adaptive-classifier
Build and Evaluate Adaptive Text Classifiers
Small labeled datasets and changing categories make text classification difficult to maintain. This skill guides incremental classifier updates and held-out evaluation with the adaptive-classifier library.
Установить с помощью моего Агента
Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.
Review the Skillstore skill "adaptive-classifier" from https://skillstore.io/skills/lambdasec-adaptive-classifier.md and its manifest at https://skillstore.io/api/skills/lambdasec-adaptive-classifier/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.
Ресурсы для AI-агентов
Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.
Протестировать
Использование «adaptive-classifier». Plan a support intent classifier from a small labeled dataset without downloading weights yet.
Ожидаемый результат:
- Suitability: a small dataset with changing intents matches the documented use case.
- Preparation: check the installed package version and confirm label consistency.
- Evaluation: separate training, validation, and test examples before fitting.
- Approval needed: confirm the encoder before downloading model weights.
- Results: no performance claims are available until evaluation runs.
Использование «adaptive-classifier». Explain what to check after adding a new technical-support category.
Ожидаемый результат:
- Confirm that the new label spelling is consistent and the class count changed as expected.
- Provide at least 10 labeled examples before relying on the new class.
- Reevaluate held-out examples for both existing and new categories.
- Report per-class precision, recall, F1, and sample sizes.
- Check update-order sensitivity and route uncertain predictions to human review.
Аудит безопасности
БезопасноAll 32 static findings are false positives: 31 match Markdown backticks, and one matches a documentation URL. No evidence found of prompt injection, credential access, or data exfiltration in the reviewed files. Model downloads require approval, remote model code stays disabled, and model-dependent examples were not executed during this audit.
Факторы риска
⚙️ Внешние команды (31)
🌐 Доступ к сети (1)
Поделиться и цитировать этот отчет
Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.
Копировать ссылку на отчёт
https://skillstore.io/skills/lambdasec-adaptive-classifier/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportЗначок Markdown
[](https://skillstore.io/skills/lambdasec-adaptive-classifier?utm_source=security_passport_badge)Значок HTML
<a href="https://skillstore.io/skills/lambdasec-adaptive-classifier?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/lambdasec-adaptive-classifier/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Встраиваемая карточка
<iframe src="https://skillstore.io/embed/skills/lambdasec-adaptive-classifier.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Академические ссылки (APA · BibTeX · CFF)
Цитата APA
lambdasec. (2026). adaptive-classifier security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/lambdasec-adaptive-classifier/audits/1Цитата BibTeX
@techreport{lambdasec-lambdasec-adaptive-classifier-2026,
author = {lambdasec},
title = {adaptive-classifier security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/lambdasec-adaptive-classifier/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "adaptive-classifier security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "lambdasec"
date-released: "2026-10-28"
url: "https://skillstore.io/skills/lambdasec-adaptive-classifier/audits/1"
identifiers:
- type: other
value: "skillstore:lambdasec-adaptive-classifier:audit:1"
description: "Skillstore immutable audit report identifier"
Оценка Skillstore
Почему такая оценка Достоверность доказательств: СреднийЧто вы можете построить
Route changing support intents
Build a ticket classifier from labeled examples, add emerging intents, and reevaluate existing categories after updates.
Evaluate small classification datasets
Compare an adaptive classifier against simple baselines using held-out data, per-class metrics, and learning curves.
Assess moderation triage robustness
Explore multilabel predictions and strategic robustness for moderation queues while retaining human review for consequential decisions.
Попробуйте эти промпты
Assess whether adaptive-classifier fits my ticket-routing task with 20 labeled examples per class. Identify missing information and ask before downloading anything.
Use my labeled texts to draft a local intent classifier with held-out evaluation. Check the installed version and request approval before downloading weights.
Add my new billing examples to an existing classifier. Check label consistency and compare held-out performance for old and new classes.
Design validation-only comparisons for pooling, blending weights, ONNX inference, and strategic robustness. Include order sensitivity, calibration, and a final untouched test evaluation.
Лучшие практики
- Separate training, validation, and test data before adding examples, and remove near-duplicates across splits.
- Request approval before model downloads, keep remote model code disabled, and publish only when explicitly requested.
- Reevaluate all classes after updates and report per-class metrics with sample sizes.
Избегать
- Evaluating on training examples or tuning settings against the final test split.
- Treating blended prediction scores as calibrated probabilities or upstream benchmark figures as guaranteed outcomes.
- Automating high-stakes decisions without human review or ignoring regressions after new labels.
Часто задаваемые вопросы
Which assistants can use this skill?
Does this skill install the library or download models automatically?
Can I add categories after creating a classifier?
Does it support multiple labels per text?
Are prediction scores reliable probabilities?
Were the model examples tested end to end?
Сведения для разработчиков
Автор
lambdasecЛицензия
Apache-2.0
Ревизия Skillstore
r1
Примечание о версии
Автор не указал версию.
Репозиторий
https://github.com/lambdasec/skills/tree/7d791206069498962a85a0f1ba95f7468dcf82f7/skills/adaptive-classifierСсылка
87c9669baf85385959f9b0a344dc9dfc8d978f9c
Актуальность поддержки
28.10.2026
Использование
0 загрузок · 0 просмотров
Структура файлов