Not in the top 1,000 by GitHub stars
sbusso/claudeclaw
Use Claude to orchestrate agents like OpenClaw
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
agent/skills/agent-browser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-compact/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-discord/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-gmail/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-image-vision/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-ollama-tool/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-parallel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-pdf-reader/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-qmd/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-reactions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-telegram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-telegram-swarm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-voice-transcription/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/add-whatsapp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/convert-to-apple-container/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/customize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/debug/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/get-qodo-rules/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/install-extension/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/qodo-pr-resolver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/uninstall/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/uninstall-extension/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/update-claudeclaw/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/update-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/use-local-whisper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
skills/x-integration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
1395af4ed2b9 → 1395af4ed2b9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 1395af4ed2b9
No earlier version was observed for comparison.
Verified commit 1395af4ed2b9be6dd6dc35a3c6596d0eaa80d753
git clone --filter=blob:none --no-checkout https://github.com/sbusso/claudeclaw.git .hotskills/sbusso-claudeclaw && git -C .hotskills/sbusso-claudeclaw checkout --detach 1395af4ed2b9be6dd6dc35a3c6596d0eaa80d753
# Copy each selected skill directory from .hotskills/sbusso-claudeclaw into .claude/skills/<skill-name>/Heat
0.4- 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
- agent-browser
agent/skills/agent-browser - add-compact
skills/add-compact - add-discord
skills/add-discord - add-gmail
skills/add-gmail - add-image-vision
skills/add-image-vision - add-ollama-tool
skills/add-ollama-tool - add-parallel
skills/add-parallel - add-pdf-reader
skills/add-pdf-reader - add-qmd
skills/add-qmd - add-reactions
skills/add-reactions - add-telegram
skills/add-telegram - add-telegram-swarm
skills/add-telegram-swarm - add-voice-transcription
skills/add-voice-transcription - add-whatsapp
skills/add-whatsapp - convert-to-apple-container
skills/convert-to-apple-container - customize
skills/customize - debug
skills/debug - get-qodo-rules
skills/get-qodo-rules - install-extension
skills/install-extension - qodo-pr-resolver
skills/qodo-pr-resolver - setup
skills/setup - uninstall
skills/uninstall - uninstall-extension
skills/uninstall-extension - update-claudeclaw
skills/update-claudeclaw - update-skills
skills/update-skills - use-local-whisper
skills/use-local-whisper - x-integration
skills/x-integration
How it works
agent-browser
When your agent uses it
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,104 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
- Quick start
- Core workflow
- Commands
- Example: Form submission
- Example: Data extraction
Files
../../../.claude-plugin/plugin.jsonasset498 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytesSKILL.mdcore4,828 bytes
Read SKILL.md
# Browser Automation with agent-browser
## Quick start
```bash
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
```
## Core workflow
View the complete source on GitHubadd-compact
When your agent uses it
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,676 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Verify
- Security Constraints
- What This Does NOT Do
- Troubleshooting
Files
SKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytesSKILL.mdcore7,192 bytes
Read SKILL.md
# Add /compact Command
Adds a `/compact` session command that compacts conversation history to fight context rot in long-running sessions. Uses the Claude Agent SDK's built-in `/compact` slash command — no synthetic system prompts.
**Session contract:** `/compact` keeps the same logical session alive. The SDK returns a new session ID after compaction (via the `init` system message), which the agent-runner forwards to the orchestrator as `newSessionId`. No destructive reset occurs — the agent retains summarized context.
## Phase 1: Pre-flight
Check if `src/session-commands.ts` exists:
```bash
test -f src/session-commands.ts && echo "Already applied" || echo "Not applied"
```
View the complete source on GitHubadd-discord
When your agent uses it
Add Discord bot channel integration to ClaudeClaw.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
1,566 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Setup
- Phase 4: Registration
- Phase 5: Verify
- Troubleshooting
- After Setup
Files
SKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytesSKILL.mdcore6,338 bytes
Read SKILL.md
# Add Discord Channel
This skill adds Discord support to ClaudeClaw, then walks through interactive setup.
## Phase 1: Pre-flight
### Check if already applied
Check if `src/channels/discord.ts` exists. If it does, skip to Phase 3 (Setup). The code changes are already in place.
### Ask the user
Use `AskUserQuestion` to collect configuration:
View the complete source on GitHubadd-gmail
When your agent uses it
Add Gmail integration to ClaudeClaw. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
1,999 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Setup
- Phase 4: Verify
- Troubleshooting
- Removal
Files
SKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytesSKILL.mdcore7,690 bytes
Read SKILL.md
# Add Gmail Integration
This skill adds Gmail support to ClaudeClaw — either as a tool (read, send, search, draft) or as a full channel that polls the inbox.
## Phase 1: Pre-flight
### Check if already applied
Check if `src/channels/gmail.ts` exists. If it does, skip to Phase 3 (Setup). The code changes are already in place.
### Ask the user
Use `AskUserQuestion`:
View the complete source on GitHubadd-image-vision
When your agent uses it
Add image vision to ClaudeClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
779 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Configure
- Phase 4: Verify
- Troubleshooting
Files
SKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytesSKILL.mdcore3,148 bytes
Read SKILL.md
# Image Vision Skill
Adds the ability for ClaudeClaw agents to see and understand images sent via WhatsApp. Images are downloaded, resized with sharp, saved to the group workspace, and passed to the agent as base64-encoded multimodal content blocks.
## Phase 1: Pre-flight
1. Check if `src/image.ts` exists — skip to Phase 3 if already applied
2. Confirm `sharp` is installable (native bindings require build tools)
**Prerequisite:** WhatsApp must be installed first (`skill/whatsapp` merged). This skill modifies WhatsApp channel files.
## Phase 2: Apply Code Changes
### Ensure WhatsApp fork remoteView the complete source on GitHubadd-ollama-tool
When your agent uses it
Add Ollama MCP server so the container agent can call local models for cheaper/faster tasks like summarization, translation, or general queries.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
1,194 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Configure
- Phase 4: Verify
- Troubleshooting
Files
SKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytesSKILL.mdcore4,525 bytes
Read SKILL.md
# Add Ollama Integration
This skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models.
Tools added:
- `ollama_list_models` — lists installed Ollama models
- `ollama_generate` — sends a prompt to a specified model and returns the response
## Phase 1: Pre-flight
### Check if already applied
Check if `agent/runner/src/ollama-mcp-stdio.ts` exists. If it does, skip to Phase 3 (Configure).
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
2,342 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
- What This Adds
- Prerequisites
- Implementation Steps
- Troubleshooting
- Uninstalling
Files
SKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytesSKILL.mdcore9,094 bytes
Read SKILL.md
# Add Parallel AI Integration
Adds Parallel AI MCP integration to ClaudeClaw for advanced web research capabilities.
## What This Adds
- **Quick Search** - Fast web lookups using Parallel Search API (free to use)
- **Deep Research** - Comprehensive analysis using Parallel Task API (asks permission)
- **Non-blocking Design** - Uses ClaudeClaw scheduler for result polling (no container blocking)
## Prerequisites
User must have:
1. Parallel AI API key from https://platform.parallel.ai
2. ClaudeClaw already set up and runningView the complete source on GitHubadd-pdf-reader
When your agent uses it
Add PDF reading to ClaudeClaw agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
763 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Verify
- Troubleshooting
Files
SKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytesSKILL.mdcore3,071 bytes
Read SKILL.md
# Add PDF Reader
Adds PDF reading capability to all container agents using poppler-utils (pdftotext/pdfinfo). PDFs sent as WhatsApp attachments are auto-downloaded to the group workspace.
## Phase 1: Pre-flight
1. Check if `agent/skills/pdf-reader/pdf-reader` exists — skip to Phase 3 if already applied
2. Confirm WhatsApp is installed first (`skill/whatsapp` merged). This skill modifies WhatsApp channel files.
## Phase 2: Apply Code Changes
### Ensure WhatsApp fork remote
```bashView the complete source on GitHubadd-qmd
When your agent uses it
Add QMD (Query Markup Documents) as an advanced memory search backend. Upgrades the built-in grep-based memory_search with hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed. Triggers on "add qmd", "qmd memory", "semantic memory search", "upgrade memory".
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
613 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
- Prerequisites
- What This Skill Does
- Implementation Notes
- Not Implemented Yet
Files
SKILL.mdcore2,516 bytesSKILL.mdcore2,516 bytes
Read SKILL.md
# Add QMD Memory Backend
QMD (https://github.com/tobi/qmd) is a local search engine for markdown files. It combines BM25 keyword search, vector semantic search, and LLM re-ranking — all running on-device via node-llama-cpp with GGUF models.
This skill upgrades ClaudeClaw's built-in grep-based `memory_search` MCP tool with QMD's hybrid search, giving agents much better recall across large memory collections.
## Prerequisites
- ClaudeClaw with memory tools already working (memory_search, memory_save, memory_get)
- ~2GB disk space for GGUF embedding + reranking models (downloaded on first run)
- Node.js 20+
## What This Skill Does
View the complete source on GitHubadd-reactions
When your agent uses it
Add WhatsApp emoji reaction support — receive, send, store, and search reactions.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
798 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Verify
- Troubleshooting
Files
SKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytesSKILL.mdcore3,249 bytes
Read SKILL.md
# Add Reactions
This skill adds emoji reaction support to ClaudeClaw's WhatsApp channel: receive and store reactions, send reactions from the container agent via MCP tool, and query reaction history from SQLite.
## Phase 1: Pre-flight
### Check if already applied
Check if `src/status-tracker.ts` exists:
```bash
test -f src/status-tracker.ts && echo "Already applied" || echo "Not applied"
```
View the complete source on GitHubadd-telegram
When your agent uses it
Add Telegram as a channel. Can replace WhatsApp entirely or run alongside it. Also configurable as a control-only channel (triggers actions) or passive channel (receives notifications only).
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,836 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Setup
- Phase 4: Registration
- Phase 5: Verify
- Troubleshooting
- After Setup
- Agent Swarms (Teams)
- Removal
Files
SKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytesSKILL.mdcore6,985 bytes
Read SKILL.md
# Add Telegram Channel
This skill adds Telegram support to ClaudeClaw, then walks through interactive setup.
## Phase 1: Pre-flight
### Check if already applied
Check if `src/channels/telegram.ts` exists. If it does, skip to Phase 3 (Setup). The code changes are already in place.
### Ask the user
Use `AskUserQuestion` to collect configuration:
View the complete source on GitHubadd-telegram-swarm
When your agent uses it
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
3,755 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
- How It Works
- Prerequisites
- Implementation
- Architecture Notes
- Troubleshooting
- Removal
Files
SKILL.mdcore14,822 bytesSKILL.mdcore14,822 bytesSKILL.mdcore14,822 bytesSKILL.mdcore14,822 bytesSKILL.mdcore14,822 bytes
Read SKILL.md
# Add Agent Swarm to Telegram
This skill adds Agent Teams (Swarm) support to an existing Telegram channel. Each subagent in a team gets its own bot identity in the Telegram group, so users can visually distinguish which agent is speaking.
**Prerequisite**: Telegram must already be set up via the `/add-telegram` skill. If `src/channels/telegram.ts` does not exist or `TELEGRAM_BOT_TOKEN` is not configured, tell the user to run `/add-telegram` first.
## How It Works
- The **main bot** receives messages and sends lead agent responses (already set up by `/add-telegram`)
- **Pool bots** are send-only — each gets a Grammy `Api` instance (no polling)
- When a subagent calls `send_message` with a `sender` parameter, the host assigns a pool bot and renames it to match the sender's role
- Messages appear in Telegram from different bot identities
```View the complete source on GitHubadd-voice-transcription
When your agent uses it
Add voice message transcription to ClaudeClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,136 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Configure
- Phase 4: Verify
- Troubleshooting
Files
SKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytesSKILL.mdcore4,562 bytes
Read SKILL.md
# Add Voice Transcription
This skill adds automatic voice message transcription to ClaudeClaw's WhatsApp channel using OpenAI's Whisper API. When a voice note arrives, it is downloaded, transcribed, and delivered to the agent as `[Voice: <transcript>]`.
## Phase 1: Pre-flight
### Check if already applied
Check if `src/transcription.ts` exists. If it does, skip to Phase 3 (Configure). The code changes are already in place.
### Ask the user
Use `AskUserQuestion` to collect information:
View the complete source on GitHubadd-whatsapp
When your agent uses it
Add WhatsApp as a channel. Can replace other channels entirely or run alongside them. Uses QR code or pairing code for authentication.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
2,994 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
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Authentication
- Phase 4: Registration
- Phase 5: Verify
- Troubleshooting
- After Setup
- Removal
Files
SKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytesSKILL.mdcore11,421 bytes
Read SKILL.md
# Add WhatsApp Channel
This skill adds WhatsApp support to ClaudeClaw. It installs the WhatsApp channel code, dependencies, and guides through authentication, registration, and configuration.
## Phase 1: Pre-flight
### Check current state
Check if WhatsApp is already configured. If `store/auth/` exists with credential files, skip to Phase 4 (Registration) or Phase 5 (Verify).
```bash
ls store/auth/creds.json 2>/dev/null && echo "WhatsApp auth exists" || echo "No WhatsApp auth"
```
View the complete source on GitHubconvert-to-apple-container
When your agent uses it
Switch from Docker to Apple Container for macOS-native container isolation. Use when the user wants Apple Container instead of Docker, or is setting up on macOS and prefers the native runtime. Triggers on "apple container", "convert to apple container", "switch to apple container", or "use apple container".
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,363 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
- Prerequisites
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Verify
- Troubleshooting
- Summary of Changed Files
Files
SKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytesSKILL.mdcore5,683 bytes
Read SKILL.md
# Convert to Apple Container
This skill switches ClaudeClaw's container runtime from Docker to Apple Container (macOS-only). It uses the skills engine for deterministic code changes, then walks through verification.
**What this changes:**
- Container runtime binary: `docker` → `container`
- Mount syntax: `-v path:path:ro` → `--mount type=bind,source=...,target=...,readonly`
- Startup check: `docker info` → `container system status` (with auto-start)
- Orphan detection: `docker ps --filter` → `container ls --format json`
- Build script default: `docker` → `container`
- Dockerfile entrypoint: `.env` shadowing via `mount --bind` inside the container (Apple Container only supports directory mounts, not file mounts like Docker's `/dev/null` overlay)
- Container runner: main-group containers start as root for `mount --bind`, then drop privileges via `setpriv`
**What stays the same:**View the complete source on GitHubcustomize
When your agent uses it
Add new capabilities or modify ClaudeClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,579 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
- Mode Detection
- Workflow
- Key Files
- Common Customization Patterns
- After Changes
- Example Interaction
Files
SKILL.mdcore6,496 bytesSKILL.mdcore6,496 bytesSKILL.mdcore6,496 bytes
Read SKILL.md
# ClaudeClaw Customization
This skill helps users add capabilities or modify behavior. Use AskUserQuestion to understand what they want before making changes.
## Mode Detection
Check if `.claude-plugin/plugin.json` exists in cwd:
```bash
cat .claude-plugin/plugin.json 2>/dev/null | grep '"name": "claudeclaw"' && echo "DEVELOPER_MODE" || echo "PLUGIN_MODE"
```
If plugin mode, offer the user a choice via AskUserQuestion:
- **Fork to developer mode (Recommended)** — Clone the repo into a new directory, copy state, full self-improvement and customization
- **Continue in plugin mode** — Limited to channel setup and config changes (no code editing)View the complete source on GitHubdebug
When your agent uses it
Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and common issues.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
3,389 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
- Architecture Overview
- Log Locations
- Enabling Debug Logging
- Common Issues
- Manual Container Testing
- SDK Options Reference
- Rebuilding After Changes
- Checking Container Image
- Session Persistence
- IPC Debugging
- Sandbox Runtime Debugging
- Quick Diagnostic Script
Files
SKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytesSKILL.mdcore13,472 bytes
Read SKILL.md
# ClaudeClaw Container & Sandbox Debugging
This guide covers debugging the agent execution system (container and sandbox runtimes).
## Architecture Overview
```
Host (macOS) Container (Linux VM)
─────────────────────────────────────────────────────────────
src/orchestrator/container-runner.ts agent/runner/
│ │
│ spawns container │ runs Claude Agent SDK
│ with volume mounts │ with MCP servers
│ │View the complete source on GitHubget-qodo-rules
When your agent uses it
Loads org- and repo-level coding rules from Qodo before code tasks begin, ensuring all generation and modification follows team standards. Use before any code generation or modification task when rules are not already loaded. Invoke when user asks to write, edit, refactor, or review code, or when starting implementation planning.
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
1,329 tokensWhen the skill is activated
Reference documents
810 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Workflow
- How Scope Levels Work
- Configuration
- Common Mistakes
Files
SKILL.mdcore5,560 bytesreferences/output-format.mddoc842 bytesreferences/pagination.mddoc1,289 bytesreferences/repository-scope.mddoc964 bytes
Read SKILL.md
# Get Qodo Rules Skill
## Description
Fetches repository-specific coding rules from the Qodo platform API before code generation or modification tasks. Rules include security requirements, coding standards, quality guidelines, and team conventions that must be applied during code generation.
**Use** before any code generation or modification task when rules are not already loaded. Invoke when user asks to write, edit, refactor, or review code, or when starting implementation planning.
**Skip** if "Qodo Rules Loaded" already appears in conversation context
---
## Workflow
### Step 1: Check if Rules Already Loaded
View the complete source on GitHubinstall-extension
When your agent uses it
Install a ClaudeClaw extension (e.g., slack, triage)
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
552 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
- Usage
- Flow
Files
SKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytesSKILL.mdcore1,959 bytes
Read SKILL.md
# Install Extension
Install a ClaudeClaw extension from GitHub.
## Usage
```
/install slack
/install triage
```
## Flow
### 1. Validate inputView the complete source on GitHubqodo-pr-resolver
When your agent uses it
Review and resolve PR issues with Qodo - get AI-powered code review issues and fix them interactively (GitHub, GitLab, Bitbucket, Azure DevOps)
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
3,937 tokensWhen the skill is activated
Reference documents
1,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Understanding Qodo Reviews
- Instructions
Files
SKILL.mdcore16,168 bytesSKILL.mdcore16,168 bytesresources/providers.mddoc6,861 bytes
Read SKILL.md
# Qodo PR Resolver
Fetch Qodo review issues for your current branch's PR/MR, fix them interactively or in batch, and reply to each inline comment with the decision. Supports GitHub, GitLab, Bitbucket, and Azure DevOps.
## Prerequisites
### Required Tools:
- **Git** - For branch operations
- **Git Provider CLI** - One of: `gh` (GitHub), `glab` (GitLab), `bb` (Bitbucket), or `az` (Azure DevOps)
**Installation and authentication details:** See [providers.md](./resources/providers.md) for provider-specific setup instructions.
### Required Context:
- Must be in a git repositoryView the complete source on GitHubsetup
When your agent uses it
Run initial ClaudeClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure claudeclaw", or first-time setup requests.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
4,914 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
- Mode Detection
- 0. Git & Fork Setup (Developer mode only)
- 1. Bootstrap (Node.js + Dependencies)
- 2. Check Environment
- 3. Container Runtime
- 4. Claude Authentication (No Script)
- 5. Set Up Channels
- 6. Mount Allowlist
- 7. Start Service
- 8. Verify
- 9. Post-Setup Audit
- Troubleshooting
Files
SKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytesSKILL.mdcore19,058 bytes
Read SKILL.md
# ClaudeClaw Setup
Run setup steps automatically. Only pause when user action is required (channel authentication, configuration choices). Setup uses `bash setup.sh` for bootstrap, then `npx tsx setup/index.ts --step <name>` for all other steps. Steps emit structured status blocks to stdout. Verbose logs go to `logs/setup.log`.
**Principle:** When something is broken or missing, fix it. Don't tell the user to go fix it themselves unless it genuinely requires their manual action (e.g. authenticating a channel, pasting a secret token). If a dependency is missing, install it. If a service won't start, diagnose and repair. Ask the user for permission when needed, then do the work.
**UX Note:** Use `AskUserQuestion` for all user-facing questions.
## Mode Detection
Before any steps, detect the execution mode:
```bash
cat .claude-plugin/plugin.json 2>/dev/null | grep '"name": "claudeclaw"' && echo "DEVELOPER_MODE" || echo "PLUGIN_MODE"View the complete source on GitHubuninstall
When your agent uses it
Stop and remove the ClaudeClaw background service and agents for this instance
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
624 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
- Flow
Files
SKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytes
Read SKILL.md
# Uninstall Service
Stop and remove the ClaudeClaw background service for the current instance. Data (store/, groups/, .env) is preserved — only the service unit is removed.
## Flow
### 1. Detect OS and find service
**macOS:**
```bash
DIRNAME=$(basename "$(pwd)")
PLIST_NAME="com.claudeclaw.${DIRNAME}"
PLIST_PATH="$HOME/Library/LaunchAgents/${PLIST_NAME}.plist"
```View the complete source on GitHubuninstall-extension
When your agent uses it
Uninstall a ClaudeClaw extension
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
326 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
- Usage
- Flow
Files
SKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytesSKILL.mdcore1,166 bytes
Read SKILL.md
# Uninstall Extension
Remove an installed ClaudeClaw extension.
## Usage
```
/uninstall slack
/uninstall triage
```
## Flow
### 1. ValidateView the complete source on GitHubupdate-claudeclaw
When your agent uses it
Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
2,581 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
- How it works
- Rollback
- Token usage
Files
SKILL.mdcore10,367 bytes
Read SKILL.md
# About
Your ClaudeClaw fork drifts from upstream as you customize it. This skill pulls upstream changes into your install without losing your modifications.
Run `/update-claudeclaw` in Claude Code.
## How it works
**Preflight**: checks for clean working tree (`git status --porcelain`). If `upstream` remote is missing, asks you for the URL (defaults to `https://github.com/sbusso/claudeclaw.git`) and adds it. Detects the upstream branch name (`main` or `master`).
**Backup**: creates a timestamped backup branch and tag (`backup/pre-update-<hash>-<timestamp>`, `pre-update-<hash>-<timestamp>`) before touching anything. Safe to run multiple times.
**Preview**: runs `git log` and `git diff` against the merge base to show upstream changes since your last sync. Groups changed files into categories:
- **Skills** (`.claude/skills/`): unlikely to conflict unless you edited an upstream skillView the complete source on GitHubupdate-skills
When your agent uses it
Check for and apply updates to installed skill branches from upstream.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,197 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
- How it works
Files
SKILL.mdcore5,071 bytes
Read SKILL.md
# About
Skills are distributed as git branches (`skill/*`). When you install a skill, you merge its branch into your repo. This skill checks upstream for newer commits on those skill branches and helps you update.
Run `/update-skills` in Claude Code.
## How it works
**Preflight**: checks for clean working tree and upstream remote.
**Detection**: fetches upstream, lists all `upstream/skill/*` branches, determines which ones you've previously merged (via merge-base), and checks if any have new commits.
**Selection**: presents a list of skills with available updates. You pick which to update.
View the complete source on GitHubuse-local-whisper
When your agent uses it
Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,370 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
- Prerequisites
- Phase 1: Pre-flight
- Phase 2: Apply Code Changes
- Phase 3: Verify
- Configuration
- Troubleshooting
Files
SKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytesSKILL.mdcore5,107 bytes
Read SKILL.md
# Use Local Whisper
Switches voice transcription from OpenAI's Whisper API to local whisper.cpp. Runs entirely on-device — no API key, no network, no cost.
**Channel support:** Currently WhatsApp only. The transcription module (`src/transcription.ts`) uses Baileys types for audio download. Other channels (Telegram, Discord, etc.) would need their own audio-download logic before this skill can serve them.
**Note:** The Homebrew package is `whisper-cpp`, but the CLI binary it installs is `whisper-cli`.
## Prerequisites
- `voice-transcription` skill must be applied first (WhatsApp channel)
- macOS with Apple Silicon (M1+) recommended
- `whisper-cpp` installed: `brew install whisper-cpp` (provides the `whisper-cli` binary)
- `ffmpeg` installed: `brew install ffmpeg`View the complete source on GitHubx-integration
When your agent uses it
X (Twitter) integration for ClaudeClaw. Post tweets, like, reply, retweet, and quote. Use for setup, testing, or troubleshooting X functionality. Triggers on "setup x", "x integration", "twitter", "post tweet", "tweet".
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
3,210 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
- Features
- Prerequisites
- Quick Start
- Configuration
- Architecture
- Setup
- Usage via WhatsApp
- Testing
- Troubleshooting
- Security
Scripts executed separately
agent.tshost.tslib/browser.tslib/config.tsscripts/like.tsscripts/post.tsscripts/quote.tsscripts/reply.tsscripts/retweet.tsscripts/setup.ts
Files
SKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesSKILL.mdcore12,780 bytesagent.tsruns7,495 byteshost.tsruns4,521 byteslib/browser.tsruns4,066 byteslib/config.tsruns1,507 bytesscripts/like.tsruns1,662 bytesscripts/post.tsruns2,300 bytesscripts/quote.tsruns2,815 bytesscripts/reply.tsruns2,557 bytesscripts/retweet.tsruns2,006 bytesscripts/setup.tsruns2,782 bytes
Read SKILL.md
# X (Twitter) Integration
Browser automation for X interactions via WhatsApp.
> **Compatibility:** ClaudeClaw v1.0.0. Directory structure may change in future versions.
## Features
| Action | Tool | Description |
|--------|------|-------------|
| Post | `x_post` | Publish new tweets |
| Like | `x_like` | Like any tweet |
| Reply | `x_reply` | Reply to tweets |
| Retweet | `x_retweet` | Retweet without comment |View the complete source on GitHubSkills included
- agent-browser
- add-compact
- add-discord
- add-gmail
- add-image-vision
- add-ollama-tool
- add-pdf-reader
- add-qmd
- add-reactions
- add-telegram
- add-telegram-swarm
- add-voice-transcription
- add-whatsapp
- convert-to-apple-container
- customize
- debug
- get-qodo-rules
- install-extension
- qodo-pr-resolver
- setup
- uninstall
- uninstall-extension
- update-claudeclaw
- update-skills
- use-local-whisper
- x-integration
Repository facts
- License
- MIT
- Created
- Mar 22, 2026
- Last pushed
- Aug 12, 2026
- Forks
- 61
- Open issues
- 1
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 271 notes
agent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagent/skills/agent-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/add-compact/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: get-qodo-rules/SKILL.md:1
- 34 dangerous shell commandsin 9 files: setup/SKILL.md:105 add-whatsapp/SKILL.md:99 add-gmail/SKILL.md:133 and 6 more
- 144 network referencesin 33 files: setup/SKILL.md:69 x-integration/agent.ts:111 add-parallel/SKILL.md:13 and 30 more
- No hidden or obfuscated text
- 8 instruction override signalsin 1 file: debug/SKILL.md:79
- 10 executable scriptsin 10 files: x-integration/agent.ts:1 x-integration/host.ts:1 x-integration/lib/browser.ts:1 and 7 more
- 75 references to secretsin 15 files: add-parallel/SKILL.md:41 x-integration/SKILL.md:35 setup/SKILL.md:38 and 12 more
- No requests to vote in Hot
Show all 272 signals by file
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "sbusso", "url": "https://github.com/sbusso" - Network accessline 6
"name": "sbusso", "url": "https://github.com/sbusso" }, - Network accessline 7
"url": "https://github.com/sbusso" - Network accessline 8
}, "repository": "https://github.com/sbusso/claudeclaw", "license": "MIT", - Network accessline 9
"repository": "https://github.com/sbusso/claudeclaw",
agent/skills/agent-browser/SKILL.md
- Network accessline 107
# Login once agent-browser open https://app.example.com/login - Network accessline 108
agent-browser open https://app.example.com/login - Network accessline 116
# Later: load saved state agent-browser state load auth.json agent-browser open https://app.example.com/dashboard - Network accessline 118
agent-browser open https://app.example.com/dashboard - Access to secretsline 124
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Dangerous shell operationline 134
agent-browser eval "document.title" # Run JavaScript - Network accessline 140
agent-browser open https://example.com/form - Network accessline 154
agent-browser open https://example.com/products
skills/add-discord/SKILL.md
- Network accessline 35
git remote add discord https://github.com/qwibitai/claudeclaw-discord.git - Network accessline 74
> I need you to create a Discord bot: > > 1. Go to the [Discord Developer Portal](https://discord.com/developers/applications) - Network accessline 75
> > 1. Go to the [Discord Developer Portal](https://discord.com/developers/applications) > 2. Click **New Application** and give it a name (e.g., "Andy Assistant") - Network accessline 76
> 1. Go to the [Discord Developer Portal](https://discord.com/developers/applications) - Access to secretsline 103
[Credential-related source omitted] - Network accessline 185
If the bot connects but can't read messages, ensure: 1. Go to [Discord Developer Portal](https://discord.com/developers/applications) - Network accessline 186
1. Go to [Discord Developer Portal](https://discord.com/developers/applications)
skills/add-gmail/SKILL.md
- Network accessline 36
git remote add gmail https://github.com/qwibitai/claudeclaw-gmail.git - Network accessline 94
> I need you to set up Google Cloud OAuth credentials: > > 1. Open https://console.cloud.google.com — create a new project or select existing - Network accessline 95
> > 1. Open https://console.cloud.google.com — create a new project or select existing > 2. Go to **APIs & Services > Library**, search "Gmail API", click **Enable** - Network accessline 96
> 1. Open https://console.cloud.google.com — create a new project or select existing - Dangerous shell operationline 133
rm -r data/sessions/*/agent-runner-src 2>/dev/null || true - Dangerous shell operationline 189
rm ~/.gmail-mcp/credentials.json - Dangerous shell operationline 210
4. Clear stale agent-runner copies: `rm -r data/sessions/*/agent-runner-src 2>/dev/null || true` - Dangerous shell operationline 221
7. Clear stale agent-runner copies: `rm -r data/sessions/*/agent-runner-src 2>/dev/null || true`
skills/add-image-vision/SKILL.md
- Network accessline 28
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git
skills/add-ollama-tool/SKILL.md
- Network accessline 28
If Ollama is not installed, direct the user to https://ollama.com/download. - Network accessline 51
git remote add upstream https://github.com/sbusso/claudeclaw.git - Network accessline 94
By default, the MCP server connects to `http://host.docker.internal:11434` (Docker Desktop) with a fallback to `localhost`. To use a custom Ollama host, add to `.env`: - Network accessline 97
OLLAMA_HOST=http://your-ollama-host:11434 - Network accessline 149
1. Verify Ollama is running: `ollama list` 2. Check Docker can reach the host: `docker run --rm curlimages/curl curl -s http://host.docker.internal:11434/api/tags` - Network accessline 150
2. Check Docker can reach the host: `docker run --rm curlimages/curl curl -s http://host.docker.internal:11434/api/tags`
skills/add-parallel/SKILL.md
- Network accessline 13
User must have: 1. Parallel AI API key from https://platform.parallel.ai - Network accessline 14
1. Parallel AI API key from https://platform.parallel.ai - Network accessline 29
**If they need one:** Tell them: > 1. Go to https://platform.parallel.ai - Network accessline 30
Tell them: > 1. Go to https://platform.parallel.ai > 2. Sign up or log in - Network accessline 31
> 1. Go to https://platform.parallel.ai - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Network accessline 99
mcpServers['parallel-search'] = { type: 'http', // REQUIRED: Must specify type for HTTP MCP servers url: 'https://search-mcp.parallel.ai/mcp', - Network accessline 100
type: 'http', // REQUIRED: Must specify type for HTTP MCP servers url: 'https://search-mcp.parallel.ai/mcp', headers: { - Network accessline 101
url: 'https://search-mcp.parallel.ai/mcp', - Network accessline 106
mcpServers['parallel-task'] = { type: 'http', // REQUIRED: Must specify type for HTTP MCP servers url: 'https://task-mcp.parallel.ai/mcp', - Network accessline 107
type: 'http', // REQUIRED: Must specify type for HTTP MCP servers url: 'https://task-mcp.parallel.ai/mcp', headers: { - Network accessline 108
url: 'https://task-mcp.parallel.ai/mcp', - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 271
[Credential-related source omitted] - Access to secretsline 275
[Credential-related source omitted] - Access to secretsline 276
[Credential-related source omitted] - Access to secretsline 288
[Credential-related source omitted]
skills/add-pdf-reader/SKILL.md
- Network accessline 26
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git
skills/add-qmd/SKILL.md
- Network accessline 8
QMD (https://github.com/tobi/qmd) is a local search engine for markdown files. It combines BM25 keyword search, vector semantic search, and LLM re-ranking — all running on-device via node-llama-cpp with GGUF models.
skills/add-reactions/SKILL.md
- Network accessline 33
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git
skills/add-telegram-swarm/SKILL.md
skills/add-telegram/SKILL.md
- Network accessline 35
git remote add telegram https://github.com/qwibitai/claudeclaw-telegram.git - Access to secretsline 97
[Credential-related source omitted] - Network accessline 188
[Credential-related source omitted] - Network accessline 189
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted]
skills/add-voice-transcription/SKILL.md
- Network accessline 22
If yes, collect it now. If no, direct them to create one at https://platform.openai.com/api-keys. - Network accessline 37
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git - Access to secretsline 56
[Credential-related source omitted] - Network accessline 76
> I need you to create an OpenAI API key: > > 1. Go to https://platform.openai.com/api-keys - Network accessline 77
> > 1. Go to https://platform.openai.com/api-keys > 2. Click "Create new secret key" - Network accessline 78
> 1. Go to https://platform.openai.com/api-keys - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Network accessline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Network accessline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Network accessline 143
Check logs for the specific error. Common causes: - Network timeout — transient, will work on next message - Invalid API key — regenerate at https://platform.openai.com/api-keys - Network accessline 144
- Network timeout — transient, will work on next message - Invalid API key — regenerate at https://platform.openai.com/api-keys - Rate limiting — wait and retry - Network accessline 145
- Invalid API key — regenerate at https://platform.openai.com/api-keys
skills/add-whatsapp/SKILL.md
- Network accessline 58
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git - Dangerous shell operationline 99
rm -rf store/auth/ - Dangerous shell operationline 138
rm -f store/pairing-code.txt && npx tsx setup/index.ts --step whatsapp-auth -- --method pairing-code --phone <their-phone-number> > /tmp/wa-auth.log 2>&1 & - Access to secretsline 176
[Credential-related source omitted] - Dangerous shell operationline 301
rm -rf store/auth/ && npx tsx src/channels/whatsapp-auth.ts - Dangerous shell operationline 309
rm -rf store/auth/ && npx tsx src/channels/whatsapp-auth.ts --pairing-code --phone <phone> - Dangerous shell operationline 320
rm -rf store/auth/ && npx tsx setup/index.ts --step whatsapp-auth -- --method qr-browser - Dangerous shell operationline 371
1. Delete auth credentials: `rm -rf store/auth/` - Access to secretsline 373
[Credential-related source omitted]
skills/convert-to-apple-container/SKILL.md
- Network accessline 33
If not installed: - Download from https://github.com/apple/container/releases - Network accessline 34
- Download from https://github.com/apple/container/releases - Network accessline 61
git remote add upstream https://github.com/sbusso/claudeclaw.git - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Dangerous shell operationline 117
rm -rf /tmp/test-ro - Dangerous shell operationline 130
cat /tmp/test-rw/new.txt && rm -rf /tmp/test-rw - Network accessline 148
**Apple Container not found:** - Download from https://github.com/apple/container/releases - Network accessline 149
- Download from https://github.com/apple/container/releases - Access to secretsline 175
[Credential-related source omitted] - Access to secretsline 176
[Credential-related source omitted]
skills/customize/SKILL.md
- Network accessline 30
- macOS: `launchctl unload ~/Library/LaunchAgents/com.claudeclaw.<dirname>.plist` - Linux: `systemctl --user stop claudeclaw-<dirname>` 4. Clone: `git clone https://github.com/<username>/claudeclaw.git <clone-path>` - Network accessline 31
- Linux: `systemctl --user stop claudeclaw-<dirname>` 4. Clone: `git clone https://github.com/<username>/claudeclaw.git <clone-path>` 5. Copy state from current data directory: `cp -r store groups .env <clone-path>/` - Network accessline 32
4. Clone: `git clone https://github.com/<username>/claudeclaw.git <clone-path>` - Access to secretsline 33
[Credential-related source omitted] - Network accessline 35
7. Clear stale sessions: `sqlite3 <clone-path>/store/messages.db "DELETE FROM sessions"` 8. Install and build: `cd <clone-path> && npm install && npm run build` 9. Set up upstream: `cd <clone-path> && git remote add upstream https://github. - Network accessline 36
8. Install and build: `cd <clone-path> && npm install && npm run build` 9. Set up upstream: `cd <clone-path> && git remote add upstream https://github.com/sbusso/claudeclaw.git` 10. Run service setup: `cd <clone-path> && npx tsx setup/index - Network accessline 37
9. Set up upstream: `cd <clone-path> && git remote add upstream https://github.com/sbusso/claudeclaw.git`
skills/debug/SKILL.md
- Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Dangerous shell operationline 79
--dangerously-skip-permissions cannot be used with root/sudo privileges - Instruction override signalline 79
--dangerously-skip-permissions cannot be used with root/sudo privileges - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Access to secretsline 184
[Credential-related source omitted] - Instruction override signalline 199
claudeclaw-agent:latest -c ' export $(cat /workspace/env-dir/env | xargs) claude -p "Say hello" --dangerously-skip-permissions --allowedTools "" - Instruction override signalline 200
export $(cat /workspace/env-dir/env | xargs) claude -p "Say hello" --dangerously-skip-permissions --allowedTools "" ' - Instruction override signalline 201
claude -p "Say hello" --dangerously-skip-permissions --allowedTools "" - Instruction override signalline 219
allowedTools: ['Bash', 'Read', 'Write', ...], permissionMode: 'bypassPermissions', allowDangerouslySkipPermissions: true, // Required with bypassPermissions - Instruction override signalline 220
permissionMode: 'bypassPermissions', allowDangerouslySkipPermissions: true, // Required with bypassPermissions settingSources: ['project'], - Instruction override signalline 221
allowDangerouslySkipPermissions: true, // Required with bypassPermissions - Instruction override signalline 228
**Important:** `allowDangerouslySkipPermissions: true` is required when using `permissionMode: 'bypassPermissions'`. Without it, Claude Code exits with code 1. - Dangerous shell operationline 276
rm -rf data/sessions/ - Dangerous shell operationline 279
rm -rf data/sessions/{groupFolder}/.claude/ - Access to secretsline 351
[Credential-related source omitted] - Access to secretsline 361
[Credential-related source omitted] - Dangerous shell operationline 367
docker info &>/dev/null && echo "OK" || echo "NOT RUNNING - start Docker Desktop (macOS) or sudo systemctl start docker (Linux)"
skills/get-qodo-rules/SKILL.md
skills/get-qodo-rules/references/pagination.md
skills/get-qodo-rules/references/repository-scope.md
skills/install-extension/SKILL.md
skills/qodo-pr-resolver/resources/providers.md
- Network accessline 30
**CLI:** `gh` - **Install:** `brew install gh` or [cli.github.com](https://cli.github.com/) - Network accessline 31
- **Install:** `brew install gh` or [cli.github.com](https://cli.github.com/) - Network accessline 40
**CLI:** `glab` - **Install:** `brew install glab` or [glab.readthedocs.io](https://glab.readthedocs.io/) - Network accessline 41
- **Install:** `brew install glab` or [glab.readthedocs.io](https://glab.readthedocs.io/) - Network accessline 50
**CLI:** `bb` or API access - **Install:** See [bitbucket.org/product/cli](https://bitbucket.org/product/cli) - Network accessline 51
- **Install:** See [bitbucket.org/product/cli](https://bitbucket.org/product/cli) - Network accessline 59
**CLI:** `az` with DevOps extension - **Install:** `brew install azure-cli` or [docs.microsoft.com/cli/azure](https://docs.microsoft.com/cli/azure) - Network accessline 60
- **Install:** `brew install azure-cli` or [docs.microsoft.com/cli/azure](https://docs.microsoft.com/cli/azure) - Network accessline 61
- **Install extension:** `az extension add --name azure-devops` - **Authenticate:** `az login` then `az devops configure --defaults organization=https://dev.azure.com/yourorg project=yourproject` - **Verify:** - Network accessline 62
- **Authenticate:** `az login` then `az devops configure --defaults organization=https://dev.azure.com/yourorg project=yourproject`
skills/setup/SKILL.md
- Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Network accessline 69
git remote rename origin upstream git remote add origin https://github.com/<their-username>/claudeclaw.git - Network accessline 70
git remote add origin https://github.com/<their-username>/claudeclaw.git - Network accessline 77
git remote add upstream https://github.com/sbusso/claudeclaw.git - Network accessline 84
git remote add upstream https://github.com/sbusso/claudeclaw.git - Network accessline 103
- If NODE_OK=false → Node.js is missing or too old. Use `AskUserQuestion: Would you like me to install Node.js 22?` If confirmed: - macOS: `brew install node@22` (if brew available) or install nvm then `nvm install 22` - Linux: `curl -f - Network accessline 104
- macOS: `brew install node@22` (if brew available) or install nvm then `nvm install 22` - Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm - After installing Node, re- - Dangerous shell operationline 105
- Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm - Network accessline 105
- Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm - Dangerous shell operationline 145
- DOCKER=installed_not_running → start Docker: `open -a Docker` (macOS) or `sudo systemctl start docker` (Linux). Wait 15s, re-check with `docker info`. - Network accessline 145
- DOCKER=installed_not_running → start Docker: `open -a Docker` (macOS) or `sudo systemctl start docker` (Linux). Wait 15s, re-check with `docker info`. - DOCKER=not_found → Use `AskUserQuestion: Docker is required for running agents. Would - Network accessline 146
- DOCKER=not_found → Use `AskUserQuestion: Docker is required for running agents. Would you like me to install it?` If confirmed: - macOS: install via `brew install --cask docker`, then `open -a Docker` and wait for it to start. If brew n - Network accessline 147
- macOS: install via `brew install --cask docker`, then `open -a Docker` and wait for it to start. If brew not available, direct to Docker Desktop download at https://docker.com/products/docker-desktop - Dangerous shell operationline 148
- Linux: install with `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER`. Note: user may need to log out/in for group membership. - Network accessline 148
- Linux: install with `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER`. Note: user may need to log out/in for group membership. - Access to secretsline 176
[Credential-related source omitted] - Access to secretsline 182
[Credential-related source omitted] - Dangerous shell operationline 238
**If FALLBACK=wsl_no_systemd:** WSL without systemd detected. Tell user they can either enable systemd in WSL (`echo -e "[boot]\nsystemd=true" | sudo tee /etc/wsl.conf` then restart WSL) or use the generated `start-claudeclaw.sh` wrapper. - Dangerous shell operationline 242
1. Immediate fix: `sudo setfacl -m u:$(whoami):rw /var/run/docker.sock` - Dangerous shell operationline 245
sudo mkdir -p /etc/systemd/system/docker.service.d - Dangerous shell operationline 246
sudo tee /etc/systemd/system/docker.service.d/socket-acl.conf << 'EOF' - Dangerous shell operationline 250
sudo systemctl daemon-reload - Network accessline 283
[Credential-related source omitted] - Network accessline 284
[Credential-related source omitted] - Access to secretsline 284
[Credential-related source omitted] - Dangerous shell operationline 285
[Credential-related source omitted] - Network accessline 285
[Credential-related source omitted] - Access to secretsline 285
[Credential-related source omitted] - Dangerous shell operationline 286
[Credential-related source omitted] - Network accessline 286
[Credential-related source omitted] - Access to secretsline 286
[Credential-related source omitted] - Access to secretsline 289
[Credential-related source omitted] - Access to secretsline 343
[Credential-related source omitted] - Access to secretsline 345
[Credential-related source omitted] - Dangerous shell operationline 372
**Container agent fails ("Claude Code process exited with code 1"):** Ensure the container runtime is running — `open -a Docker` (macOS Docker), `container system start` (Apple Container), or `sudo systemctl start docker` (Linux). Check con
skills/uninstall-extension/SKILL.md
- Dangerous shell operationline 50
rm -rf "$EXT_DIR"
skills/uninstall/SKILL.md
skills/update-claudeclaw/SKILL.md
- Network accessline 14
**Preflight**: checks for clean working tree (`git status --porcelain`). If `upstream` remote is missing, asks you for the URL (defaults to `https://github.com/sbusso/claudeclaw.git`) and adds it. Detects the upstream branch name (`main` or - Network accessline 69
- `git remote -v` If `upstream` is missing: - Ask the user for the upstream repo URL (default: `https://github.com/sbusso/claudeclaw.git`). - Network accessline 70
If `upstream` is missing: - Ask the user for the upstream repo URL (default: `https://github.com/sbusso/claudeclaw.git`). - Add it: `git remote add upstream <user-provided-url>` - Network accessline 71
- Ask the user for the upstream repo URL (default: `https://github.com/sbusso/claudeclaw.git`). - Add it: `git remote add upstream <user-provided-url>` - Then: `git fetch upstream --prune`
skills/update-skills/SKILL.md
skills/use-local-whisper/SKILL.md
- Network accessline 54
mkdir -p data/models curl -L -o data/models/ggml-base.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" - Network accessline 55
curl -L -o data/models/ggml-base.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" - Network accessline 71
git remote add whatsapp https://github.com/qwibitai/claudeclaw-whatsapp.git
skills/x-integration/SKILL.md
- Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 246
[Credential-related source omitted] - Access to secretsline 247
[Credential-related source omitted] - Access to secretsline 248
[Credential-related source omitted] - Access to secretsline 254
[Credential-related source omitted] - Network accessline 296
@Assistant like this tweet https://x.com/user/status/123 - Network accessline 298
@Assistant reply to https://x.com/user/status/123 with: Great post! - Network accessline 300
@Assistant retweet https://x.com/user/status/123 - Network accessline 302
@Assistant quote https://x.com/user/status/123 with comment: Interesting - Access to secretsline 324
[Credential-related source omitted] - Access to secretsline 330
[Credential-related source omitted] - Network accessline 336
[Credential-related source omitted] - Access to secretsline 336
[Credential-related source omitted] - Access to secretsline 351
[Credential-related source omitted] - Dangerous shell operationline 361
rm -f data/x-browser-profile/SingletonLock - Dangerous shell operationline 362
rm -f data/x-browser-profile/SingletonSocket - Dangerous shell operationline 363
[Credential-related source omitted] - Access to secretsline 363
[Credential-related source omitted]
skills/x-integration/agent.ts
- Executable scriptline 1
Executable file - Network accessline 111
Provide the tweet URL or tweet ID to like.`, { tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') - Network accessline 112
{ tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') }, - Network accessline 113
tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') - Network accessline 144
Provide the tweet URL and your reply content.`, { tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'), - Network accessline 145
{ tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'), content: z.string().max(280).describe('The reply content (max 280 characters)') - Network accessline 146
tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'), - Network accessline 179
Provide the tweet URL to retweet.`, { tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') - Network accessline 180
{ tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') }, - Network accessline 181
tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID') - Network accessline 212
Retweet with your own comment added.`, { tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'), - Network accessline 213
{ tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'), comment: z.string().max(280).describe('Your comment for the quote tweet (max 280 characters)') - Network accessline 214
tweet_url: z.string().describe('The tweet URL (e.g., https://x.com/user/status/123) or tweet ID'),
skills/x-integration/host.ts
- Executable scriptline 1
Executable file
skills/x-integration/lib/browser.ts
- Executable scriptline 1
Executable file - Network accessline 111
const tweetId = extractTweetId(tweetUrl); if (tweetId && !tweetUrl.startsWith('http')) { url = `https://x.com/i/status/${tweetId}`; - Network accessline 112
if (tweetId && !tweetUrl.startsWith('http')) { url = `https://x.com/i/status/${tweetId}`; } - Network accessline 113
url = `https://x.com/i/status/${tweetId}`;
skills/x-integration/lib/config.ts
- Executable scriptline 1
Executable file
skills/x-integration/scripts/like.ts
- Executable scriptline 1
#!/usr/bin/env npx tsx - Network accessline 2
/** * X Integration - Like Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx like.ts - Network accessline 3
* X Integration - Like Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx like.ts */ - Network accessline 4
* Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx like.ts
skills/x-integration/scripts/post.ts
skills/x-integration/scripts/quote.ts
- Executable scriptline 1
#!/usr/bin/env npx tsx - Network accessline 2
/** * X Integration - Quote Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123","comment":"My thoughts"}' | npx tsx quote.ts - Network accessline 3
* X Integration - Quote Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123","comment":"My thoughts"}' | npx tsx quote.ts */ - Network accessline 4
* Usage: echo '{"tweetUrl":"https://x.com/user/status/123","comment":"My thoughts"}' | npx tsx quote.ts
skills/x-integration/scripts/reply.ts
- Executable scriptline 1
#!/usr/bin/env npx tsx - Network accessline 2
/** * X Integration - Reply to Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123","content":"Great post!"}' | npx tsx reply.ts - Network accessline 3
* X Integration - Reply to Tweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123","content":"Great post!"}' | npx tsx reply.ts */ - Network accessline 4
* Usage: echo '{"tweetUrl":"https://x.com/user/status/123","content":"Great post!"}' | npx tsx reply.ts
skills/x-integration/scripts/retweet.ts
- Executable scriptline 1
#!/usr/bin/env npx tsx - Network accessline 2
/** * X Integration - Retweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx retweet.ts - Network accessline 3
* X Integration - Retweet * Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx retweet.ts */ - Network accessline 4
* Usage: echo '{"tweetUrl":"https://x.com/user/status/123"}' | npx tsx retweet.ts
skills/x-integration/scripts/setup.ts
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.
Declared and executed: 1 fact
- Allows Bash without restrictions, though it has no scripts or shell blocksget-qodo-rules/SKILL.md:5High confidence
Signal confidence: 267 facts
- Network access in code of the SKILL.mdagent-browser/SKILL.md:107High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:108High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:116High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:118High confidence
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:124High confidence
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:125High confidence
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:126High confidence
- Dangerous shell operation in code of the SKILL.mdagent-browser/SKILL.md:134High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:140High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:154High confidence
- Network access in code of the SKILL.mdadd-discord/SKILL.md:35High confidence
- Network access in prose of the SKILL.mdadd-discord/SKILL.md:74Low confidence
- Network access in prose of the SKILL.mdadd-discord/SKILL.md:75Low confidence
- Network access in prose of the SKILL.mdadd-discord/SKILL.md:76Low confidence
- Access to secrets in code of the SKILL.mdadd-discord/SKILL.md:103High confidence
- Network access in prose of the SKILL.mdadd-discord/SKILL.md:185Low confidence
- Network access in prose of the SKILL.mdadd-discord/SKILL.md:186Low confidence
- Network access in code of the SKILL.mdadd-gmail/SKILL.md:36High confidence
- Network access in prose of the SKILL.mdadd-gmail/SKILL.md:94Low confidence
- Network access in prose of the SKILL.mdadd-gmail/SKILL.md:95Low confidence
- Network access in prose of the SKILL.mdadd-gmail/SKILL.md:96Low confidence
- Dangerous shell operation in code of the SKILL.mdadd-gmail/SKILL.md:133High confidence
- Dangerous shell operation in code of the SKILL.mdadd-gmail/SKILL.md:189High confidence
- Dangerous shell operation in prose of the SKILL.mdadd-gmail/SKILL.md:210Low confidence
- Dangerous shell operation in prose of the SKILL.mdadd-gmail/SKILL.md:221Low confidence
- Network access in code of the SKILL.mdadd-image-vision/SKILL.md:28High confidence
- Network access in prose of the SKILL.mdadd-ollama-tool/SKILL.md:28Low confidence
- Network access in code of the SKILL.mdadd-ollama-tool/SKILL.md:51High confidence
- Network access in prose of the SKILL.mdadd-ollama-tool/SKILL.md:94Low confidence
- Network access in code of the SKILL.mdadd-ollama-tool/SKILL.md:97High confidence
- Network access in prose of the SKILL.mdadd-ollama-tool/SKILL.md:149Low confidence
- Network access in prose of the SKILL.mdadd-ollama-tool/SKILL.md:150Low confidence
- Network access in prose of the SKILL.mdadd-parallel/SKILL.md:13Low confidence
- Network access in prose of the SKILL.mdadd-parallel/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdadd-parallel/SKILL.md:29Low confidence
- Network access in prose of the SKILL.mdadd-parallel/SKILL.md:30Low confidence
- Network access in prose of the SKILL.mdadd-parallel/SKILL.md:31Low confidence
- Access to secrets in prose of the SKILL.mdadd-parallel/SKILL.md:41Low confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:44High confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:45High confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:46High confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:49High confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:50High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueadd-parallel/SKILL.md:51Low confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:52High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueadd-parallel/SKILL.md:55Low confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:56High confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:62High confidence
- Access to secrets in prose of the SKILL.mdadd-parallel/SKILL.md:67Low confidence
- Access to secrets in code of the SKILL.mdadd-parallel/SKILL.md:71High confidence
and 217 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md agent/skills/agent-browser/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md agent/skills/agent-browser/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md agent/skills/agent-browser/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md agent/skills/agent-browser/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md agent/skills/agent-browser/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.