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.
From tldr-swintonnpx claudepluginhub mistakeknot/interagency-marketplace --plugin tldr-swintonThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
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.
| Phase | Tool | Model | Output |
|---|---|---|---|
| 1. Extract | scripts/extract-functions.sh | - | catalog.json |
| 2. Categorize | scripts/categorize-prompt.md | haiku | categorized.json |
| 3. Split | scripts/prepare-category-analysis.sh | - | categories/*.json |
| 4. Detect | scripts/find-duplicates-prompt.md | opus | duplicates/*.json |
| 5. Report | scripts/generate-report.sh | - | report.md |
digraph duplicate_detection {
rankdir=TB;
node [shape=box];
extract [label="1. Extract function catalog\n./scripts/extract-functions.sh"];
categorize [label="2. Categorize by domain\n(haiku subagent)"];
split [label="3. Split into categories\n./scripts/prepare-category-analysis.sh"];
detect [label="4. Find duplicates per category\n(opus subagent per category)"];
report [label="5. Generate report\n./scripts/generate-report.sh"];
review [label="6. Human review & consolidate"];
extract -> categorize -> split -> detect -> report -> review;
}
./scripts/extract-functions.sh src/ -o catalog.json
Options:
-o FILE: Output file (default: stdout)-c N: Lines of context to capture (default: 15)-t GLOB: File types (default: *.ts,*.tsx,*.js,*.jsx)--include-tests: Include test files (excluded by default)Test files (*.test.*, *.spec.*, __tests__/**) are excluded by default since test utilities are less likely to be consolidation candidates.
Dispatch a haiku subagent using the prompt in scripts/categorize-prompt.md.
Insert the contents of catalog.json where indicated in the prompt template. Save output as categorized.json.
./scripts/prepare-category-analysis.sh categorized.json ./categories
Creates one JSON file per category. Only categories with 3+ functions are worth analyzing.
For each category file in ./categories/, dispatch an opus subagent using the prompt in scripts/find-duplicates-prompt.md.
Save each output as ./duplicates/{category}.json.
./scripts/generate-report.sh ./duplicates ./duplicates-report.md
Produces a prioritized markdown report grouped by confidence level.
Review the report. For HIGH confidence duplicates:
Focus extraction on these areas first - they accumulate duplicates fastest:
| Zone | Common Duplicates |
|---|---|
utils/, helpers/, lib/ | General utilities reimplemented |
| Validation code | Same checks written multiple ways |
| Error formatting | Error-to-string conversions |
| Path manipulation | Joining, resolving, normalizing paths |
| String formatting | Case conversion, truncation, escaping |
| Date formatting | Same formats implemented repeatedly |
| API response shaping | Similar transformations for different endpoints |
Extracting too much: Focus on exported functions and public methods. Internal helpers are less likely to be duplicated across files.
Skipping the categorization step: Going straight to duplicate detection on the full catalog produces noise. Categories focus the comparison.
Using haiku for duplicate detection: Haiku is cost-effective for categorization but misses subtle semantic duplicates. Use Opus for the actual duplicate analysis.
Consolidating without tests: Before deleting duplicates, ensure the survivor has tests covering all use cases of the deleted functions.