utils:find-claude-plugin-root
This skill should be used when the user needs to locate a plugin's installation path, when ${CLAUDE_PLUGIN_ROOT} doesn't expand in markdown files, or when invoked via /utils:find-claude-plugin-root. Generates a CPR resolver script at /tmp/cpr.py.
What this skill does
# Find Claude Plugin Root
This skill generates a Python resolver script at `/tmp/cpr.py` that locates a plugin's installation directory by reading `~/.claude/plugins/installed_plugins.json`.
## Problem It Solves
`${CLAUDE_PLUGIN_ROOT}` environment variable doesn't expand in markdown command files, making it impossible to reference plugin scripts and resources. This is a known issue: https://github.com/anthropics/claude-code/issues/9354
## Solution
Generate a Python script that:
1. Accepts plugin name as argument
2. Tries `${CLAUDE_PLUGIN_ROOT}` first (backwards compatible)
3. Reads installed_plugins.json and searches for exact match
4. If no exact match, finds similar plugin names (fuzzy matching)
5. Outputs the plugin installation path to stdout
6. Saves to `/tmp/cpr.py` (ephemeral, no project pollution)
## Usage
Invoke this skill before executing plugin scripts:
```bash
# Generate the resolver
Skill(skill="utils:find-claude-plugin-root")
# Use it to find a plugin and execute its scripts
PLUGIN_ROOT=$(python3 /tmp/cpr.py readme-and-co)
python "$PLUGIN_ROOT/scripts/populate_license.py" --license MIT
```
## Implementation
### Step 1: Create the CPR resolver Python script
```bash
cat > /tmp/cpr.py << 'CPREOF'
#!/usr/bin/env python3
"""
Claude Plugin Root (CPR) Resolver
Usage: python3 /tmp/cpr.py <plugin-name>
Returns: absolute path to plugin installation directory
Searches for plugins in ~/.claude/plugins/installed_plugins.json with fuzzy matching.
"""
import json
import os
import sys
from pathlib import Path
from difflib import SequenceMatcher
def similarity(a, b):
"""Calculate similarity ratio between two strings."""
return SequenceMatcher(None, a.lower(), b.lower()).ratio()
def find_plugin_root(plugin_name):
"""
Find plugin installation directory.
Returns: (plugin_root_path, match_type)
match_type: 'env_var', 'exact', 'fuzzy', or None
"""
# Try CLAUDE_PLUGIN_ROOT first (backwards compatible)
env_root = os.environ.get('CLAUDE_PLUGIN_ROOT')
if env_root and os.path.isdir(env_root):
return env_root.rstrip('/'), 'env_var'
# Read installed_plugins.json
plugins_file = Path.home() / '.claude' / 'plugins' / 'installed_plugins.json'
if not plugins_file.exists():
return None, None
try:
with open(plugins_file, 'r') as f:
data = json.load(f)
plugins = data.get('plugins', {})
except (OSError, json.JSONDecodeError):
return None, None
# Try exact match first (case-insensitive)
for key, value in plugins.items():
if plugin_name.lower() in key.lower():
# Handle list or dict value
if isinstance(value, list) and len(value) > 0:
value = value[0]
install_path = value.get('installPath', '').rstrip('/')
if install_path and os.path.isdir(install_path):
return install_path, 'exact'
# Try fuzzy matching if no exact match
matches = []
for key, value in plugins.items():
# Extract just the plugin name from key (e.g., "owner/plugin-name" -> "plugin-name")
key_parts = key.split('/')
plugin_part = key_parts[-1] if key_parts else key
# Also handle @ separator (e.g., "plugin-name@plugin-name")
plugin_part = plugin_part.split('@')[0]
ratio = similarity(plugin_name, plugin_part)
if ratio > 0.6: # 60% similarity threshold
# Handle list or dict value
if isinstance(value, list) and len(value) > 0:
value = value[0]
install_path = value.get('installPath', '').rstrip('/')
if install_path and os.path.isdir(install_path):
matches.append((ratio, install_path, key))
if matches:
# Return best match
matches.sort(reverse=True, key=lambda x: x[0])
best_match = matches[0]
return best_match[1], 'fuzzy'
return None, None
def main():
if len(sys.argv) < 2:
print("Usage: python3 /tmp/cpr.py <plugin-name>", file=sys.stderr)
print("Example: python3 /tmp/cpr.py readme-and-co", file=sys.stderr)
sys.exit(1)
plugin_name = sys.argv[1]
plugin_root, match_type = find_plugin_root(plugin_name)
if plugin_root:
# Output just the path to stdout (for command substitution)
print(plugin_root)
sys.exit(0)
else:
print(f"Error: Could not locate plugin '{plugin_name}'", file=sys.stderr)
print(f"Checked: $CLAUDE_PLUGIN_ROOT, ~/.claude/plugins/installed_plugins.json", file=sys.stderr)
sys.exit(1)
if __name__ == '__main__':
main()
CPREOF
chmod +x /tmp/cpr.py
```
### Step 2: Verify the script works
```bash
# Test finding the utils plugin itself
if PLUGIN_ROOT=$(python3 /tmp/cpr.py utils); then
echo "✓ CPR resolver created at /tmp/cpr.py"
echo "✓ Test lookup succeeded: $PLUGIN_ROOT"
else
echo "❌ CPR resolver test failed" >&2
exit 1
fi
```
## Examples
### Find and use readme-and-co plugin
```bash
# Invoke this skill first
Skill(skill="utils:find-claude-plugin-root")
# Then use the resolver - run script and capture output
PLUGIN_ROOT=$(python3 /tmp/cpr.py readme-and-co)
python "$PLUGIN_ROOT/scripts/detect_project_info.py"
```
### Find and use any plugin
```bash
# The resolver works for any plugin
PLUGIN_ROOT=$(python3 /tmp/cpr.py my-plugin)
node "$PLUGIN_ROOT/tools/analyzer.js"
```
## Benefits
- **No project pollution** - Script saved to /tmp, not in project
- **Backwards compatible** - Tries ${CLAUDE_PLUGIN_ROOT} first
- **Fuzzy matching** - Finds plugins even if name doesn't exactly match
- **Pure Python** - No external dependencies (jq not needed)
- **Reusable** - One skill for all plugins
- **Ephemeral** - /tmp/cpr.py cleaned up on reboot
## Limitations
- Recreated on each system reboot (since /tmp is ephemeral)
- Requires Python 3 (standard on all modern systems)
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.