Agent skill

Experiment Bridge

by appleweiping in appleweiping/WEIPING_WIKI

Bridge from experiment plan to executable code. An agent skill from appleweiping/WEIPING_WIKI.

MITAuto-check passed

Install Experiment Bridge

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a claude-code

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

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge --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/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .claude/skills/experiment-bridge && 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/

Paste into Claude Code

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .claude/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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

$skill-installer install https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge

Type 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.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .agents/skills/experiment-bridge && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .agents/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .cursor/skills/experiment-bridge && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .cursor/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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

$ gemini skills install https://github.com/appleweiping/WEIPING_WIKI.git --path .claude/skills/aris/skills/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.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .gemini/skills/experiment-bridge && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .gemini/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge

Installs 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).

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .github/skills/experiment-bridge && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .github/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI experiment-bridge --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-bridge .opencode/skills/experiment-bridge && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "experiment-bridge" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-bridge into .opencode/skills/experiment-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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: experiment-bridge
GitHub stars: 119
Token cost: ~900 tokens
SKILL.md length: 356 words
Files: 1
Skills in repo: 51
Repo updated: Aug 26, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Bridge from experiment plan to executable code. An agent skill from appleweiping/WEIPING_WIKI.

Works in 5 steps: Code Architecture → Baseline Implementation → Our Method Implementation → …
User says experiment-bridge
SKILL.md covers Decision Gate, Phase 1 — Code Architecture, Phase 2 — Baseline… and Phase 3 — Our Method…, plus 4 more sections
Calls python

What it does

Experiment Bridge is an agent skill from appleweiping/WEIPING_WIKI. Bridge from experiment plan to executable code. Translates the experiment plan into runnable scripts, configs, and infrastructure. Use when user says "experiment-bridge", "实验桥接", "bridge to code", "implement the experiment", or after experiment-plan is complete and reviewed.

Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.

When your agent uses it

User says experiment-bridge
Implement the experiment
After experiment-plan is complete and reviewed

Example prompts

“experiment-bridge”
“bridge to code”
“implement the experiment”
“/experiment-bridge”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Code Architecture
Baseline Implementation
Our Method Implementation
Run Infrastructure
Validation Run

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
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

Experiment Bridge loads about 900 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 356 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~73
When it runs · the whole SKILL.md, loaded when a task matches: ~900

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). 356 words, ~900 tokens.

Download SKILL.mdSave it as .claude/skills/experiment-bridge/SKILL.md (or your agent's skills folder).

name: experiment-bridge
description: Bridge from experiment plan to executable code. Translates the experiment plan into runnable scripts, configs, and infrastructure. Use when user says "experiment-bridge", "实验桥接", "bridge to code", "implement the experiment", or after experiment-plan is complete and reviewed.

Experiment Bridge

Turn the experiment plan into code that runs. No hand-waving, no "TODO: implement later."

Decision Gate

Before running:

refine-logs/EXPERIMENT_PLAN.md exists and was reviewed by Codex (score ≥6 on all dimensions)
refine-logs/EXPERIMENT_TRACKER.md exists
Compute resources are confirmed accessible (SSH to server works)
Dataset paths are verified

Phase 1 — Code Architecture

Survey existing code in the project directory

Design the experiment runner structure:

experiments/
  configs/          # YAML configs per block/baseline
  scripts/          # Run scripts (train, eval, analyze)
  baselines/        # Baseline implementations or wrappers
  results/          # Output directory (gitignored)
  analysis/         # Post-hoc analysis scripts

Identify reusable components from existing code
Define the config schema (dataset, model, hyperparams, seeds, output_dir)

Output: Architecture doc in experiments/README.md

Phase 2 — Baseline Implementation

For each of the 8+ baselines:

Official implementation available? → Write a wrapper script
Need reimplementation? → Implement from paper, verify on reported numbers
Create unified evaluation interface — all baselines produce same output format

Quality check: Each baseline must reproduce reported numbers within 5% (or document why not).

Phase 3 — Our Method Implementation

Core algorithm — implement the novel component
Integration — connect to data pipeline and evaluation
Sanity check — run on tiny subset, verify no crashes, output format correct
Config files — one per experiment block × baseline × seed

Phase 4 — Run Infrastructure

Launcher script — handles seed loops, GPU allocation, logging
Monitoring — progress bars, estimated time, early stopping
Result collection — auto-aggregate across seeds into summary tables
Checkpoint strategy — save intermediate results for crash recovery

Example launcher:

bash

#!/bin/bash
for seed in $(seq 1 $NUM_SEEDS); do
  for config in configs/block_${BLOCK}/*.yaml; do
    python run.py --config $config --seed $seed --output results/
  done
done

Show full SKILL.md (133 more words)Show less

Phase 5 — Validation Run

M0 sanity milestone: Run Block 1 with 3 seeds
Verify: Results are reasonable, no NaN/Inf, metrics in expected range
Timing: Measure wall-clock per run, extrapolate total compute
Fix issues before scaling up

Quality check: M0 must pass before proceeding to full runs.

Handoff

Output: experiments/ directory with all code, configs, scripts
Update refine-logs/EXPERIMENT_TRACKER.md (M0 status)
Update memory/facts/<project>-status.md
Next ARIS step: run-experiment → monitor
Handoff to: OpenCode (executor) for running, or user for GPU submission

Hard Rules

No mock implementations — every baseline must actually run
Config-driven: changing an experiment should only require editing a YAML file
Reproducibility: same config + same seed = same result (set all random seeds)
All results go to results/ (gitignored), never committed to repo
Evidence labels: M0 outputs are "diagnostic" until full seeds complete

Files

Just SKILL.md in .claude/skills/aris/skills/experiment-bridge of appleweiping/WEIPING_WIKI.

Open the folder on GitHubat commit 76fdc42

Compare with similar skills

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.

Experiment Bridge compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Experiment Bridge this skillappleweiping/WEIPING_WIKI	119	—	~900	Automated safety check: Pass	MIT	1 mo ago
Translation Diff TranslateDevolutions/UniGetUI	26k	—	~934	Automated safety check: Pass	MIT	yesterday
Plane UI Translationmakeplane/plane	61k	—	~16k	Automated safety check: Pass	AGPL-3.0	yesterday
Visa Doc Translateaffaan-m/ECC	275k	4 repos	~1k	Automated safety check: Pass	MIT	3 days ago
Translatorholaboss-ai/holaOS	11k	—	~617	Automated safety check: Pass	Custom licence	1 mo ago
Generate Translationspayloadcms/payload	45k	—	~1.1k	Automated safety check: Pass	MIT	today

Similar skills

Translation Diff Translate
Devolutions/UniGetUI
Translates a sparse UniGetUI JSON language patch, writes completed entries into the working copy, preserves placeholders and terminology, and prepares the patch for merge-back.
26k GitHub stars~934 tokensUpdated yesterday
Writing & ContentAuto-check passed
Plane UI Translation
makeplane/plane
Sets the rules for translating and updating Plane's UI strings across locales: do-not-translate terms, plural forms, placeholders and AI translation review.
61k GitHub stars~16k tokensUpdated yesterday
Writing & ContentAuto-check passed
Visa Doc Translate
affaan-m/ECC
Translate visa document images (bank deposit, employment, income, and retirement certificates; HEIC, PNG, or JPG) into English via OCR and produce a bilingual PDF pairing the original image with a…
275k GitHub starsUsed in 4 repos~1k tokens
Writing & ContentAuto-check passed
Translator
holaboss-ai/holaOS
Translate content across languages while preserving brand voice and cultural nuance.
11k GitHub stars~617 tokensUpdated 1 mo ago
Writing & ContentAuto-check passed
Generate Translations
payloadcms/payload
A skill your agent uses when new translation keys are added to packages to generate new translations strings
45k GitHub stars~1.1k tokensUpdated today
Writing & ContentAuto-check passed
Translation
doxygen/doxygen
Keeps all Doxygen and Doxywizard translations up to date across three mechanisms: translator C++ classes (src/translatorxx.h), Qt .ts locale files for the Doxywizard GUI (addon/doxywizard/i18n/)…
6.6k GitHub stars~5.2k tokensUpdated 8 days ago
Writing & ContentAuto-check passed

More from appleweiping/WEIPING_WIKI

All 51 skills in this repo

Communication Assistant
appleweiping/WEIPING_WIKI
Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.
119 GitHub stars~1.1k tokensUpdated 1 mo ago
Auto-check passed
Content Refinement Agent
appleweiping/WEIPING_WIKI
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.
119 GitHub stars~3k tokensUpdated 1 mo ago
Auto-check passed
Chrome Automation
appleweiping/WEIPING_WIKI
Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).
119 GitHub starsUsed in 1 repo~5.3k tokens
Auto-check: warnings
Email Assistant
appleweiping/WEIPING_WIKI
Personal Gmail and Google Workspace email assistant for Vipin.
119 GitHub stars~1.3k tokensUpdated 1 mo ago
Auto-check passed
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…
119 GitHub stars~765 tokensUpdated 1 mo ago
Auto-check passed
Feishu Bridge
appleweiping/WEIPING_WIKI
Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.
119 GitHub stars~906 tokensUpdated 1 mo ago
Auto-check passed

Questions about Experiment Bridge

What does Experiment Bridge do?

Bridge from experiment plan to executable code. An agent skill from appleweiping/WEIPING_WIKI. Experiment Bridge is an agent skill from appleweiping/WEIPING_WIKI. Bridge from experiment plan to executable code.

When should I use Experiment Bridge?

Experiment Bridge fits situations like: user says experiment-bridge; implement the experiment; after experiment-plan is complete and reviewed.

How do I install Experiment Bridge in Claude Code?

Run `npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a claude-code`. Or copy the skill folder (.claude/skills/aris/skills/experiment-bridge in appleweiping/WEIPING_WIKI) into .claude/skills/experiment-bridge in your project. Claude Code loads it when a task matches its description.

How do I install Experiment Bridge in Codex?

Run `npx skills add appleweiping/WEIPING_WIKI --skill experiment-bridge -a codex`. Or copy the skill folder (.claude/skills/aris/skills/experiment-bridge in appleweiping/WEIPING_WIKI) into .agents/skills/experiment-bridge in your project. Codex loads it when a task matches its description.

Can I use 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 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/experiment-bridge, .gemini/skills/experiment-bridge, .github/skills/experiment-bridge and .opencode/skills/experiment-bridge in your project.

What does Experiment Bridge need to run?

Going by SKILL.md and its folder, Experiment Bridge needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does 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 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 Experiment Bridge use?

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 Experiment Bridge use?

About 900 tokens (SKILL.md is roughly 3.6k 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 Experiment Bridge?

Skills that share tags, products or a category with Experiment Bridge: Translation Diff Translate (Devolutions/UniGetUI, 26k stars), Plane UI Translation (makeplane/plane, 61k stars), Visa Doc Translate (affaan-m/ECC, 275k stars) and Translator (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 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.

Install Experiment Bridge

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Experiment Bridge

Decision Gate

Phase 1 — Code Architecture

Phase 2 — Baseline Implementation

Phase 3 — Our Method Implementation

Phase 4 — Run Infrastructure

Phase 5 — Validation Run

Handoff

Hard Rules

Files

Compare with similar skills

Similar skills

More from appleweiping/WEIPING_WIKI

Questions about Experiment Bridge