Not in the top 1,000 by GitHub stars
obra/superpowers-lab
Experimental skills for Claude Code Superpowers - new techniques and tools
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
skills/finding-duplicate-functions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
51111f74f240 → 51111f74f240
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 51111f74f240
No earlier version was observed for comparison.
skills/mcp-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
51111f74f240 → 51111f74f240
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 51111f74f240
No earlier version was observed for comparison.
skills/using-tmux-for-interactive-commands/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
51111f74f240 → 51111f74f240
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 51111f74f240
No earlier version was observed for comparison.
skills/windows-vm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
51111f74f240 → 51111f74f240
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 51111f74f240
No earlier version was observed for comparison.
Verified commit 51111f74f24058117752d9aa917cb19859f8ec86
git clone --filter=blob:none --no-checkout https://github.com/obra/superpowers-lab.git .hotskills/obra-superpowers-lab && git -C .hotskills/obra-superpowers-lab checkout --detach 51111f74f24058117752d9aa917cb19859f8ec86
# Copy each selected skill directory from .hotskills/obra-superpowers-lab into .claude/skills/<skill-name>/Heat
4.0- 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
- finding-duplicate-functions
skills/finding-duplicate-functions - mcp-cli
skills/mcp-cli - using-tmux-for-interactive-commands
skills/using-tmux-for-interactive-commands - windows-vm
skills/windows-vm
How it works
finding-duplicate-functions
When your agent uses it
Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
1,059 tokensWhen the skill is activated
Reference documents
1,286 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Quick Reference
- Process
- High-Risk Duplicate Zones
- Common Mistakes
Scripts executed separately
scripts/extract-functions.shscripts/generate-report.shscripts/prepare-category-analysis.sh
Files
../../.claude-plugin/plugin.jsonasset577 bytesSKILL.mdcore4,794 bytesSKILL.mdcore4,794 bytesscripts/categorize-prompt.mddoc2,773 bytesscripts/extract-functions.shruns8,171 bytesscripts/find-duplicates-prompt.mddoc2,953 bytesscripts/generate-report.shruns4,670 bytesscripts/prepare-category-analysis.shruns1,965 bytes
Read SKILL.md
# Finding Duplicate-Intent Functions
## Overview
LLM-generated codebases accumulate semantic duplicates: functions that serve the same purpose but were implemented independently. Classical copy-paste detectors (jscpd) find syntactic duplicates but miss "same intent, different implementation."
This skill uses a two-phase approach: classical extraction followed by LLM-powered intent clustering.
## When to Use
- Codebase has grown organically with multiple contributors (human or LLM)
- You suspect utility functions have been reimplemented multiple times
- Before major refactoring to identify consolidation opportunities
- After jscpd has been run and syntactic duplicates are already handledView the complete source on GitHubmcp-cli
When your agent uses it
Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
2,430 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
- When to Use This Skill
- Prerequisites
- Discovery Workflow
- Making Tool Calls
- Reading Resources
- Using Prompts
- Server Aliases (for repeated use)
- Authentication
- Transport Types
- Common MCP Servers
- Best Practices
- Debugging
- Quick Reference
- Example: Complete Workflow
- Troubleshooting
Files
SKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytesSKILL.mdcore9,217 bytes
Read SKILL.md
# MCP CLI: On-Demand MCP Server Usage
Use the `mcp` CLI tool to dynamically discover and invoke MCP server capabilities without pre-configuring them as permanent integrations.
## When to Use This Skill
Use this skill when you need to:
- Explore an MCP server's capabilities before deciding to use it
- Make one-off calls to an MCP server without permanent integration
- Access MCP functionality without polluting the context window
- Test or debug MCP servers
- Use MCP servers that aren't pre-configured
## PrerequisitesView the complete source on GitHubusing-tmux-for-interactive-commands
When your agent uses it
Use when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that require real-time input/output - provides tmux-based approach for controlling interactive sessions through detached sessions and send-keys
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,383 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
- Overview
- When to Use
- Quick Reference
- Core Pattern
- Implementation
- Common Patterns
- Common Mistakes
- Real-World Impact
Scripts executed separately
tmux-wrapper.sh
Files
SKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytesSKILL.mdcore5,074 bytestmux-wrapper.shruns1,911 bytes
Read SKILL.md
# Using tmux for Interactive Commands
## Overview
Interactive CLI tools (vim, interactive git rebase, REPLs, etc.) cannot be controlled through standard bash because they require a real terminal. tmux provides detached sessions that can be controlled programmatically via `send-keys` and `capture-pane`.
## When to Use
**Use tmux when:**
- Running vim, nano, or other text editors programmatically
- Controlling interactive REPLs (Python, Node, etc.)
- Handling interactive git commands (`git rebase -i`, `git add -p`)
- Working with full-screen terminal apps (htop, etc.)
- Commands that require terminal control codes or readlineView the complete source on GitHubwindows-vm
When your agent uses it
Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
2,866 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
- Host prerequisites
- Configuration
- Actions
- Important Notes
- Post-install gotchas
Files
SKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytesSKILL.mdcore10,034 bytes
Read SKILL.md
# Headless Windows 11 VM
Manage a headless Windows 11 VM running via [dockur/windows](https://github.com/dockur/windows) in Docker with KVM acceleration. The VM is accessible via SSH only — no RDP or GUI required.
## Host prerequisites
- Docker
- KVM support (`/dev/kvm` must exist — check with `ls /dev/kvm`)
- `sshpass` (`sudo apt install sshpass`)
- `imagemagick` (optional, for screenshot debugging: `sudo apt install imagemagick`)
## Configuration
- **Container name**: `windows11`View the complete source on GitHubSkills included
- finding-duplicate-functions
- mcp-cli
- using-tmux-for-interactive-commands
- windows-vm
Repository facts
- License
- MIT
- Created
- Oct 23, 2025
- Last pushed
- Jun 1, 2026
- Forks
- 38
- 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 72 notes
skills/finding-duplicate-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/mcp-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: windows-vm/SKILL.md:1
- 4 dangerous shell commandsin 1 file: windows-vm/SKILL.md:16
- 20 network referencesin 3 files: mcp-cli/SKILL.md:24 windows-vm/SKILL.md:10 .claude-plugin/plugin.json:7
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 4 files: finding-duplicate-functions/scripts/extract-functions.sh:1 finding-duplicate-functions/scripts/generate-report.sh:1 finding-duplicate-functions/scripts/prepare-category-analysis.sh:1 and 1 more
- 7 references to secretsin 2 files: mcp-cli/SKILL.md:51 windows-vm/SKILL.md:167
- No requests to vote in Hot
Show all 36 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"email": "jesse@fsck.com" }, "homepage": "https://github.com/obra/superpowers-lab", - Network accessline 8
}, "homepage": "https://github.com/obra/superpowers-lab", "repository": "https://github.com/obra/superpowers-lab", - Network accessline 9
"homepage": "https://github.com/obra/superpowers-lab", - Network accessline 10
"repository": "https://github.com/obra/superpowers-lab",
skills/finding-duplicate-functions/scripts/extract-functions.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/finding-duplicate-functions/scripts/generate-report.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/finding-duplicate-functions/scripts/prepare-category-analysis.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/mcp-cli/SKILL.md
- Network accessline 24
# Clone and build cd /tmp && git clone --depth 1 https://github.com/f/mcptools.git - Network accessline 25
cd /tmp && git clone --depth 1 https://github.com/f/mcptools.git - Access to secretsline 51
[Credential-related source omitted] - Network accessline 53
# HTTP-based server mcp tools https://example.com/mcp - Network accessline 54
mcp tools https://example.com/mcp - Network accessline 199
mcp tools --auth-user "username:password" https://api.example.com/mcp - Network accessline 204
mcp tools --auth-header "Bearer your-token-here" https://api.example.com/mcp - Access to secretsline 209
[Credential-related source omitted] - Access to secretsline 210
[Credential-related source omitted] - Network accessline 223
mcp tools https://example.com/mcp - Network accessline 228
mcp tools http://localhost:3001/sse - Network accessline 230
mcp tools --transport sse http://localhost:3001 - Access to secretsline 248
[Credential-related source omitted] - Access to secretsline 249
[Credential-related source omitted] - Access to secretsline 254
[Credential-related source omitted]
skills/using-tmux-for-interactive-commands/tmux-wrapper.sh
- Executable scriptline 1
#!/bin/bash
skills/windows-vm/SKILL.md
- Broad permissionsline 1
Bash, Read, Write - Network accessline 10
Manage a headless Windows 11 VM running via [dockur/windows](https://github.com/dockur/windows) in Docker with KVM acceleration. The VM is accessible via SSH only — no RDP or GUI required. - Dangerous shell operationline 16
- `sshpass` (`sudo apt install sshpass`) - Dangerous shell operationline 17
- `imagemagick` (optional, for screenshot debugging: `sudo apt install imagemagick`) - Dangerous shell operationline 58
docker stop windows11 && docker rm windows11 - Dangerous shell operationline 59
rm -f "$HOME/windows-vm/storage/data.img" - Network accessline 115
You can also watch the VM screen via the web console at `http://localhost:8006`. - Network accessline 125
cat << 'PS' | sshpass -p 'password' ssh -o StrictHostKeyChecking=no -p 2222 user@localhost "powershell -ExecutionPolicy Bypass -Command -" # Download and install Node.js silently Invoke-WebRequest -Uri 'https://nodejs.org/dist/v22.14. - Network accessline 126
# Download and install Node.js silently Invoke-WebRequest -Uri 'https://nodejs.org/dist/v22.14.0/node-v22.14.0-x64.msi' -OutFile 'C:\Users\user\node-install.msi' Start-Process msiexec.exe -ArgumentList '/i C:\Users\user\node-install.m - Network accessline 127
Invoke-WebRequest -Uri 'https://nodejs.org/dist/v22.14.0/node-v22.14.0-x64.msi' -OutFile 'C:\Users\user\node-install.msi' - Access to secretsline 167
[Credential-related source omitted] - Network accessline 199
docker exec windows11 bash -c "echo 'screendump /tmp/screen.ppm' | nc -w 2 localhost 7100" > /dev/null 2>&1 - Network accessline 216
- **Node.js is not pre-installed** — the Claude Code install script (`irm https://claude.ai/install.ps1 | iex`) will report success but `claude` won't work without Node. Install Node.js via MSI first.
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.
Combined signals: 1 fact
- Reads SSH keys, and the same file sends data over the network or runs a command (line 199)windows-vm/SKILL.md:167High confidence
Signal confidence: 32 facts
- Executable script in code of a file that runsfinding-duplicate-functions/scripts/extract-functions.sh:1High confidence
- Executable script in code of a file that runsfinding-duplicate-functions/scripts/generate-report.sh:1High confidence
- Executable script in code of a file that runsfinding-duplicate-functions/scripts/prepare-category-analysis.sh:1High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:24High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:25High confidence
- Access to secrets in code of the SKILL.mdmcp-cli/SKILL.md:51High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:53High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:54High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:199High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:204High confidence
- Access to secrets in code of the SKILL.mdmcp-cli/SKILL.md:209High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuemcp-cli/SKILL.md:210Low confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:223High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:228High confidence
- Network access in code of the SKILL.mdmcp-cli/SKILL.md:230High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuemcp-cli/SKILL.md:248Low confidence
- Access to secrets in code of the SKILL.mdmcp-cli/SKILL.md:249High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuemcp-cli/SKILL.md:254Low confidence
- Executable script in code of a file that runsusing-tmux-for-interactive-commands/tmux-wrapper.sh:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwindows-vm/SKILL.md:1High confidence
- Network access in prose of the SKILL.mdwindows-vm/SKILL.md:10Low confidence
- Dangerous shell operation in prose of the SKILL.mdwindows-vm/SKILL.md:16Low confidence
- Dangerous shell operation in prose of the SKILL.mdwindows-vm/SKILL.md:17Low confidence
- Dangerous shell operation in code of the SKILL.mdwindows-vm/SKILL.md:58High confidence
- Dangerous shell operation in code of the SKILL.mdwindows-vm/SKILL.md:59High confidence
- Network access in prose of the SKILL.mdwindows-vm/SKILL.md:115Low confidence
- Network access in code of the SKILL.mdwindows-vm/SKILL.md:125High confidence
- Network access in code of the SKILL.mdwindows-vm/SKILL.md:126High confidence
- Network access in code of the SKILL.mdwindows-vm/SKILL.md:127High confidence
- Access to secrets in code of the SKILL.md: reads a credential storewindows-vm/SKILL.md:167High confidence
- Network access in code of the SKILL.mdwindows-vm/SKILL.md:199High confidence
- Network access in prose of the SKILL.mdwindows-vm/SKILL.md:216Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/finding-duplicate-functions/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/finding-duplicate-functions/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/finding-duplicate-functions/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/finding-duplicate-functions/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/finding-duplicate-functions/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.