856 skills · sorted by relevance
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
Inspect suspicious PDFs without opening them in a reader. Use PDFiD, pdf-parser, and peepdf to examine internal objects, extract scripts, embedded files, and URLs, and document how the suspected attack works.
Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
The English summary is being prepared. Showing the original description.
Inspect suspicious PDFs without opening them in a document viewer. Use peepdf, pdfid, and pdf-parser to examine internal objects, extract embedded code and files, and report threat indicators such as URLs and hashes.
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.
The English summary is being prepared. Showing the original description.
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.
The English summary is being prepared. Showing the original description.
Use when assigning a confidence level to an analytical judgment, the user asks "how confident are we?" / "what is the confidence on X?", or the orchestrator's tradecraft pipeline calls for a confidence level before publishing. Provides three named levels (High, Moderate, Low) with 0-100 score ranges aligned to STIX, and the rule that confidence cannot exceed what the weakest load-bearing claim supports.
The English summary is being prepared. Showing the original description.
Expert knowledge for Azure Confidential Ledger development including troubleshooting, decision making, security, integrations & coding patterns, and deployment. Use when configuring ACL auth/attestation, integrating with Blob/Cosmos, using MST payloads, or deploying via ARM/Terraform, and other Azure Confidential Ledger related development tasks. Not for Azure Confidential Computing (use azure-confidential-computing), Azure Key Vault (use azure-key-vault), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Payment Hsm (use azure-payment-hsm).
The English summary is being prepared. Showing the original description.
Guides compliance with India's Digital Personal Data Protection Act 2023. Covers consent manager registration, data fiduciary obligations under Sections 4-7, significant data fiduciary requirements under Section 10, data principal rights, and Board enforcement framework. Keywords: DPDP Act, India data protection, consent manager, data fiduciary, significant data fiduciary, data principal rights.
The English summary is being prepared. Showing the original description.
Process calibrated one-dimensional NMR signals into spectra, candidate peaks, and signed integration results. Supports manual phase adjustment, baseline correction, and recorded processing settings so results can be reviewed and reproduced.
Generate candidate positions and orientations for small molecules binding to proteins with DiffDock and DiffDock-L. Prepare single or batch docking runs, organize predicted poses by model confidence, and review validation needs without treating confidence as binding affinity.
Compare evidence from cyber operations to assess which attacker may be responsible. Weigh shared infrastructure, attack methods, malware similarities, timing, and language clues against competing explanations, then report attribution findings with justified confidence levels.
Expert knowledge for Azure Confidential Computing development including decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using SGX/SEV-SNP, AKS confidential containers, attestation/SKR, Fortanix CCM, or SGX capacity planning, and other Azure Confidential Computing related development tasks. Not for Azure Enclave (use azure-enclave), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Cloud Hsm (use azure-cloud-hsm), Azure Payment Hsm (use azure-payment-hsm).
The English summary is being prepared. Showing the original description.
Reads model uncertainty from token log-probabilities. Covers collecting logprobs and aggregating multi-token labels, confidence tiers and margins for triage, calibration assessment with ECE, Brier scores, and reliability diagrams against human labels, responsible downstream use of confidence, and reproducibility archives. Use when the user asks about classifier confidence by item, logprobs, top-k tokens, calibration, ECE, Brier, reliability diagrams, or routing low-confidence cases to human review. Codebook and validation design go to text-classification.
The English summary is being prepared. Showing the original description.
VRChat エコシステムツール（ModularAvatar / liltoon / VRCFury / AvatarOptimizer 等）の ナレッジを 4 フェーズで段階的に調査・検証し `knowledge/*.md` に再現可能な形で蓄積する。 ソースコード読解 → inspect 実測まで進めると confidence を `high` に昇格できる。 トリガー: 新しい VRChat コミュニティツールに初めて遭遇した、 既存ナレッジの confidence が low で作業に支障がある、 ユーザーから「このツールについて調べて」と依頼された場合。
The English summary is being prepared. Showing the original description.
Design text extraction for forms, invoices, and quizzes using regex, rules that match text patterns. Check extraction confidence and send uncertain items to an LLM for review, with guidance on testing and tracking processing costs.
Coordinate Paperclip vulnerability response from confidential report review and private fixes to local testing, CVE identifier requests, advisory publication, and immediate security releases, with human assistance for reporter communication.
Compare a PPTX exported from HTML with its source slides to find cropped text, footer overlaps, and lost styling. Identify shared causes, revise layout rules, and re-export the deck with automated checks for content extending beyond slide boundaries.
Assess a repository without changing it and report its type, suggested agent roles, risk, MCP connections, test confidence, and publication readiness. Use the results for setup decisions, comparisons over time, or automated risk checks in CI.
Design a role permission matrix showing which business areas each role should view or edit, including confidentiality levels. Get a review workflow and, on request, empty CSV templates, SQL table definitions, JSON Schema, or Notion mappings.
Draft a Confidential Information Memorandum, a detailed company document for prospective buyers in an M&A sale. Organize business, market, customer, and financial information into a Word document with charts and a separate Excel financial appendix.
Set up Cisco Duo multi-factor authentication for VPN, RDP, SSH, and web applications. Configure access rules based on users and device health, introduce security keys, and establish authentication monitoring and emergency access procedures.