Results for “e-e-a-t”

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. Use when a student wants help understanding or reviewing a topic — this skill ensures the AI works from what the learner already knows.

Automate OpenAI API operations: generate text and multimodal responses with structured output, create embeddings, generate images, and list models via the Composio MCP integration.

OWL v5.2 — Pure contrarian. One scanner, one thesis: the crowd is wrong. Monitors crowding across top 30 assets (funding extremity, OI concentration, SM tilt). When crowding persists 4+ hours AND exhaustion signals fire (volume declining, price stalling, RSI divergence), enters AGAINST the crowd to ride the liquidation unwind. 1-2 trades per day max. Re-crowding exit: if the crowd comes back, thesis is dead, exit immediately. DSL High Water Mode (mandatory). The patient predator. v5.2: funding floor lowered from 20% to 12% so the five-factor scoring model actually runs. Added observability logging (top 3 crowding scores per scan cycle).

Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking

Automate Honeybadger error monitoring operations through Composio's Honeybadger toolkit via Rube MCP.

Execute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent itself, fix bugs, add features, or modify the bot code. This is a COMMAND HANDLER, not a script executor.

Evaluates computational throughput and real-time efficiency of embedded CPU and GPU platforms by measuring peak FLOPS via a matrix rotation kernel and assessing inference latency and power consumption on a robotic vision pipeline.

Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Benchmarks LLM agents fine-tuned with the Agent Data Protocol across software engineering, web browsing, OS/database tool use, and reasoning tasks, reporting unit test pass rates and task success rates.

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.

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

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".

Automate video editing and media processing tasks using Shotstack through Composio's Rube MCP integration.

Integrates with the OpenAI API to build AI-powered applications using GPT models, embeddings, and function calling.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.

Design deliberately flawed examples that develop error-detection skills and deepen understanding. Use when students make characteristic errors and need practice spotting mistakes.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

You are an expert in Viem, the TypeScript interface for Ethereum that provides low-level, type-safe primitives for interacting with the blockchain. You help developers build dApps, scripts, and backends that read blockchain data, send transactions, interact with smart contracts, and handle wallet connections — with full type inference from ABIs, tree-shakeable modules, and zero dependencies beyond noble cryptography.

Filters and ranks trending Hugging Face models, datasets, and spaces by novelty and significance, providing a 'why notable' explanation for each pick.

This skill enables comprehensive control and inspection of the Chrome browser without extensions, utilizing the Chrome DevTools Protocol via chrome-devtools-mcp. Use it for advanced browser automation, performance analysis, debugging network requests, taking screenshots, and interacting with web pages. Triggers include explicit requests to browse, automate, debug, or analyze Chrome's behavior, or any task requiring headless/direct browser interaction.

You are an expert in LLM observability and evaluation. You think in terms of traces, spans, and metrics. You know that LLM applications need monitoring just like traditional software - but with different dimensions (cost, quality, latency).

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Model cap tables, dilution scenarios, and vesting schedules for startups. Use when planning fundraising, pricing options, or tracking equity.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Framework autônomo de agente de IA biomédica para executar tarefas de pesquisa complexas em genômica, descoberta de fármacos, biologia molecular e análise clínica. Use esta skill ao conduzir pesquisa biomédica em múltiplas etapas, incluindo design de triagem CRISPR, análise de RNA-seq de células únicas, previsão ADMET, interpretação GWAS, diagnóstico de doenças raras ou otimização de protocolos de laboratório. Aproveita o raciocínio de LLM com execução de código e bancos de dados biomédicos integrados.

Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair. Load when a run failed, results are wrong, or the user asks what went wrong in an agent session. Also triggers on "localize the fault", "first incorrect step", "debug this run", "trace attribution", "why did the agent fail", or after run-trace captures errors. Pairs with debug-and-fix for code defects and dynamic-routing for plan faults.

Convert daily market observations and news reactions into structured edge hints, with optional LLM augmentation, outputting a canonical hints.yaml for downstream concept synthesis.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Maps a described workflow to the right ECC command-group with run-order and stop condition, and browses all command-group recipe families.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.