Results for “l-eval”

Use when forecasting resource needs, evaluating if current capacity is sufficient for planned work, or sizing systems for expected load. This skill provides procedures for estimating, planning, and monitoring capacity to prevent resource shortages.

Evaluate UI designs through an emotional resonance lens, identifying what's missing and prescribing specific changes at the copy, motion, and interaction layer.

Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews. Triggers on keywords like: job posting, job application, CV, cover letter, resume, interview prep, job fit, career, application, apply, ansøgning, stilling

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in...

Benchmarks large audio-language models against adversarial audio attacks using the CAA dataset, computing WER, ROUGE-L, cosine similarity, and coherence scores to assess robustness in conversational settings.

Analyze and optimize content for visibility in AI Overviews, ChatGPT, Perplexity, and other AI search systems by evaluating citability, structure, authority, and technical accessibility.

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.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Validates the Emotional Attitude Score (EAS) metric by measuring its consistency with human judgment on word-level sentiment polarity, using the AmbGIMT dataset and pairwise score comparisons.

Evaluate a screen's information density by analyzing cognitive load, content prioritization, scanning patterns, and progressive disclosure, with actionable fixes for each dimension.

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.

Model software around the business domain using bounded contexts, aggregates, and ubiquitous language, with scoring and diagnostic tools for evaluating domain model quality.

Guides the creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation.

Route academic-figure work into the lightest workable PaperBanana mode instead of jumping straight to a full multi-agent generation run. Use when the user needs publication-quality methodology diagrams, statistical plots, figure evaluation, polishing an existing figure, batch/sweep generation, or a full-paper figure package from text or PDF. Even if the user does not say "paperbanana" — also triggers on: academic figure, methodology diagram, publication figure, generate diagram from paper, statistical plot from CSV, figure evaluation, polish figure, NeurIPS/ICML figure, arxiv illustration, plan-then-refine diagram pipeline.

Evaluates Power BI data model architecture, relationships, storage modes, and performance to identify optimization opportunities and ensure adherence to best practices.

Discovers and evaluates community skills from skills.sh and awesome-openclaw-skills when local skills don't cover a need, scoring credibility and installing top recommendations with permission.

Route research prompts to evidence, retrieval, scraping, data, market, or scientific research skills. Use when prompts mention deep research, current facts, citations, Exa, iterative retrieval, search-first, scraping, data pipelines, PubMed, USPTO, gget, literature review, or scholar evaluation.

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.

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

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.

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.

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.

Spark by Lightspark: statechain-derived L2 with FROST threshold signatures, leaf architecture, Lightning compatibility. Beta launched April 2025; managed by Spark Operators (SOs). USE WHEN: integrating with Spark, evaluating Spark vs Ark vs Lightning, designing leaf-based UTXO trees.

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.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.

Reads invocation logs from eval_tracker and recommends which of the 50+ skills to prune or consolidate. Run monthly to keep the skill surface tight. Triggers: "audit skills", "prune skills", "which skills do I never use", "skill cleanup".

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 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.

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.

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.

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.

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.

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

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.

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.