Results for “validation”

Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Automate email validation and Zerobounce operations through Composio's toolkit via Rube MCP.

Automates phone number validation tasks through Composio's Realphonevalidation toolkit via Rube MCP.

Automate email validation and mailbox verification tasks using the Mailboxlayer API through Composio's Rube MCP integration.

Extract structured data from LLM responses with Pydantic validation, automatic retries, and streaming support across multiple providers.

`analysis-agent`/`task-agent`/`review-agent`: use when form fields, validation, async checks, submit states, or recovery change; skip when form behavior is unaffected.

End-to-end review of agent validation system for live trader readiness. Audits gating thresholds, model health wiring, live feedback loop, notebook consistency.

Zod schema validation and type inference.

Automate Bouncer email validation operations through Composio's Bouncer toolkit via Rube MCP, with dynamic tool discovery and connection management.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Design and ship production-ready MCP servers from OpenAPI contracts instead of hand-written tool wrappers. Supports Python and TypeScript, schema validation, and safe evolution.

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

Find and validate email addresses using Snov.io via Chrome DevTools MCP. Takes LinkedIn profile URLs and returns verified emails. Replaces ZeroBounce.

`analysis-agent`/`task-agent`/`review-agent`: use for input authority, parsing, canonicalization, bounds, state checks, writable fields, rejection, or external-response changes.

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

Use before delivering any work product to validate quality. This skill provides a standardized checklist that every agent must complete before marking work as done, ensuring consistent quality across all deliverables regardless of agent or company.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Security patterns for MCP servers including OAuth 2.0, rate limiting, input validation, and audit loggingUse when "mcp security, mcp authentication, mcp oauth, mcp rate limit, secure mcp server, mcp, security, oauth, authentication, rate-limiting, validation" mentioned.

End-to-end Kaggle competition workflow for scored submissions, covering code competitions, validation, metrics, public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling, multi-notebook architectures, Kaggle GPU offload, and hidden-test debugging.

Claim-driven 实验设计：界定目标 claims → 设计实验块（baseline/validation/ablation/robustness）→ 构建执行顺序 → 可选 Review LLM review → 写入 wiki

Creates cross-platform agent skills from workflow descriptions, files, URLs, or screenshots. Supports single skills, multi-agent suites, template-based creation, cross-platform export, spec validation, and security auditing of third-party skills before install.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

MCP tools for loading, saving, and validating claude-flow configuration with path traversal protection and schema validation

Data Quality Specialist IA — Expert en qualité des données (profiling, cleaning, déduplication, validation de schéma, Great Expectations)

Add safety guardrails to an LLM app — prompt-injection defense, output validation, PII handling, and a clear refusal policy.

Plans parallel agents or worktrees with isolated ownership, validation lanes, and merge rules. Use only for safely separable work.

Use the host-side `agent-browser` CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

Patterns for Bayesian inference in R using brms, including multilevel models, DAG validation, and marginal effects. Use when performing Bayesian analysis.