Review R
maxwell2732/paper-replicate-agent-demo
Run the R code review protocol on R scripts. An agent skill from maxwell2732/paper-replicate-agent-demo.
Code review focused on experiment integrity, not general code quality.
Install Aris Experiment Bridge
$ npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-experiment-bridge --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/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .claude/skills/aris-experiment-bridge && 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 "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .claude/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridgeType 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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-experiment-bridge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .agents/skills/aris-experiment-bridge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .agents/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-experiment-bridge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .cursor/skills/aris-experiment-bridge && 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 "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .cursor/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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/appleweiping/WEIPING_WIKI.git --path .codex/skills/aris-experiment-bridge--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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-experiment-bridge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .gemini/skills/aris-experiment-bridge && 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 "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .gemini/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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 appleweiping/WEIPING_WIKI aris-experiment-bridgeInstalls 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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .github/skills/aris-experiment-bridge && 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 "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .github/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-experiment-bridge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/aris-experiment-bridge .opencode/skills/aris-experiment-bridge && 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 "aris-experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-bridge into .opencode/skills/aris-experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-experiment-bridge", 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
aris-experiment-bridge- GitHub stars
- 119
- Token cost
- ~1.6k tokens
- SKILL.md length
- 613 words
- Files
- 1
- Skills in repo
- 51
- Repo updated
- First seen
- Licence
- MIT
At a glance
Code review focused on experiment integrity, not general code quality.
- Works in 4 steps: Config Schema Check → Seed and Reproducibility Check → Baseline Fairness Check → …
- Tasks that involve Reproducible research
- SKILL.md covers Your Mandate, Scope Boundaries, Phase 1: Config Schema Check and Phase 2: Seed and…, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Aris Experiment Bridge is an agent skill from appleweiping/WEIPING_WIKI. Code review focused on experiment integrity, not general code quality. Check reproducibility, config-driven design, baseline fairness, seed handling. Triggers: "review experiment code", "check implementation", "bridge review", "is this code reproducible", "audit experiment implementation"
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 Development, covering Reproducible research and Code quality. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.
When your agent uses it
- Tasks that involve Reproducible research
- Tasks that involve Code quality
Example prompts
- “review experiment code”
- “check implementation”
- “bridge review”
- “/aris-experiment-bridge”
Requirements
- Python 3
Workflow steps
4 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 76fdc42. 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
Aris Experiment Bridge loads about 1.6k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 613 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 appleweiping/WEIPING_WIKI at commit 76fdc42, republished under its MIT licence (© appleweiping). 613 words, ~1,608 tokens.
Download SKILL.mdSave it as
.claude/skills/aris-experiment-bridge/SKILL.md (or your agent's skills folder).- name
- aris-experiment-bridge
- description
- Code review focused on experiment integrity, not general code quality. Check reproducibility, config-driven design, baseline fairness, seed handling. Triggers: "review experiment code", "check implementation", "bridge review", "is this code reproducible", "audit experiment implementation"
- role
- auditor
- stage
- experiment-bridge
ARIS Experiment-Bridge Auditor
You are the AUDITOR for experiment implementation code. This is NOT a general code review. You focus exclusively on whether the code will produce REPRODUCIBLE, FAIR, and TRUSTWORTHY experimental results. Style, performance, and architecture are someone else's problem.
Your Mandate
- Code that passes your review will produce the same results on any machine
- Baselines get the same treatment as the proposed method
- Configuration is externalized so experiments are auditable
- Random state is controlled everywhere it matters
Scope Boundaries
IN SCOPE (you review these):
- Random seed handling and propagation
- Config/hyperparameter management
- Data loading and splitting logic
- Baseline implementation fairness
- Result logging and storage
- Checkpoint and resume logic
OUT OF SCOPE (ignore these):
- Code style, naming conventions, formatting
- Performance optimization
- Error handling (unless it silently corrupts results)
- Documentation quality
- Test coverage (unless tests verify reproducibility)
Phase 1: Config Schema Check
Required Config Properties
Every experiment must externalize these. Check that they exist and are NOT hardcoded:
-
seedorrandom_seed— top-level, propagated to all sources of randomness -
model/method— which method is being run -
dataset— which data, including version/split info -
hyperparameters— all tunable values externalized -
output_dir— where results are written -
device/compute— hardware specification
Config Anti-Patterns (flag each occurrence)
| Anti-Pattern | Severity | Example |
|---|---|---|
| Magic numbers in code | HIGH | lr = 0.001 without config reference |
| Conditional logic by method name | MEDIUM | if method == "ours": special_treatment() |
| Config values with no default | LOW | Crashes if key missing |
| Nested configs without schema | LOW | Hard to audit what was actually run |
| Config mutation during runtime | HIGH | Config changes after experiment starts |
Config Verdict
CONFIG STATUS: [CLEAN / HAS_ISSUES / BROKEN]
HARDCODED VALUES FOUND: [count]
CRITICAL: [list of high-severity issues]Phase 2: Seed and Reproducibility Check
Seed Propagation Audit
Trace the seed from config to every source of randomness:
- Python
randommodule seeded - NumPy
np.randomseeded (both legacy and Generator API) - PyTorch
torch.manual_seedANDtorch.cuda.manual_seed_all - CUDA determinism:
torch.backends.cudnn.deterministic = True - CUDA benchmark:
torch.backends.cudnn.benchmark = False - Data loader:
worker_init_fnseeds each worker - Data shuffling uses seeded RNG (not global state)
- Any third-party library randomness controlled
Reproducibility Red Flags
| Flag | Impact | Found? |
|---|---|---|
np.random.seed() called without argument | Results vary per run | |
| Seed set after data loading begins | Partial reproducibility | |
| Multi-GPU without distributed seed sync | Different results per GPU count | |
| Non-deterministic operations without acknowledgment | Silent variance | |
| Seed hardcoded (not from config) | Cannot vary for multiple runs | |
random.shuffle() without seeded RNG instance | Uncontrolled randomness |
Show full SKILL.md (240 more words)Show less
Reproducibility Verdict
REPRODUCIBILITY: [DETERMINISTIC / MOSTLY_REPRODUCIBLE / NON_REPRODUCIBLE]
UNCONTROLLED RANDOMNESS SOURCES: [count]
CRITICAL: [list]Phase 3: Baseline Fairness Check
This is the most important check. Unfair baselines invalidate the entire paper.
Fairness Criteria
For EACH baseline, verify:
| Criterion | Proposed Method | Baseline 1 | Baseline 2 | ... |
|---|---|---|---|---|
| Same data splits | ||||
| Same preprocessing | ||||
| Same compute budget | ||||
| Same hyperparameter tuning effort | ||||
| Same evaluation metric code | ||||
| Same number of seeds | ||||
| Same early stopping criteria |
Common Fairness Violations
- Proposed method gets more hyperparameter tuning than baselines
- Baselines use default hyperparameters while proposed method is tuned
- Different data augmentation for proposed vs baselines
- Proposed method trains longer than baselines
- Baselines evaluated on different metric implementation
- Proposed method gets warm-start or pre-training that baselines don't
Fairness Verdict
FAIRNESS: [FAIR / QUESTIONABLE / UNFAIR]
VIOLATIONS: [list with severity]
MOST ADVANTAGED METHOD: [which method gets best treatment]Phase 4: Overall Verdict
Scoring
| Dimension | Score | Notes |
|---|---|---|
| Config Quality | /10 | Externalized, schema-validated, immutable |
| Reproducibility | /10 | Same code + same config = same results |
| Baseline Fairness | /10 | All methods get equal treatment |
| Result Integrity | /10 | Results are logged correctly, not cherry-picked |
Decision Matrix
| Condition | Verdict |
|---|---|
| All >= 7, no HIGH severity flags | PROCEED to run experiments |
| Reproducibility < 5 | ITERATE (fix seeds before running) |
| Fairness < 5 | ITERATE (fix baselines before running) |
| Any CRITICAL issue | ITERATE (fix before any runs) |
| Multiple HIGH issues across dimensions | ITERATE (systematic fixes needed) |
Verdict Format
VERDICT: [PROCEED / ITERATE]
SCORES: C={config} R={reproducibility} F={fairness} I={integrity} AVG={avg}
CRITICAL ISSUES: [count]
HIGH ISSUES: [count]
BLOCKING: [one-line or "None"]
NEXT ACTION: [specific fix list]Interaction Rules
- Focus on experiment integrity, not code quality.
- "This code is ugly but reproducible" → PROCEED.
- "This code is elegant but has uncontrolled randomness" → ITERATE.
- Be specific: cite file, line, and the exact problem.
- If you cannot determine fairness from the code alone, ask for the experiment plan.
© appleweiping, 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 .codex/skills/aris-experiment-bridge of appleweiping/WEIPING_WIKI.
Open the folder on GitHubat commit 76fdc42
Compare with similar skills
Aris Experiment Bridge 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 |
|---|---|---|---|---|---|---|
| Aris Experiment Bridge this skillappleweiping/WEIPING_WIKI | 119 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Review Rmaxwell2732/paper-replicate-agent-demo | 137 | 1 repos | ~315 | Automated safety check: Pass | None | |
| Review Rpedrohcgs/claude-code-my-workflow | 1.7k | — | ~430 | Automated safety check: Pass | MIT | |
| WooCommerce Code Reviewwoocommerce/woocommerce | 11k | 3 repos | ~1.1k | Automated safety check: Pass | Custom licence | |
| Ponytail Lazy Developer ModeDietrichGebert/ponytail | 160k | 1 repos | ~873 | Automated safety check: Pass | MIT | |
| Systematic Code Refactoringluongnv89/claude-howto | 42k | — | ~3k | Automated safety check: Pass | MIT |
Similar skills
Review R
pedrohcgs/claude-code-my-workflow
Read-only R code review protocol for .R scripts. An agent skill from pedrohcgs/claude-code-my-workflow.
WooCommerce Code Review
woocommerce/woocommerce
Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.
Ponytail Lazy Developer Mode
DietrichGebert/ponytail
Makes the agent pick the laziest solution that works: skip unneeded work, reuse what exists, prefer the standard library and platform features, and keep diffs small.
Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
Install Anti-Slop Oxlint Rules
dmmulroy/anti-slop
Installs, updates or migrates the vendored anti-slop Oxlint plugin in a repository, keeping local rule changes and the plugin's license and provenance files.
More from appleweiping/WEIPING_WIKI
All 51 skills in this repoCommunication Assistant
appleweiping/WEIPING_WIKI
Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.
Content Refinement Agent
appleweiping/WEIPING_WIKI
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.
Chrome Automation
appleweiping/WEIPING_WIKI
Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).
Email Assistant
appleweiping/WEIPING_WIKI
Personal Gmail and Google Workspace email assistant for Vipin.
Wechat Video Channel Publish
appleweiping/WEIPING_WIKI
A skill your agent uses when the user wants to log into 微信视频号, validate cookie state, upload videos, set scheduled publish time, fill long description, set a cover image, or save drafts through a…
Feishu Bridge
appleweiping/WEIPING_WIKI
Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.
Related
Categories
Questions about Aris Experiment Bridge
What does Aris Experiment Bridge do?
Code review focused on experiment integrity, not general code quality. Aris Experiment Bridge is an agent skill from appleweiping/WEIPING_WIKI. Code review focused on experiment integrity, not general code quality.
When should I use Aris Experiment Bridge?
Aris Experiment Bridge fits situations like: tasks that involve Reproducible research; tasks that involve Code quality.
How do I install Aris Experiment Bridge in Claude Code?
Run `npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a claude-code`. Or copy the skill folder (.codex/skills/aris-experiment-bridge in appleweiping/WEIPING_WIKI) into .claude/skills/aris-experiment-bridge in your project. Claude Code loads it when a task matches its description.
How do I install Aris Experiment Bridge in Codex?
Run `npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a codex`. Or copy the skill folder (.codex/skills/aris-experiment-bridge in appleweiping/WEIPING_WIKI) into .agents/skills/aris-experiment-bridge in your project. Codex loads it when a task matches its description.
Can I use Aris Experiment Bridge 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 appleweiping/WEIPING_WIKI --skill aris-experiment-bridge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aris-experiment-bridge, .gemini/skills/aris-experiment-bridge, .github/skills/aris-experiment-bridge and .opencode/skills/aris-experiment-bridge in your project.
What does Aris Experiment Bridge need to run?
SKILL.md names no scripts, command-line tools or credentials: Aris Experiment Bridge is instructions for the agent only. Our summary lists: Python 3.
Does Aris Experiment Bridge 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 Aris Experiment Bridge 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 Aris Experiment Bridge use?
Aris Experiment Bridge 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 Aris Experiment Bridge use?
About 1.6k tokens (SKILL.md is roughly 6.4k 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 Aris Experiment Bridge?
Skills that share tags, products or a category with Aris Experiment Bridge: Review R (maxwell2732/paper-replicate-agent-demo, 137 stars), Review R (pedrohcgs/claude-code-my-workflow, 1.7k stars), WooCommerce Code Review (woocommerce/woocommerce, 11k stars) and Ponytail Lazy Developer Mode (DietrichGebert/ponytail, 160k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Aris Experiment Bridge?
appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_WIKI, which has 119 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 26, 2026.
Source: appleweiping/WEIPING_WIKI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.