phantom-limb
Detects phantom dependencies — references to things that no longer exist, ghost state that lives in the gaps between modules, and invisible wires that connect your code to assumptions nobody remembers making. The codebase equivalent of feeling a limb that's already been amputated.
Why use this skill?
Eliminate stale references, ghost state, and invisible dependencies in your project with Phantom Limb. Identify the technical debt you can't see.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jcools1977/phantom-limbWhat This Skill Does
Phantom Limb is a diagnostic agent skill for OpenClaw that detects 'ghost dependencies'—references to concepts, configurations, or environmental states that no longer exist in your production environment but persist within your codebase. Unlike traditional linters that look for syntax errors or broken imports, Phantom Limb analyzes the semantic gaps between your code and its actual deployment context. It identifies the 'negative space' where deprecated logic, stale environmental variables, and architectural artifacts continue to influence the runtime environment without throwing explicit errors. By flagging these dormant connections, the tool reduces cognitive load, speeds up onboarding, and eliminates the 'it works on my machine' class of bugs.
Installation
To integrate this skill into your environment, use the OpenClaw command-line interface. Ensure you have the necessary read permissions for your source directory.
Command: clawhub install openclaw/skills/skills/jcools1977/phantom-limb
After installation, initialize the tool by pointing it to your root directory: openclaw phantom-limb scan --path ./src
Use Cases
- Refactoring Cleanup: Identify legacy wrappers that were intended to be temporary but are still being imported by newer modules.
- Production Debugging: Detect why certain features behave inconsistently by uncovering hidden fallbacks to environment variables that are no longer populated in the cluster.
- Onboarding Optimization: Clean up stale, confusing 'deprecated' paths that slow down new developers trying to understand the current architecture.
- Dependency Auditing: Locate code blocks that rely on internal service endpoints or hardware assumptions that have been decommissioned.
Example Prompts
- 'Run a full audit on the repository to identify any environment variables referenced in the code that aren't defined in our current CI/CD environment files.'
- 'Check for referential phantoms in the legacy folder; flag any imports that resolve through more than two shims or re-export layers.'
- 'Identify any code paths that reference the old v1 API architecture that are still active despite the total migration to v2.'
Tips & Limitations
Phantom Limb is a static analysis tool; it cannot detect runtime-only phantoms that are only created through dynamic evaluation or complex runtime reflection. It works best when combined with live deployment manifests. Always review the output before applying automated code deletions, as some 'phantoms' may serve as safety buffers for edge-case hardware or legacy clients that you are still actively supporting.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jcools1977-phantom-limb": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read
Related Skills
Li_python_sec_check
Python 安全规范检查工具 - 基于 CloudBase 规范 + 腾讯安全指南 + LLM 智能分析(LLM 功能默认禁用,本地执行优先)
skill-vettr
Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patterns before installation. Use when vetting skills from ClawHub or untrusted sources.
skill-vettr
Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patterns before installation. Use when vetting skills from ClawHub or untrusted sources.