Not in the top 1,000 by GitHub stars
Syysean/web-ai-skills
Pi agent skills for using Gemini, Grok, DeepSeek, Claude & ChatGPT via browser — no API keys required.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
chatgpt-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
claude-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
deepseek-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
gemini-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
grok-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
web-ai-router/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0d4526020dc1 → 0d4526020dc1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0d4526020dc1
No earlier version was observed for comparison.
16GitHub stars
1star in 7 days
6skills in this repository
0commits in 30 days
Heat
3.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- chatgpt-worker
chatgpt-worker - claude-worker
claude-worker - deepseek-worker
deepseek-worker - gemini-worker
gemini-worker - grok-worker
grok-worker - web-ai-router
web-ai-router
How it works
chatgpt-worker
When your agent uses it
Use this skill to send a prompt to ChatGPT and get a response. Triggers when the user wants to query ChatGPT, use ChatGPT as an external AI worker, or when the web-ai-router directs a task to ChatGPT. Best for general QA, writing, coding, and creative tasks. Requires login — session is persisted in Chrome profile.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,568 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment
- Input
- Output
- Critical Architecture Note
- Workflow
- Retry Policy
- Selector Change Resilience
- Example Output
Files
SKILL.mdcore6,372 bytesSKILL.mdcore6,372 bytesSKILL.mdcore6,372 bytes
Read SKILL.md
# ChatGPT Worker
Send a prompt to ChatGPT via browser and return the response.
## Environment
- URL: https://chatgpt.com
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Required — session persisted in ~/.cache/browser-tools profile
- Tools: `browser-start.js`, `browser-nav.js`, `browser-eval.js`, `browser-screenshot.js`
---
## Inputclaude-worker
When your agent uses it
Use this skill to send a prompt to Claude.ai and get a response. Triggers when the user wants to query Claude.ai via browser, use Claude as an external AI worker, or when the web-ai-router directs a task to Claude. Best for general QA, writing, analysis, and coding tasks. Requires login — session is persisted in Chrome profile.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,319 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment
- Input
- Output
- Workflow
- Retry Policy
- Selector Change Resilience
- Example Output
Files
SKILL.mdcore5,429 bytesSKILL.mdcore5,429 bytesSKILL.mdcore5,429 bytes
Read SKILL.md
# Claude Worker
Send a prompt to Claude.ai via browser and return the response.
## Environment
- URL: https://claude.ai
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Required — session persisted in ~/.cache/browser-tools profile
- Tools: `browser-start.js`, `browser-nav.js`, `browser-eval.js`, `browser-screenshot.js`
---
## Inputdeepseek-worker
When your agent uses it
Use this skill to send a prompt to DeepSeek and get a response. Triggers when the user wants to query DeepSeek, use DeepSeek as an AI worker, or when the web-ai-router directs a task to DeepSeek. Best for deep reasoning, math, code analysis, and complex multi-step problems. Requires login — session is persisted in Chrome profile.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,401 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment
- Input
- Output
- Workflow
- Retry Policy
- Selector Change Resilience
- Example Output
Files
SKILL.mdcore5,812 bytesSKILL.mdcore5,812 bytesSKILL.mdcore5,812 bytes
Read SKILL.md
# DeepSeek Worker
Send a prompt to DeepSeek via browser and return the response.
## Environment
- URL: https://chat.deepseek.com
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Required — session persisted in ~/.cache/browser-tools profile
- Tools: `browser-start.js`, `browser-nav.js`, `browser-eval.js`, `browser-screenshot.js`
---
## Inputgemini-worker
When your agent uses it
Use this skill to send a prompt to Gemini and get a response. Triggers when the user wants to query Gemini, use Gemini as an AI worker, or when the web-ai-router directs a task to Gemini. Handles navigation, input, waiting, and response extraction automatically. No login required.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,475 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment
- Input
- Output
- Workflow
- Retry Policy
- Decision Guide for the Agent
- Selector Change Resilience
- Example Output
Files
SKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytes
Read SKILL.md
# Gemini Worker
Send a prompt to Gemini via browser and return the response.
## Environment
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Not required — Gemini guest mode is confirmed working
- Tools: `browser-start.js`, `browser-nav.js`, `browser-eval.js`, `browser-screenshot.js`
---
## Input
grok-worker
When your agent uses it
Use this skill to send a prompt to Grok and get a response. Triggers when the user wants to query Grok, use Grok as an AI worker, or when the web-ai-router directs a task to Grok. Best for tasks requiring real-time web search, current events, or news. Requires login — session is persisted in Chrome profile.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,322 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Shell Escaping Note
- Environment
- Input
- Output
- Workflow
- Retry Policy
- Selector Change Resilience
- Example Output
Files
SKILL.mdcore5,369 bytesSKILL.mdcore5,369 bytesSKILL.mdcore5,369 bytes
Read SKILL.md
## Shell Escaping Note
When passing JavaScript to browser-eval.js, always use double quotes
for the outer shell argument and single quotes inside the JavaScript.
Example: browser-eval.js "document.querySelector('.class')?.innerText"
# Grok Worker
Send a prompt to Grok via browser and return the response.
## Environment
- URL: https://grok.com
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Required — session persisted in ~/.cache/browser-tools profileweb-ai-router
When your agent uses it
Use this skill ONLY when the user explicitly asks to use Gemini, Grok, DeepSeek, Claude, or ChatGPT by name, or says 'ask another AI', 'let Grok search', 'use DeepSeek to analyze', 'ask Claude', 'query an external AI'. Do NOT trigger for general search or QA tasks.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,069 tokensWhen the skill is activated
Reference documents
400 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Available Workers
- Routing Logic
- Multi-Worker Mode
- Decision Examples
Files
SKILL.mdcore4,461 bytesworker-contract.mddoc1,664 bytes
Read SKILL.md
# Web AI Router
Select the best available web AI for a task and delegate to the appropriate worker.
---
## Available Workers
| Worker | URL | Login Required | Best For |
|--------|-----|---------------|----------|
| gemini-worker | gemini.google.com | ❌ No | General QA, summarization, translation, current events (has Google Search) |
| grok-worker | grok.com | ✅ Yes | Real-time web search, breaking news, current events, X/Twitter context |
| deepseek-worker | chat.deepseek.com | ✅ Yes | Deep reasoning, math, code analysis, complex multi-step problems |
| claude-worker | claude.ai | ✅ Yes | Writing, analysis, coding, nuanced long-form tasks |Skills included
- chatgpt-worker
- claude-worker
- deepseek-worker
- gemini-worker
- grok-worker
- web-ai-router
Repository facts
- License
- MIT
- Created
- May 31, 2026
- Last pushed
- Jun 1, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 10 notes
chatgpt-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatgpt-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddeepseek-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddeepseek-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgemini-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgemini-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgrok-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgrok-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 19 network referencesin 5 files: chatgpt-worker/SKILL.md:12 claude-worker/SKILL.md:12 deepseek-worker/SKILL.md:12 and 2 more
- 10 obfuscation signalsin 2 files: deepseek-worker/SKILL.md:99 grok-worker/SKILL.md:148
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 29 signals by file
chatgpt-worker/SKILL.md
- Network accessline 12
- URL: https://chatgpt.com - Network accessline 71
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://chatgpt.com - Network accessline 199
- Maximum retries: 2 - On each retry: re-navigate to `https://chatgpt.com` before retrying - Network accessline 200
- On each retry: re-navigate to `https://chatgpt.com` before retrying
claude-worker/SKILL.md
- Network accessline 12
- URL: https://claude.ai - Network accessline 65
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://claude.ai - Network accessline 187
- Maximum retries: 2 - On each retry: re-navigate to `https://claude.ai` before retrying - Network accessline 188
- On each retry: re-navigate to `https://claude.ai` before retrying
deepseek-worker/SKILL.md
- Network accessline 12
- URL: https://chat.deepseek.com - Network accessline 65
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://chat.deepseek.com - Possible obfuscationline 99
<U+200B>```javascript - Possible obfuscationline 113
<U+200B>``` - Possible obfuscationline 127
<U+200B>```javascript - Possible obfuscationline 135
<U+200B>``` - Possible obfuscationline 168
<U+200B>```javascript - Possible obfuscationline 176
<U+200B>``` - Network accessline 189
- Maximum retries: 2 - On each retry: re-navigate to `https://chat.deepseek.com` before retrying - Network accessline 190
- On each retry: re-navigate to `https://chat.deepseek.com` before retrying
gemini-worker/SKILL.md
- Network accessline 64
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://gemini.google.com/app - Network accessline 173
- Maximum retries: 2 - On each retry: re-navigate to `https://gemini.google.com/app` before retrying - Network accessline 174
- On each retry: re-navigate to `https://gemini.google.com/app` before retrying
grok-worker/SKILL.md
- Network accessline 17
- URL: https://grok.com - Network accessline 70
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://grok.com - Possible obfuscationline 148
<U+200B>```javascript - Possible obfuscationline 154
<U+200B>``` - Possible obfuscationline 162
<U+200B>```javascript - Possible obfuscationline 168
<U+200B>``` - Network accessline 181
- Maximum retries: 2 - On each retry: re-navigate to `https://grok.com` before retrying - Network accessline 182
- On each retry: re-navigate to `https://grok.com` before retrying
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 29 facts
- Network access in prose of the SKILL.mdchatgpt-worker/SKILL.md:12Low confidence
- Network access in code of the SKILL.mdchatgpt-worker/SKILL.md:71High confidence
- Network access in prose of the SKILL.mdchatgpt-worker/SKILL.md:199Low confidence
- Network access in prose of the SKILL.mdchatgpt-worker/SKILL.md:200Low confidence
- Network access in prose of the SKILL.mdclaude-worker/SKILL.md:12Low confidence
- Network access in code of the SKILL.mdclaude-worker/SKILL.md:65High confidence
- Network access in prose of the SKILL.mdclaude-worker/SKILL.md:187Low confidence
- Network access in prose of the SKILL.mdclaude-worker/SKILL.md:188Low confidence
- Network access in prose of the SKILL.mddeepseek-worker/SKILL.md:12Low confidence
- Network access in code of the SKILL.mddeepseek-worker/SKILL.md:65High confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:99Low confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:113Low confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:127Low confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:135Low confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:168Low confidence
- Possible obfuscation in prose of the SKILL.mddeepseek-worker/SKILL.md:176Low confidence
- Network access in prose of the SKILL.mddeepseek-worker/SKILL.md:189Low confidence
- Network access in prose of the SKILL.mddeepseek-worker/SKILL.md:190Low confidence
- Network access in code of the SKILL.mdgemini-worker/SKILL.md:64High confidence
- Network access in prose of the SKILL.mdgemini-worker/SKILL.md:173Low confidence
- Network access in prose of the SKILL.mdgemini-worker/SKILL.md:174Low confidence
- Network access in prose of the SKILL.mdgrok-worker/SKILL.md:17Low confidence
- Network access in code of the SKILL.mdgrok-worker/SKILL.md:70High confidence
- Possible obfuscation in prose of the SKILL.mdgrok-worker/SKILL.md:148Low confidence
- Possible obfuscation in prose of the SKILL.mdgrok-worker/SKILL.md:154Low confidence
- Possible obfuscation in prose of the SKILL.mdgrok-worker/SKILL.md:162Low confidence
- Possible obfuscation in prose of the SKILL.mdgrok-worker/SKILL.md:168Low confidence
- Network access in prose of the SKILL.mdgrok-worker/SKILL.md:181Low confidence
- Network access in prose of the SKILL.mdgrok-worker/SKILL.md:182Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md chatgpt-worker/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
