experiment-iteration-loop" agent skill from https://github.com/BingHanOfUESTC/open_agent_team/tree/main/teams/auto_research_team/skills/experiment-iteration-loop into .opencode/skills/experiment-iteration-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-iteration-loop", 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
experiment-iteration-loop- GitHub stars
- 106
- Token cost
- ~446 tokens
- SKILL.md length
- 86 words
- Files
- 1
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.
- Works in 5 steps: Experiment Queue → Required Experiment Types → Logging → …
- Iterating experiments for the selected research idea
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Tasks that involve Hypothesis generation
What it does
Experiment Iteration Loop is an agent skill from BingHanOfUESTC/open_agent_team. Use this skill when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.
Its SKILL.md is about 450 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 Research & Science, covering Hypothesis generation. The repository describes itself as: Build persistent multi-agent teams that collaborate like real organizations to deliver complex tasks. The licence is MIT.
When your agent uses it
- Iterating experiments for the selected research idea
- Tasks that involve Hypothesis generation
Example prompts
- “/experiment-iteration-loop”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 7e28736. 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 (its code samples are markdown).
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
Experiment Iteration Loop loads about 446 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 86 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
The full file from BingHanOfUESTC/open_agent_team at commit 7e28736, republished under its MIT licence (© BingHanOfUESTC). 86 words, ~446 tokens.
Download SKILL.mdSave it as
.claude/skills/experiment-iteration-loop/SKILL.md (or your agent's skills folder).- name
- experiment-iteration-loop
- description
- Use this skill when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.
Experiment Iteration Loop
This skill ensures experiments are decisive, logged, and honest about failures.
1. Experiment Queue
Maintain:
research_workspace/experiments/experiment_queue.mdUse this structure:
## EXP-<N>: <name>
- Purpose:
- Hypothesis:
- Baseline or variant:
- Config:
- Command:
- Expected duration:
- Hardware:
- Success criterion:
- Failure criterion:
- Status:2. Required Experiment Types
Default order:
SMOKE: environment and data sanity
BASE: baseline reproduction or minimum baseline
MAIN: proposed method
ABL: ablation that isolates the change
ROB: robustness/sensitivity if resources allow
FAIL: diagnosis for unexpected failureDo not run expensive variants before baseline and smoke tests.
3. Logging
For every run, save:
config
command
stdout/stderr
metric output
random seed
hardware
start/end time
git diff or file state
notesWrite summary to:
research_workspace/09_experiment_log.mdStore raw logs under:
research_workspace/experiments/logs/4. Result Table
Maintain:
research_workspace/experiments/results.csvMinimum columns:
experiment_id
method
dataset
split
seed
metric
value
runtime
hardware
log_path
notesFigures and LaTeX tables must be generated from this file or a documented equivalent.
5. Iteration Decision
After each batch of experiments, decide:
continue
debug
ablate
pivot
downgrade
stop_success
stop_negative_result
blockedRecord the decision and evidence in decision_register.md.
© BingHanOfUESTC, 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 teams/auto_research_team/skills/experiment-iteration-loop of BingHanOfUESTC/open_agent_team.
Open the folder on GitHubat commit 7e28736
Compare with similar skills
Experiment Iteration Loop 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 |
|---|---|---|---|---|---|---|
| Experiment Iteration Loop this skillBingHanOfUESTC/open_agent_team | 106 | — | ~446 | Automated safety check: Pass | MIT | |
| Hypothesis Generationspacering-net/codeg | 3.8k | 15 repos | ~3.6k | Automated safety check: Notes | MIT | |
| Nature Paper CardYuan1z0825/nature-skills | 46k | 2 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Hypothesis GenerationK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Good QuestionRimagination/good-question | 305 | 1 repos | ~4.3k | Automated safety check: Pass | MIT | |
| Claim-Driven Experiment PlannerzjYao36/Auto-Research-Refine | 128 | 7 repos | ~2.3k | Automated safety check: Notes | None |
Similar skills
Nature Paper Card
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
Hypothesis Generation
K-Dense-AI/claude-scientific-writer
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready…
Good Question
Rimagination/good-question
A skill your agent uses when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled…
Claim-Driven Experiment Planner
zjYao36/Auto-Research-Refine
Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.
High Stakes Analytics Decision Lab
limingrui679-design/high-stakes-analytics-decision-lab
Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.
More from BingHanOfUESTC/open_agent_team
All 30 skills in this repoSkill Validation And Evaluation
BingHanOfUESTC/open_agent_team
A skill your agent uses when validating a newly created or updated agent skill with structure checks, routing positive and negative examples, contamination checks, progressive disclosure review, and…
Autoresearch Orchestration
BingHanOfUESTC/open_agent_team
A skill your agent uses when autoresearchteam needs to manage an end-to-end research lifecycle from Boss brief to literature, idea, implementation, experiments, synthesis, and LaTeX delivery.
Latex Paper Artifact
BingHanOfUESTC/open_agent_team
A skill your agent uses when producing the final arXiv-style LaTeX paper, BibTeX, figures, tables, reproducibility statement, appendix, and artifact manifest.
Literature Evidence Mapping
BingHanOfUESTC/open_agent_team
A skill your agent uses when discovering papers, mapping related work, reading papers deeply, checking citations, or building evidence cards for an auto research task.
Media Asset Sourcing
BingHanOfUESTC/open_agent_team
A skill your agent uses when PPT slides need external images, screenshots, logos, product photos, stock-like visuals, diagrams, or videos that must be downloaded, inserted, or linked with source and…
Originality Safety Guard
BingHanOfUESTC/open_agent_team
A skill your agent uses when checking creative fiction for originality, name safety, public figure misuse, historical figure misuse, news-event overfitting, recognizable plot borrowing, IP-like…
Related
Categories
Questions about Experiment Iteration Loop
What does Experiment Iteration Loop do?
A skill your agent uses when designing, running, logging, diagnosing, or iterating experiments for the selected research idea. Experiment Iteration Loop is an agent skill from BingHanOfUESTC/open_agent_team. Use this skill when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.
When should I use Experiment Iteration Loop?
Experiment Iteration Loop fits situations like: iterating experiments for the selected research idea; tasks that involve Hypothesis generation.
How do I install Experiment Iteration Loop in Claude Code?
Run `npx skills add BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a claude-code`. Or copy the skill folder (teams/auto_research_team/skills/experiment-iteration-loop in BingHanOfUESTC/open_agent_team) into .claude/skills/experiment-iteration-loop in your project. Claude Code loads it when a task matches its description.
How do I install Experiment Iteration Loop in Codex?
Run `npx skills add BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a codex`. Or copy the skill folder (teams/auto_research_team/skills/experiment-iteration-loop in BingHanOfUESTC/open_agent_team) into .agents/skills/experiment-iteration-loop in your project. Codex loads it when a task matches its description.
Can I use Experiment Iteration Loop 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 BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/experiment-iteration-loop, .gemini/skills/experiment-iteration-loop, .github/skills/experiment-iteration-loop and .opencode/skills/experiment-iteration-loop in your project.
What does Experiment Iteration Loop need to run?
SKILL.md names no scripts, command-line tools or credentials: Experiment Iteration Loop is instructions for the agent only.
Does Experiment Iteration Loop 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 Experiment Iteration Loop 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 Experiment Iteration Loop use?
Experiment Iteration Loop 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 Experiment Iteration Loop use?
About 446 tokens (SKILL.md is roughly 1.8k 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 Experiment Iteration Loop?
Skills that share tags, products or a category with Experiment Iteration Loop: Hypothesis Generation (spacering-net/codeg, 3.8k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars), Hypothesis Generation (K-Dense-AI/claude-scientific-writer, 2.4k stars) and Good Question (Rimagination/good-question, 305 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Experiment Iteration Loop?
BingHanOfUESTC (a GitHub user) maintains it in BingHanOfUESTC/open_agent_team, which has 106 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on June 23, 2026.
Source: BingHanOfUESTC/open_agent_team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.