fingerprint
Generates performance metrics and regression tests for chord recognition algorithms.
Install
mkdir -p .claude/skills/fingerprint && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13040" && unzip -o skill.zip -d .claude/skills/fingerprint && rm skill.zipInstalls to .claude/skills/fingerprint
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Führt den Chord-Recognition-Fingerprint des Repos aus, indem der Statistik-Test für die Akkorderkennung samt TP/TN/FP/FN, Sensitivität, Spezifität, Precision, Accuracy, F1 und Falllisten gestartet wird. Verwenden, wenn der aktuelle Erkennungsstand kompakt und reproduzierbar gemessen werden soll.Key capabilities
- →Measure the current state of chord recognition reproducibly
- →Calculate TP, FP, FN, TN values for chord recognition
- →Determine sensitivity, specificity, precision, and accuracy
- →Compute F1 score and negative predictive value
- →Generate lists of False Positives, False Negatives, True Positives, and True Negatives
- →Optionally run associated Essentia-Fingerprint-Test
How it works
The skill executes a Node.js script to perform a chord recognition fingerprint based on Frozen-HPCP-Fixtures. It then calculates various statistical metrics and lists classification results.
Inputs & outputs
When to use fingerprint
- →Test chord recognition accuracy
- →Run regression for recognition
- →Generate fingerprint metrics
About this skill
Fingerprint
Zweck
Den aktuellen Stand der Chord-Erkennung reproduzierbar messen und ausgeben.
Der Fingerprint basiert auf den Frozen-HPCP-Fixtures und liefert:
- TP, FP, FN, TN
- Sensitivität
- Spezifität
- Precision
- Negative Predictive Value
- Accuracy
- False Positive Rate
- False Negative Rate
- F1
- Listen der False Positives, False Negatives, True Positives und True Negatives
Workflow
- Neuer Essentia-Fingerprint:
node scripts/chord-recognition-fingerprint.mjs
- Optional zusätzlich den zugehörigen Essentia-Fingerprint-Test laufen lassen:
npx vitest run tests/unit/essentiaChordFingerprintMetrics.test.js tests/unit/essentiaChordFingerprintRegression.test.js
- Vorbereitete Essentia-Fixtures bei Bedarf neu erzeugen:
node scripts/generate-essentia-fingerprint-fixtures.mjs
- Bestehender JS-Fingerprint bleibt separat verfügbar:
node scripts/chord-recognition-jsfingerprint.mjs
- Optional zusätzlich den zugehörigen JS-Fingerprint-Test laufen lassen:
npx vitest run tests/unit/essentiaChordJsfingerprintMetrics.test.js
Regeln
- Für den Fingerprint keine zweite, abweichende Statistiklogik bauen.
- Immer dieselbe Auswertung aus
tests/helpers/chordRecognitionMetrics.jsverwenden. - Zahlen nur aus dem aktuellen Repo-Stand ableiten, nicht aus alten Notizen übernehmen.
When not to use it
- →When building a second, different statistical logic for the fingerprint
- →When using evaluation logic other than `chordRecognitionMetrics.js`
- →When deriving numbers from old notes instead of the current repo state
Limitations
- →Requires the use of `tests/helpers/chordRecognitionMetrics.js` for evaluation
- →Derives numbers only from the current repository state
- →Does not build a second, different statistical logic for the fingerprint
How it compares
This workflow provides a standardized and reproducible measurement of chord recognition performance using specific fixtures and a consistent evaluation logic, unlike ad-hoc testing.
Compared to similar skills
fingerprint side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fingerprint (this skill) | 0 | 3mo | Review | Intermediate |
| similarity-search-patterns | 3 | 2mo | No flags | Advanced |
| orchardcore-tester | 1 | 6mo | Review | Intermediate |
| add-test | 0 | 4mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
similarity-search-patterns
wshobson
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
orchardcore-tester
OrchardCMS
Tests OrchardCore CMS features through browser automation. Use when the user needs to build, run, setup, or test OrchardCore functionality including admin features, content management, media library, and module testing.
add-test
affandar
Add a new integration test to PilotSwarm test suite. Tests verify end-to-end flows through PilotSwarmClient, duroxide orchestration, and the Copilot SDK.
integration-testing
EmanuelAngel
>
verify
melnicorn
Build, run, and drive Sensify locally to verify changes end-to-end
generate-validation-notebook
monte-carlo-data
Generate SQL validation notebooks for dbt changes. Pass a GitHub PR URL or local dbt repo path.