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.
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 "pts-pivotal-token-search" from https://skillstore.io/skills/lambdasec-pts-pivotal-token-search.md and its manifest at https://skillstore.io/api/skills/lambdasec-pts-pivotal-token-search/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「pts-pivotal-token-search」。 Explain how to compare token events and latent events in my PTS file.
預期結果:
Rank token events by absolute probability change and retain the direction of the shift. Report latent readout scores separately. Do not combine these scales into one ranking.
正在使用「pts-pivotal-token-search」。 Plan my first token search without starting it.
預期結果:
Confirm the model, dataset, device, and time budget. Inspect the installed CLI flags. Propose fewer examples and samples for an initial pass. Request download consent and disclose the expected cost before execution.
正在使用「pts-pivotal-token-search」。 Prepare existing events for a local DPO export.
預期結果:
Link the local events, inspect available export filters, and test DPO export on a small file. Review the sample before scaling up. Do not publish or upload the results.
All 30 static findings are false positives: Markdown backticks, legitimate local PTS workflows, and relevant project links. The skill requires consent for downloads and publishing, prohibits automatic installation, and cautions against unsupported causal claims. No evidence found of prompt injection or unauthorized data transfer; external PTS implementations and hosted services were not audited.
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-pts-pivotal-token-search/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/lambdasec-pts-pivotal-token-search?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/lambdasec-pts-pivotal-token-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/lambdasec-pts-pivotal-token-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/lambdasec-pts-pivotal-token-search.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). pts-pivotal-token-search security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/lambdasec-pts-pivotal-token-search/audits/1@techreport{lambdasec-lambdasec-pts-pivotal-token-search-2026,
author = {lambdasec},
title = {pts-pivotal-token-search security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/lambdasec-pts-pivotal-token-search/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: "pts-pivotal-token-search security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "lambdasec"
date-released: "2026-10-28"
url: "https://skillstore.io/skills/lambdasec-pts-pivotal-token-search/audits/1"
identifiers:
- type: other
value: "skillstore:lambdasec-pts-pivotal-token-search:audit:1"
description: "Skillstore immutable audit report identifier"
Plan a small token or sentence search to identify events associated with changes in task success.
Review existing event files, compare events within one scale, and identify examples that need manual checking.
Link existing events and test a filtered DPO export before processing a larger collection.
Explain the fields in my local PTS events file at [path]. Summarize its scales and model identifiers without running searches or uploading data.
Plan a token search for [model] on [dataset] using [device] within [budget]. Check available flags and ask before downloads or execution.
Review [events path] and plan J-lens enrichment for [model]. Include shuffled controls, consent for downloads, and separate reporting of latent scores.
Design repeated-seed checks and an intervention for [events path], then propose a filtered local DPO export. Separate observational findings from causal evidence.
作者
lambdasec授權
Apache-2.0
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
87c9669baf85385959f9b0a344dc9dfc8d978f9c
維護新鮮度
2026/10/28
使用量
0 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md
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.
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.
使用 SHAP 解釋機器學習模型
由 davila7
機器學習團隊需要清楚了解模型預測背後的原因。此技能可協助選擇 SHAP explainer、建立圖表、進行除錯與公平性檢查，以及設計正式環境的解釋工作流程。
Research Supply-Chain Investment Bottlenecks
由 muxuuu
Broad investment themes often hide the scarce components that control growth. This skill maps value chains, grades evidence, and ranks research priorities with clear risks.
建立可投稿期刊的 Nature 圖表
由 Yuan1z0825
研究人員需要能清楚傳達證據並符合期刊匯出規範的圖表。此技能可將資料集、草稿和圖表構想轉換為結構化的 Python 或 R 工作流程，以產出可直接提交的視覺化成果。
準備學術投稿場域提交文件
由 K-Dense-AI
學術投稿常因各場域的格式規則不同而失敗。此技能提供範本、要求與範例，以加快準備流程。
執行 DiffDock 分子對接工作流程
由 davila7
分子對接設定常因輸入、參數與信心分數難以對齊而失敗。此技能會引導 DiffDock 工作流程，從準備到結果檢閱。
Analyze One Scientific Paper as an Evidence Card
由 yuan1z0825
Scientific papers are difficult to evaluate when claims, methods, and evidence are scattered across sections. This skill creates a structured, traceable Paper Card with explicit limits.