620 个 · 按相关度排序
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
中文简介正在准备中。当前显示英语简介。
Set up an email reporting button and an automated security response workflow. Classify reported messages, extract attack indicators, remove confirmed phishing emails, and send feedback to the people who reported them.
中文简介正在准备中。当前显示英语简介。
Observe malware in an isolated Cuckoo Sandbox environment and review its processes, network traffic, and system changes. Use the findings to trace infection stages, identify persistence mechanisms, and extract indicators of compromise for behavioral reports.
中文简介正在准备中。当前显示英语简介。
Build safety checks for LLM prompts and responses using Meta's LlamaGuard moderation model. Classify potentially harmful content, block flagged messages, serve checks through an API, and integrate them with NeMo Guardrails.
中文简介正在准备中。当前显示英语简介。
Build Python workflows that constrain language model output using text patterns and grammar rules. Generate structured JSON, restrict classifications to allowed labels, extract information, and combine reusable generation steps with loops and tool selection.
中文简介正在准备中。当前显示英语简介。
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
中文简介正在准备中。当前显示英语简介。
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
中文简介正在准备中。当前显示英语简介。
Consolidate inconsistent gbrain page types into the standard gbrain-base-v2 classification. Preview proposed changes, convert redirect pages into aliases and relationship pages into links, then verify the migration with original type information retained for rollback.
中文简介正在准备中。当前显示英语简介。
Organize the outputs of a substantial work session into linked knowledge pages with sources. A seven-phase review checks classification rules, identifies reusable workflows, audits overlapping skills, and verifies that saved pages and skills can be found.
中文简介正在准备中。当前显示英语简介。
Triage a GitHub issue by reviewing its discussion, related issues, and fixing pull requests. Publish a concise comment with classification, severity, evidence, and the next action, then update a small set of triage labels.
中文简介正在准备中。当前显示英语简介。
Review open Mastra GitHub issues and trace reported defects to source code. Apply the @mastra/core label to confirmed core bugs, report uncertain ownership, and summarize whether fixes are active, stale, or unclaimed.
中文简介正在准备中。当前显示英语简介。
Route enterprise research questions to specialized skills for clinical studies, R&D finance, market research, or user research. Receive a concise digest of findings, next actions, output files, and assumptions that need human review.
中文简介正在准备中。当前显示英语简介。
Routes regulatory and quality management requests to one of 15 specialist skills. Helps HealthTech and MedTech teams select the right workflow for audits, medical device regulations, information security, privacy, or AI compliance.
中文简介正在准备中。当前显示英语简介。
Plan and conduct internal audits for medical device quality management systems under ISO 13485. Organize evidence, classify findings, verify corrective and preventive actions, and prepare for external audits with structured checklists and risk-based scheduling.
中文简介正在准备中。当前显示英语简介。
Organize EU AI Act compliance work with references to Articles and Annexes. Classify AI systems by risk, plan conformity assessments that check regulatory requirements, prepare technical documentation checklists, and map obligations and deadlines to organizational roles.
中文简介正在准备中。当前显示英语简介。
Check Agent Skills for documentation structure and Python script behavior, then score quality and security posture. Get grades and improvement priorities, and use pass criteria in pre-commit checks or continuous integration, which runs checks automatically.
中文简介正在准备中。当前显示英语简介。
Plan and analyze A/B tests, prepare tabular data, and train and evaluate prediction models. Estimate intervention effects from observational data, track model experiments with MLflow, and translate statistical findings into business decisions.
中文简介正在准备中。当前显示英语简介。
Organize responses to service outages and degraded performance, from initial assessment through recovery review. Classify severity, reconstruct event timelines, draft stakeholder updates, and create response guides and follow-up actions based on incident findings.
中文简介正在准备中。当前显示英语简介。
Review an AI system's EU AI Act readiness through six structured questions. Produce an article-cited assessment covering risk classification, conformity checks, organizational obligations, transparency, and general-purpose models, with gaps and three prioritized actions.
中文简介正在准备中。当前显示英语简介。
Review an AI plan through six questions covering evaluation examples, error targets, fallback behavior, regulatory risk, model choices, costs, and hiring. Produce a structured verdict with gaps to address and three concrete next steps.
中文简介正在准备中。当前显示英语简介。
Support startup AI strategy by comparing API use, fine-tuning—additional training of an existing model—and in-house development. Assess three-year costs, regulatory risk, self-hosting breakeven points, and hiring priorities to inform leadership decisions.
中文简介正在准备中。当前显示英语简介。
Investigate Apache ShardingSphere issues using official documentation, code, tests, and issue discussions. Distinguish bugs, unsupported usage, duplicates, and enhancement requests, then draft a concise maintainer-style reply explaining the evidence and next action.
中文简介正在准备中。当前显示英语简介。
Import existing notes and agent instructions into LifeOS by splitting content into sections and proposing destinations. Review uncertain classifications, approve selected groups, and retain source information alongside the imported material.
中文简介正在准备中。当前显示英语简介。
Map sensitive data across the systems you manage, explore what a compromised asset could expose, and maintain a risk register. Record likelihood, impact, owners, mitigations, and review dates to support ongoing security planning.
中文简介正在准备中。当前显示英语简介。