Your Task
Target: $ARGUMENTS
- Get lyrics for the specified track(s)
- Extract distinctive phrases using MCP tool
- Web search top phrases for matches against known songs
- Use LLM knowledge to independently flag similarities
- Generate structured risk report
Plagiarism Checker
You scan lyrics for phrases that may unintentionally echo existing songs. This is a quality check, not a legal tool — it catches borrowing early so the writer can revise before release.
Workflow
Step 1: Get Lyrics
- Use
extract_section(album_slug, track_slug, "streaming") to get streaming lyrics (preferred — no phonetic spellings that confuse web searches)
- If streaming lyrics empty, fall back to
extract_section(album_slug, track_slug, "lyrics") for Suno lyrics
- If raw text was provided instead of album/track reference, use that directly
Step 2: Extract Distinctive Phrases
Call extract_distinctive_phrases(text, max_phrases=15, include_raw_lines=False) MCP tool. This returns:
- Distinctive 4-7 word n-grams ranked by section priority (top 15)
- Pre-formatted search suggestions with quoted phrases + "lyrics"
- Common cliches already filtered out
Step 3: Web Search
- Search the top 10-15
search_suggestions returned by the tool using WebSearch
- For short lyrics (<100 words), limit to 5-8 searches
- Look for results that reference specific songs by title/artist
- Skip results that are:
- Lyrics aggregator sites listing hundreds of matches (too generic)
- Dictionary/reference pages
- The user's own published work
Step 4: Deep Compare
For any search result that names a specific song:
- WebFetch the lyrics page
- Compare the matching section against the user's lyrics
- Check if the match is:
- Exact consecutive words (5+) — HIGH risk
- Partial overlap (4 words) — MEDIUM risk
- Thematic similarity only — LOW risk
Step 5: LLM Knowledge Check
Independently scan ALL lines of the lyrics (not just extracted phrases) using your training knowledge:
- Flag any line that closely resembles a well-known song lyric
- Include the suspected source song and artist
- Note whether the similarity is in words, melody hook phrasing, or concept
Step 6: Generate Report
Risk Levels
| Level |
Criteria |
Action |
| HIGH |
5+ consecutive matching words from a known song, especially chorus/hook |
Rewrite the line immediately |
| MEDIUM |
4-word match from known song, or structural similarity flagged by LLM |
Review and consider rewording |
| LOW |
Common phrasing overlap, likely coincidence |
Note for awareness, no action needed |
Output Format
PLAGIARISM CHECK REPORT
Album: [Album Name]
Track: [Track Title]
Date: [Scan Date]
PHRASES SEARCHED: [N]
WEB MATCHES FOUND: [N]
LLM FLAGS: [N]
FINDINGS:
------------------------------------------------------------------------
[HIGH] Line 12 (Chorus): "burning shadows fall tonight across the wire"
Match: "Shadows Fall Tonight" by [Artist] — 5 consecutive words match chorus
Source: [URL]
Recommendation: Rewrite this line to avoid direct overlap
[MEDIUM] Line 24 (Verse 2): "walking through the ruins of the empire"
Similarity: Resembles "Empire" by [Artist] — similar phrasing in bridge
Source: LLM knowledge
Recommendation: Consider rewording if concerned
[LOW] Line 8 (Verse 1): "the city sleeps beneath the stars"
Note: Generic night imagery, appears in many songs
Recommendation: No action needed
------------------------------------------------------------------------
SUMMARY:
HIGH risk findings: 1
MEDIUM risk findings: 1
LOW risk findings: 1
VERDICT: NEEDS REVIEW
1 high-risk match requires attention before release.
COMMON PHRASES FILTERED: [N] (not searched — too generic to flag)
Verdicts
| Verdict |
Criteria |
| CLEAR |
No HIGH or MEDIUM findings |
| NEEDS REVIEW |
Any MEDIUM findings, or 1 HIGH finding |
| REWRITE REQUIRED |
2+ HIGH findings |
Important Notes
- This is not a legal tool. It catches likely borrowing, not copyright infringement. Only a lawyer can determine infringement.
- Streaming lyrics preferred. Suno lyrics contain phonetic respellings (e.g., "Seh-KYOOR-ih-tee" for "security") that will produce garbage web search results.
- Common cliches are pre-filtered. The MCP tool removes ~75 ubiquitous phrases ("break my heart", "falling in love", etc.) before returning results. These are too common to flag.
- Web searches may fail. If WebSearch is unavailable or rate-limited, proceed with LLM knowledge check only and note the limitation in the report.
- Not a pre-generation gate. This check is too slow (web searches) and too unreliable (search availability) to block generation. Run it before release, not before Suno.
Running for Full Album
When given an album slug without a specific track:
- List all tracks via
list_tracks(album_slug)
- Run the check for each track with status "In Progress", "Generated", or "Final"
- Skip tracks with status "Not Started" or "Sources Pending"
- Aggregate findings into a single album-level report with per-track sections
Example Invocations
/plagiarism-checker dark-tide
/plagiarism-checker dark-tide 03-the-wire
1---2name: plagiarism-checker3description: Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.4---5
6## Your Task
7
8**Target**: $ARGUMENTS
9
101. Get lyrics for the specified track(s)
112. Extract distinctive phrases using MCP tool
123. Web search top phrases for matches against known songs
134. Use LLM knowledge to independently flag similarities
145. Generate structured risk report
15
16---
17
18# Plagiarism Checker
19
20You scan lyrics for phrases that may unintentionally echo existing songs. This is a quality check, not a legal tool — it catches borrowing early so the writer can revise before release.
21
22---
23
24## Workflow
25
26### Step 1: Get Lyrics
27
28- Use `extract_section(album_slug, track_slug, "streaming")` to get streaming lyrics (preferred — no phonetic spellings that confuse web searches)
29- If streaming lyrics empty, fall back to `extract_section(album_slug, track_slug, "lyrics")` for Suno lyrics
30- If raw text was provided instead of album/track reference, use that directly
31
32### Step 2: Extract Distinctive Phrases
33
34Call `extract_distinctive_phrases(text, max_phrases=15, include_raw_lines=False)` MCP tool. This returns:
35- Distinctive 4-7 word n-grams ranked by section priority (top 15)
36- Pre-formatted search suggestions with quoted phrases + "lyrics"
37- Common cliches already filtered out
38
39### Step 3: Web Search
40
41- Search the top 10-15 `search_suggestions` returned by the tool using WebSearch
42- For short lyrics (<100 words), limit to 5-8 searches
43- Look for results that reference specific songs by title/artist
44- Skip results that are:
45 - Lyrics aggregator sites listing hundreds of matches (too generic)
46 - Dictionary/reference pages
47 - The user's own published work
48
49### Step 4: Deep Compare
50
51For any search result that names a specific song:
521. WebFetch the lyrics page
532. Compare the matching section against the user's lyrics
543. Check if the match is:
55 - Exact consecutive words (5+) — HIGH risk
56 - Partial overlap (4 words) — MEDIUM risk
57 - Thematic similarity only — LOW risk
58
59### Step 5: LLM Knowledge Check
60
61Independently scan ALL lines of the lyrics (not just extracted phrases) using your training knowledge:
62- Flag any line that closely resembles a well-known song lyric
63- Include the suspected source song and artist
64- Note whether the similarity is in words, melody hook phrasing, or concept
65
66### Step 6: Generate Report
67
68---
69
70## Risk Levels
71
72| Level | Criteria | Action |
73|-------|----------|--------|
74| **HIGH** | 5+ consecutive matching words from a known song, especially chorus/hook | Rewrite the line immediately |
75| **MEDIUM** | 4-word match from known song, or structural similarity flagged by LLM | Review and consider rewording |
76| **LOW** | Common phrasing overlap, likely coincidence | Note for awareness, no action needed |
77
78---
79
80## Output Format
81
82```
83PLAGIARISM CHECK REPORT
84Album: [Album Name]
85Track: [Track Title]
86Date: [Scan Date]
87
88PHRASES SEARCHED: [N]
89WEB MATCHES FOUND: [N]
90LLM FLAGS: [N]
91
92FINDINGS:
93------------------------------------------------------------------------
94
95[HIGH] Line 12 (Chorus): "burning shadows fall tonight across the wire"
96 Match: "Shadows Fall Tonight" by [Artist] — 5 consecutive words match chorus
97 Source: [URL]
98 Recommendation: Rewrite this line to avoid direct overlap
99
100[MEDIUM] Line 24 (Verse 2): "walking through the ruins of the empire"
101 Similarity: Resembles "Empire" by [Artist] — similar phrasing in bridge
102 Source: LLM knowledge
103 Recommendation: Consider rewording if concerned
104
105[LOW] Line 8 (Verse 1): "the city sleeps beneath the stars"
106 Note: Generic night imagery, appears in many songs
107 Recommendation: No action needed
108
109------------------------------------------------------------------------
110
111SUMMARY:
112 HIGH risk findings: 1
113 MEDIUM risk findings: 1
114 LOW risk findings: 1
115
116VERDICT: NEEDS REVIEW
117 1 high-risk match requires attention before release.
118
119COMMON PHRASES FILTERED: [N] (not searched — too generic to flag)
120```
121
122### Verdicts
123
124| Verdict | Criteria |
125|---------|----------|
126| **CLEAR** | No HIGH or MEDIUM findings |
127| **NEEDS REVIEW** | Any MEDIUM findings, or 1 HIGH finding |
128| **REWRITE REQUIRED** | 2+ HIGH findings |
129
130---
131
132## Important Notes
133
134- **This is not a legal tool.** It catches likely borrowing, not copyright infringement. Only a lawyer can determine infringement.
135- **Streaming lyrics preferred.** Suno lyrics contain phonetic respellings (e.g., "Seh-KYOOR-ih-tee" for "security") that will produce garbage web search results.
136- **Common cliches are pre-filtered.** The MCP tool removes ~75 ubiquitous phrases ("break my heart", "falling in love", etc.) before returning results. These are too common to flag.
137- **Web searches may fail.** If WebSearch is unavailable or rate-limited, proceed with LLM knowledge check only and note the limitation in the report.
138- **Not a pre-generation gate.** This check is too slow (web searches) and too unreliable (search availability) to block generation. Run it before release, not before Suno.
139
140---
141
142## Running for Full Album
143
144When given an album slug without a specific track:
145
1461. List all tracks via `list_tracks(album_slug)`
1472. Run the check for each track with status "In Progress", "Generated", or "Final"
1483. Skip tracks with status "Not Started" or "Sources Pending"
1494. Aggregate findings into a single album-level report with per-track sections
150
151---
152
153## Example Invocations
154
155```
156/plagiarism-checker dark-tide
157/plagiarism-checker dark-tide 03-the-wire
158```