“eval”的搜索结果

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

中文简介正在准备中。当前显示原文说明。

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.

中文简介正在准备中。当前显示原文说明。

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks

中文简介正在准备中。当前显示原文说明。

Systematically evaluate weak, stale, or low-conviction theses for upgrade, monitoring, or closure. Use when user says "prune", "kill list", "clean up theses", "what should I close", or "reduce portfolio".

中文简介正在准备中。当前显示原文说明。

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

中文简介正在准备中。当前显示原文说明。

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

中文简介正在准备中。当前显示原文说明。

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".

中文简介正在准备中。当前显示原文说明。

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

中文简介正在准备中。当前显示原文说明。

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

中文简介正在准备中。当前显示原文说明。

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

中文简介正在准备中。当前显示原文说明。

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

中文简介正在准备中。当前显示原文说明。

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

中文简介正在准备中。当前显示原文说明。

Audit of existing Vue components in the project. Use when reviewing Vue design system consistency, identifying duplicate patterns, evaluating legacy components (Options API), or before implementing something new.

中文简介正在准备中。当前显示原文说明。

Implement React Server Actions in Next.js 14+ for secure, progressively enhanced form handling and server mutations without API routes. Use when handling form submissions, performing server-side mutations, implementing progressive enhancement, creating actions that work without JavaScript, validating data on the server, revalidating cached data after mutations, handling file uploads server-side, implementing optimistic UI updates, or building forms that gracefully degrade without client-side JavaScript.

中文简介正在准备中。当前显示原文说明。

Facilitate ideation, explore alternatives, and refine concepts through structured brainstorming techniques before implementation. Use when starting new projects, designing features, exploring solutions, evaluating tradeoffs, challenging assumptions, generating creative ideas, planning architecture, or refining rough concepts into detailed designs.

中文简介正在准备中。当前显示原文说明。

Research competitors, analyze market positioning, identify differentiators, and understand competitive landscape to inform product strategy and positioning. Use when researching competitors, analyzing features, identifying market gaps, understanding pricing strategies, evaluating competitive advantages, researching market trends, or informing product decisions.

中文简介正在准备中。当前显示原文说明。

Systematically review pull requests, feature implementations, and code changes to ensure quality, maintainability, security, and adherence to best practices. Use when reviewing code before merging, conducting peer reviews, performing self-reviews, auditing code quality, checking for security vulnerabilities, ensuring consistent coding standards, verifying test coverage, assessing performance implications, evaluating architectural decisions, or providing constructive feedback to improve team code quality.

中文简介正在准备中。当前显示原文说明。

Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.

中文简介正在准备中。当前显示原文说明。

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For downloadable content lead magnets (ebooks, checklists, templates), see lead-magnets.

中文简介正在准备中。当前显示原文说明。

Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".

中文简介正在准备中。当前显示原文说明。

Evaluate learning progress, identify blockers, and adjust the learning plan

中文简介正在准备中。当前显示原文说明。

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。