Results for “eval”

Discover, evaluate, install, and wrap external agent skills from ClawHub registry, skillflag-compliant CLI tools, and GitHub repos. Use when asked to find new capabilities, install a skill, browse what's available, or package a local skill for sharing.

Agent profile for design AI/ML features, retrieval, model calls, structured outputs, cost controls, evals, and fallbacks. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Stacks: Bitcoin smart contract layer with Clarity language, sBTC for native peg, Nakamoto upgrade for fast finality, PoX (Proof of Transfer) consensus. USE WHEN: building Bitcoin smart contracts, integrating sBTC, evaluating Stacks vs RSK / EVM alternatives.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.

Trains, evaluates, exports, and runs inference for Visual ChangeNet models used in AOI defect detection, comparing image pairs for PASS/NO_PASS classification or change-segmentation masks.

Identify the first beachhead market segment for a product launch by evaluating segments against burning pain, willingness to pay, winnable market share, and referral potential.

Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.

Systematically evaluates evidence to determine which threat actor is responsible for a cyber operation using the Diamond Model and Analysis of Competing Hypotheses.

Assess security of SCADA HMI systems by evaluating authentication, communication, web interfaces, and hardening against IEC 62443 and NIST SP 800-82 guidelines.

Conducts end-to-end user research, from study design through behavioral insight synthesis, using frameworks like Nielsen's Heuristics, SUS, and User Journey Mapping.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

Use when symbolic mathematics must cross into NumPy vector evaluation or SciPy numerical algorithms: lambdify contracts, domains, dtypes, parameters, residuals, tolerances, and symbolic-versus-numeric verification. Do not use for work confined entirely to one of those libraries.

Evaluate Google AI Overview presence and click-cannibalization risk for BID-passing Pleasur.ai Stage 01 keyword candidates using current Ahrefs evidence. Use after BID validation and before prioritization, in either presence-only or human-approved deep-completeness mode.

The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions. Use when the learner wants to test their understanding — teaching forces a different kind of organisation than studying.

Comprehensive paid media auditor who systematically evaluates Google Ads, Microsoft Ads, and Meta accounts across 200+ checkpoints spanning account structure, tracking, bidding, creative, audiences, and competitive positioning. Produces actionable audit reports with prioritized recommendations and projected impact.

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

Install and route through OpenSpace, the skill management layer for AI agents, so a host agent can retrieve/rank/load the right SKILL.md out of this jeo-skills catalog (~150 installed skills), then evaluate skill quality from real execution evidence and evolve skills via FIX/DERIVED/CAPTURED updates. Covers install-as-skill-finder, retrieve-a-skill, evaluate-quality, evolve-skills, and local-first hub share/import. Triggers on: openspace, skill finder, skill retrieval, find the right skill, rank skills, skill discovery, skill quality, evolve skill, FIX DERIVED CAPTURED, skill hub, openspace-mcp, DiscoverSkills, skill-discovery, delegate-task.

Sets up Google's agents-cli toolkit and guides through the full agent development lifecycle: scaffold, build, evaluate, deploy, publish, and monitor on Gemini Enterprise Agent Platform.

Evaluates Google Cloud workloads against the Performance Optimization pillar of the Well-Architected Framework, providing actionable recommendations for resource allocation, modular design, elasticity, and monitoring.

Execute QA test plans on Holoscan Sensor Bridge hardware by reading a test document, filtering tests by setup, running automatable tests with pass/fail evaluation, and producing a structured report.

Trains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Ingests, normalizes, and enriches structured and unstructured threat intelligence feeds into STIX 2.1 format, evaluating feed quality and deduplicating indicators for distribution to SIEM, firewall, and EDR platforms.

Assess SSL/TLS server configurations using the sslyze Python library to evaluate cipher suites, certificate chains, protocol versions, HSTS headers, and known vulnerabilities like Heartbleed and ROBOT.

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Benchmarks mobile GUI agents on multi-step tasks across 20 Android apps, measuring task completion and essential-state navigation with Task Success Rate and Essential State Achieved Rate.

Use when planning a PLDI campaign across its annual clock — backward-planning from the November deadline through winter reviewing, the February response window, March notification, post-acceptance artifact evaluation, PACMPL production, and the June conference, with owners for each deliverable.

Agent profile for evaluate and implement no-code/low-code workflows, forms, automations, Airtable/Sheets/Zapier-like patterns. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

Guides the creation of high-quality MCP servers that enable LLMs to interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation across multiple programming languages.

Assess whether your product work is AI-first or AI-shaped, evaluate maturity across five key competencies, and get recommendations on which capability to build next.

Evaluates a local pre-trade checklist before manual order entry, blocking planless, oversized, revenge-risk, market-regime-blocked, or circuit-breaker-blocked entries while journaling the decision for later review.

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.

After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.