Evaluate and Improve Prompts With Test Cases
Prompt changes can look useful without improving real results. This skill scores examples, proposes revisions, and retains candidates that improve training scores without lowering validation scores.
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "rsi-skill" from https://skillstore.io/skills/lambdasec-rsi-skill.md and its manifest at https://skillstore.io/api/skills/lambdasec-rsi-skill/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
正在使用「rsi-skill」。 Summarize the documented GSM8K optimization example.
預期結果:
正在使用「rsi-skill」。 Initialize a new sentiment classification task.
預期結果:
Most static alerts concern harmless formatting, arithmetic examples, documentation links, or intended backend configuration. Four HTTP request findings expose credentials through unrestricted redirects; a separate model-grading weakness can undermine evaluation integrity. No evidence found of malicious instructions, embedded credentials, or intentional data theft.
這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
https://skillstore.io/skills/lambdasec-rsi-skill/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/lambdasec-rsi-skill?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/lambdasec-rsi-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/lambdasec-rsi-skill/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/lambdasec-rsi-skill.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>lambdasec. (2026). rsi-skill security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/lambdasec-rsi-skill/audits/1@techreport{lambdasec-lambdasec-rsi-skill-2026,
author = {lambdasec},
title = {rsi-skill security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/lambdasec-rsi-skill/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "rsi-skill security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "lambdasec"
date-released: "2026-10-28"
url: "https://skillstore.io/skills/lambdasec-rsi-skill/audits/1"
identifiers:
- type: other
value: "skillstore:lambdasec-rsi-skill:audit:1"
description: "Skillstore immutable audit report identifier"
Compare a classifier prompt against labeled examples and inspect failures before accepting a revision.
Use the bundled math cases to compare prompt variants with numeric checks and a reproducible validation split.
Evaluate instruction text against representative cases and review the proposed changes before applying them.
Help me evaluate this prompt: [prompt]. Initialize a task directory and help me define expected answers. Confirm the backend before sending data.
Evaluate the prompt and cases in [directory] using [approved endpoint and model]. Report the baseline score, failed cases, and scoring methods without revising anything.
Optimize [directory] for up to five rounds using [approved endpoint and model]. Keep the default validation split and copy rejection. Report scores and proposed changes.
Optimize [directory] using [evaluation model] and [proposal model] on [approved endpoint]. Reevaluate the best prompt on [independent test directory]. Review failures before requesting deployment approval.
作者
lambdasec授權
Apache-2.0
Skillstore 修訂
r1
版本提示
作者未聲明版本。
儲存庫
https://github.com/lambdasec/skills/tree/7d791206069498962a85a0f1ba95f7468dcf82f7/skills/rsi-skill引用
87c9669baf85385959f9b0a344dc9dfc8d978f9c
維護新鮮度
2026/10/28
使用量
0 次下載 · 0 次瀏覽
Analyze Local Model Reasoning with PTS
Reasoning traces do not show which events change a model's chance of solving a task. This skill guides PTS searches, event interpretation, and local dataset exports with explicit measurement caveats.
Scan and Triage Code Vulnerabilities with Frame
Security scan results need source review before teams can trust findings or apply fixes. This skill guides Frame scans, evidence-based triage, patch review, and verification.
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.
Run Local Models on Apple Silicon with mlx-optiq
Local model serving requires matching model size, memory limits, and client settings. This skill guides mlx-optiq checks, consent-based server startup, client connections, and performance evaluation.
Créer des agents Claude Code
由 Dami-Randle
Concevoir des agents Claude Code fiables est difficile sans structure. Cette compétence fournit des modèles, des règles de validation et des exemples pour les prompts d’agents, les déclencheurs, les outils et les métadonnées.
Créer une automatisation de tests fiable
由 89jobrien
Les tests faibles ralentissent les livraisons et masquent les régressions. Cette compétence guide la stratégie de test, le TDD, l’automatisation, l’examen de la couverture et les vérifications web avec Playwright.
Concevoir de meilleurs prompts pour les LLM
由 alirezarezvani
La qualité des prompts échoue souvent parce que les exigences, les exemples et les critères d’évaluation ne sont pas clairs. Cette compétence aide les équipes à concevoir, tester et réviser des prompts de production pour Claude, Codex et Claude Code.
Planifier des tests fiables dans toute votre base de code
由 0xDarkMatter
Cette compétence aide les équipes à choisir des stratégies de test, des mocks, des jeux de données, des seuils de couverture et des modèles CI sans mélanger les périmètres de test. Elle fournit à Claude, Codex et Claude Code des recommandations structurées pour les tests unitaires, d’intégration, de bout en bout, TDD e
Concevoir des outils d'agent fiables
由 Asmayaseen
Les agents échouent lorsque les noms d'outils, les entrées, les sorties ou les erreurs sont ambigus. Cette compétence fournit des modèles pratiques pour les descriptions d'outils, les schémas, les formats de réponse et les tests.
Déboguer systématiquement les problèmes logiciels
由 Asmayaseen
La correction non structurée de bugs fait perdre du temps et peut masquer la véritable défaillance. Cette skill guide Claude, Codex et Claude Code dans une analyse des causes racines fondée sur des preuves.