agentsclimarketplace

Context & AI engineering

25,831 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Sentence transformers

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-codex/.agents/skills/ai-research-skills/15-rag/sentence-transformers Skill

    93★ repo

    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.

    The same file is in 4 other repositories

  • 0 autoresearch skill

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/0-autoresearch-skill Skill

    93★ repo

    Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

    The same file is in 2 other repositories

  • Torchtitan

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/01-model-architecture/torchtitan Skill

    93★ repo

    Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

    The same file is in 4 other repositories

  • Prompt guard

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/07-safety-alignment/prompt-guard Skill

    93★ repo

    Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

    The same file is in 2 other repositories

  • Skypilot

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/09-infrastructure/skypilot Skill

    93★ repo

    Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

    The same file is in 6 other repositories

  • Tensorrt llm

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/12-inference-serving/tensorrt-llm Skill

    93★ repo

    Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

    The same file is in 4 other repositories

  • A evolve

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/14-agents/a-evolve Skill

    93★ repo

    Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

    The same file is in 1 other repository

  • Crewai

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/14-agents/crewai Skill

    93★ repo

    Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

    The same file is in 4 other repositories

  • Chroma

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/15-rag/chroma Skill

    93★ repo

    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.

    The same file is in 5 other repositories

  • Pinecone

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/15-rag/pinecone Skill

    93★ repo

    Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

    The same file is in 5 other repositories

  • Qdrant

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/15-rag/qdrant Skill

    93★ repo

    High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

    The same file is in 4 other repositories

  • Sentence transformers

    nota-america/forgecat-agent-profiles/profiles/orchestra-research/ai-research-skills/for-forgecat/skills/ai-research-skills/15-rag/sentence-transformers Skill

    93★ repo

    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.

    The same file is in 4 other repositories

  • Context7 mcp

    nota-america/forgecat-agent-profiles/profiles/upstash/context7/for-forgecat/skills/context7-mcp Skill

    93★ repo

    This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

    The same file is in 3 other repositories

  • Running claude code via litellm copilot

    nota-america/forgecat-agent-profiles/profiles/xixu-me/skills/for-claude/.claude/skills/running-claude-code-via-litellm-copilot Skill

    93★ repo

    Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.

  • Running claude code via litellm copilot

    nota-america/forgecat-agent-profiles/profiles/xixu-me/skills/for-codex/.agents/skills/running-claude-code-via-litellm-copilot Skill

    93★ repo

    Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.

  • Running claude code via litellm copilot

    nota-america/forgecat-agent-profiles/profiles/xixu-me/skills/for-forgecat/skills/running-claude-code-via-litellm-copilot Skill

    93★ repo

    Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.

    The same file is in 1 other repository

  • Skill evaluator

    HeshamFS/materials-simulation-skills/skills/meta/skill-evaluator Skill

    93★ repo

    Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, optimize a skill's triggering, or set up an eval suite — even if the user just says "is this skill any good," "does my skill work," or "benchmark this skill." Drives Claude Code, OpenAI Codex, Antigravity (agy), Cursor, GitHub Copilot, Amp, opencode, or Grok in headless mode.

    The same file is in 1 other repository

  • Simulation orchestrator

    HeshamFS/materials-simulation-skills/skills/simulation-workflow/simulation-orchestrator Skill

    93★ repo

    Orchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hypercube sampling), initialize and track batch job campaigns, monitor job completion status, and aggregate results with summary statistics across all runs. Use when running a parameter study across dt, kappa, or other simulation inputs, managing dozens or hundreds of simulation configurations, combining outputs from completed batch runs to find the best result, or automating the generate-run-collect workflow for systematic studies, even if the user only says "I need to try many parameter combinations" or "how do I organize a sweep."

    The same file is in 1 other repository

  • Benchmark and mms planner

    HeshamFS/materials-simulation-skills/skills/verification-validation/benchmark-and-mms-planner Skill

    93★ repo

    Plan verification and validation campaigns for simulation codes using manufactured solutions, canonical benchmark problems, grid/time refinement, uncertainty propagation, and pass/fail acceptance criteria. Use when an agent needs to prove a solver, model, or result is trustworthy rather than only plausible.

    The same file is in 1 other repository

  • Mathodology skill authoring

    sweetcornna/mathodology/.claude/skills/mathodology-skill-authoring Skill

    93★ repo

    Use when adding, updating, validating, or reviewing Mathodology project skills, SKILL.md files, or agents/openai.yaml metadata.

  • Write agent memory system review

    zby/commonplace/kb/instructions/write-agent-memory-system-review Skill

    93★ repo

    Write or update a local code-grounded agent memory system review from a GitHub repository reference, including checkout refresh, optional sub-agent drafting, semantic QA, and validation.

  • Claude code skill creator

    zby/commonplace/kb/work/skill-creator-distillation/sources/claude-code-skill-creator Skill

    93★ repo

    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.

  • Codex skill creator

    zby/commonplace/kb/work/skill-creator-distillation/sources/codex-skill-creator Skill

    93★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

  • Run2 parallel orchestration

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run2_parallel-orchestration Skill

    93★ repo

    Structured approach to grid search with nested loops and parallelization.

  • Run1 llm token tracking

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/enterprise-information-search/run1_llm-token-tracking Skill

    93★ repo

    Extracts and tracks the consumed token usage from an LLM API response to monitor API cost and utilization.

  • Mcp builder

    dkyazzentwatwa/chatgpt-skills/mcp-builder Skill

    no license91★ repo

    Plan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.

  • Skill creator

    dkyazzentwatwa/chatgpt-skills/skill-creator Skill

    no license91★ repo

    Create or update agent skills with concise SKILL.md instructions, bundled resources, agent metadata, validation, and packaging. Use when building or refactoring skills.

  • Prompt pack

    nelsonwerd/idea-to-ship-skills/skills/prompt-pack Skill

    91★ repo

    Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts, each run in its own fresh chat so a single change never dies to a context/token limit. Also writes paste-ready handoff briefings to resume a dying chat or relay work to another tool (e.g. Codex). ALWAYS invoke when the user says any of "make a prompt pack", "turn this into prompts", "break this into phases", "prompts I can run in separate chats", "I'm running out of tokens/context", "write me a handoff", "a prompt I can paste into a new chat", "this is too big for one chat", "build plan I can hand off", or "execute Pxx / phase X from the pack". Also invoke proactively when a requested change is too large or too risky to finish safely in one session and should be decomposed into ordered, verifiable steps.

    The same file is in 1 other repository

  • Instrument agent

    monte-carlo-data/mc-agent-toolkit/skills/instrument-agent Skill

    91★ repo

    Instrument a new AI agent in a Python codebase for Monte Carlo Agent Observability. Detects AI libraries, installs the Monte Carlo OpenTelemetry SDK, and proposes tracing setup and decorator placements as diffs. Asks before editing any file.

  • Reinforce agent

    monte-carlo-data/mc-agent-toolkit/skills/reinforce-agent Skill

    91★ repo

    Reinforces an AI agent by turning Monte Carlo's reinforcement loop diagnosis into code fixes. Reads the daily reinforcement loop report for an agent's workflows, ranks the diagnosed issues, proposes what to fix, and — with the user's approval at each step — opens a pull request. Activates on "fix my agent", "improve my agent's health", "reinforce my agent", "what should I fix in my agent". Not for investigating a specific agent alert or trace (monte-carlo-troubleshoot-agent-traces), creating agent monitors (monte-carlo-monitoring-advisor), or instrumenting a new agent (monte-carlo-instrument-agent).

  • Troubleshoot agent traces

    monte-carlo-data/mc-agent-toolkit/skills/troubleshoot-agent-traces Skill

    91★ repo

    Troubleshoots Monte Carlo AI agent alerts and traces — eval score drops, latency/token spikes, trajectory and validation breaches. Not for data incidents (monte-carlo-analyze-root-cause) or monitor creation (monte-carlo-monitoring-advisor).

  • Claude skill

    HKUST-KnowComp/DeepRefine-Skill/deeprefine_skill/claude_skill Skill

    91★ repo

    Claude Code adapter for the DeepRefine agent-native refinement loop. Use when the user invokes /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

  • Codex skill

    HKUST-KnowComp/DeepRefine-Skill/deeprefine_skill/codex_skill Skill

    91★ repo

    Codex adapter for the DeepRefine agent-native refinement loop. Use when the user invokes $deeprefine or /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

  • Deeprefine

    HKUST-KnowComp/DeepRefine-Skill/deeprefine_skill/gemini_extension/skills/deeprefine Skill

    91★ repo

    Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

  • Deeprefine

    HKUST-KnowComp/DeepRefine-Skill/skills/deeprefine Skill

    91★ repo

    Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

  • Delegation framework

    mfwarren/entrepreneur-claude-skills/skills/operations/delegation-framework Skill

    90★ repo

    Production-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadership. 24 skills built by a founder, for founders.

  • Skill creator

    aws-samples/sample-strands-agents-agentskills/skills/skill-creator Skill

    90★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Knowledge base update

    omergocmen/vibe-coder-kit/.agent/skills/knowledge-base-update Skill

    89★ repo

    Use this skill whenever you learn something important during a conversation: a key architectural decision, a project-specific convention, a bug root-cause, a 3rd-party API quirk, or any fact that would help a future agent avoid re-doing the same research. Writes structured entries to the project's knowledge base so that context persists across conversations and agents.

  • Prompt enhancer

    omergocmen/vibe-coder-kit/.agent/skills/prompt-enhancer Skill

    89★ repo
  • Hk skill creator

    deepklarity/harness-kit/.claude/skills/hk-skill-creator Skill

    89★ repo

    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. Triggers on: 'create a skill', 'new skill', 'make a skill for', 'improve this skill', 'test this skill', 'skill eval', 'optimize skill description', or /hk-skill-creator.

  • Pydantic ai agent creation

    existential-birds/beagle/plugins/beagle-ai/skills/pydantic-ai-agent-creation Skill

    88★ repo

    Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

    The same file is in 2 other repositories

  • Agent architecture analysis

    existential-birds/beagle/plugins/beagle-analysis/skills/agent-architecture-analysis Skill

    88★ repo

    Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on "analyze agent architecture", "12-factor audit", "how compliant is this agent", or "evaluate this LLM app". Also applies when comparing frameworks or planning agent improvements. Not for quick checklists \u2014 this performs deep per-factor codebase analysis with file-level evidence.

  • Artifact analysis

    existential-birds/beagle/plugins/beagle-analysis/skills/artifact-analysis Skill

    88★ repo

    Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: "analyze these docs", "scan my project for context", "read the docs folder", "summarize what's in .beagle/concepts/", "extract context from docs/", "what's in this folder", "go read everything in X and tell me what's there". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

  • Llm judge

    existential-birds/beagle/plugins/beagle-analysis/skills/llm-judge Skill

    88★ repo

    Use when comparing two or more code implementations against a spec or requirements doc. Triggers on "which repo is better", "compare these implementations", "evaluate both solutions", "rank these codebases", or "judge which approach wins". Also covers choosing between competing PRs or vendor submissions solving the same problem. Does NOT review a single codebase for quality \u2014 use code review skills instead. Does NOT evaluate strategy docs \u2014 use strategy-review. Requires a spec file and 2+ repo paths.

  • Web research

    existential-birds/beagle/plugins/beagle-analysis/skills/web-research Skill

    88★ repo

    Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: "research X for me", "do web research on", "look up sources for", "find citations for", "gather evidence on", "what does the web say about X". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

  • Fix llm artifacts

    existential-birds/beagle/plugins/beagle-core/skills/fix-llm-artifacts Skill

    88★ repo

    Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.

  • Llm artifacts detection

    existential-birds/beagle/plugins/beagle-core/skills/llm-artifacts-detection Skill

    88★ repo

    Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

  • Prompt improver

    existential-birds/beagle/plugins/beagle-core/skills/prompt-improver Skill

    88★ repo

    Optimize prompts for code-related tasks following prompt-engineering best practices. Use when refining prompts for implementation, debugging, refactoring, code review, or testing.

  • Review llm artifacts

    existential-birds/beagle/plugins/beagle-core/skills/review-llm-artifacts Skill

    88★ repo

    Detects common LLM coding agent artifacts across four categories (tests, dead code, abstraction, style) over the project or changed files — using parallel subagents when the agent supports them, otherwise four sequential passes. Scans files changed since main by default; use --all for full-project scan. Triggers on LLM cruft cleanup, agent-generated code review, dead code sweeps, test-quality passes, or when the user asks to scan the whole repo.

  • Skill builder

    existential-birds/beagle/plugins/beagle-core/skills/skill-builder Skill

    88★ repo

    Create Agent Skills with best practices, structure, validation, and testing. Use when designing or refining skills, prompts, references, or supporting files.

  • Subagent prompt

    existential-birds/beagle/plugins/beagle-core/skills/subagent-prompt Skill

    88★ repo

    Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated execution. Use when the user wants to execute discussed/planned work in a new session, run a job to completion via sub-agents, or generate a portable handoff prompt with per-task verification. Assumes the target session supports sub-agents. Triggers on "subagent-prompt", "give me a prompt to run this in a new session", "hand this off to sub-agents", "execute this with sub-agents".

  • Verify llm artifacts

    existential-birds/beagle/plugins/beagle-core/skills/verify-llm-artifacts Skill

    88★ repo

    Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding. Use after a review run, when the user wants to reduce false positives, before fix-llm-artifacts on dead code, or when validating a full-project scan.

  • Dmux workflows

    mturac/everything-openai-codex/skills/dmux-workflows Skill

    88★ repo

    Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across OpenAI Codex, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

  • Eval harness

    mturac/everything-openai-codex/skills/eval-harness Skill

    88★ repo

    Formal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principles

  • Mcp server patterns

    mturac/everything-openai-codex/skills/mcp-server-patterns Skill

    88★ repo

    Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

  • Mcp server patterns

    mturac/everything-openai-codex/.cursor/skills/mcp-server-patterns Skill

    88★ repo

    Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

  • Agentic engineering

    mturac/everything-openai-codex/.kiro/skills/agentic-engineering Skill

    88★ repo

    Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents perform most implementation work and humans enforce quality and risk controls.

  • Agent architecture audit

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-architecture-audit Skill

    88★ repo

    エージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。

  • Agent eval

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-eval Skill

    88★ repo

    カスタムタスクでコーディングエージェント(OpenAI Codex、Aider、Codex など)をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定します

  • Agent harness construction

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-harness-construction Skill

    88★ repo

    AI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。