Context & AI engineering
25,815 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
Performing memory forensics with volatility3
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/performing-memory-forensics-with-volatility3 Skill
48★ repoAnalyze volatile memory dumps using Volatility 3 to extract running processes, network connections, loaded modules, and evidence of malicious activity.
The same file is in 1 other repository
Securing agentic ai tool invocation
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/securing-agentic-ai-tool-invocation Skill
48★ repoApply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.
Testing for system prompt leakage
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/testing-for-system-prompt-leakage Skill
48★ repoExtract and defend system prompts plus embedded secrets and routing logic.
Testing prompt injection in rag pipelines
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/testing-prompt-injection-in-rag-pipelines Skill
48★ repoProbe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/autoresearch Skill
48★ repoAutonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/bug-hunter/skills/hunt-llm-ai Skill
48★ repoHunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10). Patterns: direct prompt injection in user input (bypass system prompt with 'ignore previous instructions'), indirect injection via documents/web pages the model reads, ASCII smuggling (Unicode tag block U+E0000-U+E007F invisible to humans, visible to model), tool-use exfiltration (model has fetch_url tool, attacker injects URL, model exfils chat history), system prompt extraction (manipulate model to reveal hidden instructions), training data extraction, IDOR-via-AI (model reads other-user data via system prompt confusion). Tools: chatbots, RAG endpoints, summarization, agentic copilots. Detection: any LLM-backed endpoint, document upload that triggers AI processing, autonomous agent with tools. Validate: cross-user data leak, system prompt revealed, tool-use exfil demonstrated. Use when hunting AI features, chatbots, RAG, agentic systems.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/agent-self-scheduling Skill
48★ repoMake an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/delegating-to-agents Skill
48★ repoHow to delegate work to another AI agent (Pi, Codex, Claude Code, Hermes) — picking the right agent, sending prompts to TUI agents, polling progress. Read BEFORE any `cmux send`/`tmux send-keys` to an agent, or whenever delegating, relaying, spawning, or orchestrating agent-to-agent work.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/fable-safe-prompt Skill
48★ repoRewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guardrails that force-route to Opus 4.8 or return stop_reason "refusal"). Use when the user hands you a prompt that touches cybersecurity, auth, exploits, malware, pentesting, or other dual-use topics and asks to make it "Fable-safe", "guardrail-safe", "won't get flagged/refused/downgraded", or to rewrite it so Fable 5 won't block it.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/handoff Skill
48★ repoCompact the current conversation into a single, detailed handoff message — everything that happened, why it happened, and what's left — output in a code block so it can be copy-pasted into a fresh agent session. Use when hitting context limits, switching focus, ending a work session, or partitioning a task across fresh contexts.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe Skill
48★ repoScore any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/research-and-web/research-prompt Skill
48★ repoWrite a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.
Distribute skill to all agents
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/skill-authoring/distribute-skill-to-all-agents Skill
48★ repoDistribute a skill across the 4 agent skill folders (Codex, Claude Code, Pi, Hermes) so all agents see it. Use when the user says "distribute this skill", "sync skills across agents", or after creating/updating a skill that should be global. Covers the symlink layout and the ~/.pi/agent/skills trap.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/skill-authoring/effective-agent-skills Skill
48★ repoHow to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.
Folder specific claude and agents md
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/skill-authoring/folder-specific-claude-and-agents-md Skill
48★ repoCreate a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when David asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/dispatching-parallel-agents Skill
48★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 5 other repositories
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/camada-agentica Skill
48★ repoUse to propose and generate the project's agentic layer — rules (CLAUDE.md, settings.json), subagents (.claude/agents), skills (.claude/skills), and workflows/CI — tuned to the stack, tools, process, and domain. Proposes with justification and generates only what is approved. It is called by /kickoff and also runs standalone as the project evolves or new tools arrive. Trigger with /camada-agentica.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/evals Skill
48★ repoUse to evaluate how faithfully the implementation matches the spec — runs the eval that checks whether each AC-N is covered by a task and referenced in a test, counts SPEC_DEVIATION and reports a score per feature. Trigger with /evals.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/handoff Skill
48★ repoUse when PAUSING/ending a work session (records the current state in docs/STATE.md to resume later) or when RESUMING (reads docs/STATE.md and the active spec and reassembles the context, proposing the next step). Keeps continuity between sessions of humans and agents. Trigger with /handoff.
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/matt-pocock/misc/git-guardrails-claude-code Skill
48★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
The same file is in 18 other repositories
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/matt-pocock/productivity/handoff Skill
48★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 7 other repositories
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/subagent-driven-development Skill
48★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/taste-skills/skills/gpt-tasteskill Skill
48★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
The same file is in 13 other repositories
jjmartres/ai-coding-agents/shared/.ai-agents/skills/mcp-builder Skill
48★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 1 other repository
jjmartres/ai-coding-agents/shared/.ai-agents/skills/worktrunk Skill
48★ repoUse this skill when the user asks about Worktrunk (wt), git worktree management, running parallel AI agents with worktrees, setting up wt hooks, configuring wt.toml, using `wt switch`, `wt list`, `wt merge`, `wt remove`, `wt step`, LLM commit messages, or integrating Worktrunk with your AI agent. Also trigger when the user wants to run multiple AI agent sessions in parallel across isolated git branches, or automate dev server / database / dependency setup per worktree. Always use this skill for any question involving the `wt` CLI, worktree lifecycle automation, or the worktrunk plugin.
The same file is in 1 other repository
t2a-protocol/T2A/skills/t2a-tool-author Skill
48★ repoUse when modifying a CLI, API, SDK, CI job, workflow, or MCP server that has embedded LLM calls, model/provider config, or a bounded reasoning checkpoint and needs T2A authoring guidance.
cypress-io/ai-toolkit/io.cypress.mcp/cypress-cloud MCP server
48★ repoDirect access to Cypress tests results and accessibility reports in your AI workflow.
Kanevry/session-orchestrator/skills/claude-md-drift-check Skill
47★ repoLoop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.
The same file is in 3 other repositories
Kanevry/session-orchestrator/skills/docs-orchestrator Skill
47★ repoUse this skill when orchestrating documentation generation and updates within a session. Maps session scope to audience-specific docs tasks (User / Dev / Vault), dispatches the docs-writer agent with source-grounded prompts, and reports coverage gaps to session-end. Gated on `docs-orchestrator.enabled: true` in Session Config. Zero overhead when disabled.
The same file is in 4 other repositories
Kanevry/session-orchestrator/skills/eval Skill
47★ repoUse this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v1 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.
The same file is in 3 other repositories
Kanevry/session-orchestrator/skills/frontmatter-guard Skill
47★ repoInjects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes. <example>Context: wave-executor is about to dispatch a vault-mirror agent that writes learning notes under ~/Projects/vault/40-learnings/. user: "dispatch vault-write agent" assistant: "Injecting frontmatter-guard snippet into agent prompt (vault scope detected). Required fields: id, type, created, updated. Enum type: note|daily|project|person|reference|idea|learning|session." <commentary>The wave-executor pre-dispatch hook calls detectVaultTaskScope() — the fileScope contains /Projects/vault/40-learnings/ so the guard triggers and the snippet is prepended to the agent system prompt.</commentary></example>
The same file is in 2 other repositories
Kanevry/session-orchestrator/skills/hook-development Skill
47★ repoLoop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.
The same file is in 1 other repository
Kanevry/session-orchestrator/skills/mcp-builder Skill
47★ repoUse when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool discoverability/performance. Guides through research → implementation → test → eval phases with TypeScript-first guidance matching our stack. Trigger on phrases like "build an MCP server", "expose X as an MCP tool", "write MCP tools for Y", "integrate Z via MCP".
The same file is in 1 other repository
Kanevry/session-orchestrator/skills/memory-cleanup Skill
47★ repoUse this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under ~/.claude/projects/*/memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke with /memory-cleanup.
The same file is in 1 other repository
Kanevry/session-orchestrator/skills/skill-creator Skill
47★ repoUse when creating a new skill from scratch, modifying an existing skill, or optimizing a skill's triggering description. Guides intent capture, structure, writing patterns, and progressive-disclosure organization so skills reliably trigger and stay maintainable. Trigger on phrases like "turn this into a skill", "write a skill for X", "improve this skill", "my skill isn't triggering".
The same file is in 4 other repositories
Kanevry/session-orchestrator/skills/test-runner Skill
47★ repoUse this skill when orchestrating agentic end-to-end tests. Resolves target + profile, dispatches the right driver(s) (playwright for web today, peekaboo for macOS (issue #381)), invokes the ux-evaluator agent (opus, read-only) against driver artifacts, reconciles findings with the open issue tracker via scripts/lib/test-runner/issue-reconcile.mjs, and writes report.md + JSONL roll-up. Wraps upstream tools (no forks). Hard-gates Playwright MCP for browser drive (4× token cost vs CLI per Microsoft's own benchmark).
The same file is in 1 other repository
huangwb8/skills/awesome-code/agents/multi-agent-coordinator Skill
47★ repoUse when executing implementation plans with independent tasks - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates. Supports orchestrator, peer-to-peer, and pipeline coordination modes.
huangwb8/skills/better-prompt Skill
47★ repo当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"或"将简陋 prompt 转换为最佳实践版本"时使用。基于 OpenAI 和 Anthropic 官方最佳实践,对用户提供的简陋 prompt 进行结构化优化,输出符合社区标准的高质量版本。
huangwb8/skills/init-project Skill
47★ repo当用户明确要求"初始化项目"、"创建项目指令文件"或"生成 AGENTS.md"时使用。完全自动化:自动检测操作系统默认语言,分析项目目录结构(支持 Python/Web/Rust/Go/Java/数据科学/文档项目等),推断项目类型和用途,一键生成规范的项目指令文档。生成结果包括:AGENTS.md(跨平台通用项目指令,Single Source of Truth)、CLAUDE.md(Claude Code 特定适配,通过 @./AGENTS.md 引用)、README.md(项目介绍与使用方法)、CHANGELOG.md(项目变更记录)、.gitignore(Git 忽略规则,安全优先),并在完整初始化时自动补齐 `docs/` 与 `docs/plans/`。
huangwb8/skills/parallel-vibe Skill
47★ repo当用户明确要求"并行执行同一条 Vibe Coding 指令 / 多个独立 agent 或 subagent 同时审查、想方案、优化、对比多条路线 / 多线程独立尝试"时使用。默认使用智能模式:由宿主原生 subagent 独立分析并由主 agent 汇总;智能模式和代码模式必须使用同一套 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/parallel-vibe/{yyyy-mm-dd-hh-mm}/` 运行目录、`@main/plan.json`、thread `workspace/`、`RESULT.md` 与 `runner.log` 契约,区别只在底层执行机制;当用户要求脚本 runner、plan-file、resume、跨 CLI runner、退出码或无可用 subagent 时,切换到代码模式并调用 `scripts/parallel_vibe.py`。⚠️ 不适用:普通 shell 并发、单元测试并发、下载任务、要求强安全隔离或处理高度敏感数据。
allinherog-star/ai-skills/skills/agent-browser Skill
no license47★ repo业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
allinherog-star/ai-skills/skills/ai-gpt-image-2 Skill
no license47★ repo视觉质量诊断助手适合市场营销、运营、内容媒体、电商在用户提出“这张图够发布吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
The same file is in 1 other repository
allinherog-star/ai-skills/skills/ai-visual-prompt-review Skill
no license47★ repo视觉质量诊断助手适合设计、运营、市场营销、内容创作者在用户提出“这张图够发布吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
The same file is in 1 other repository
Creator commercial value benchmark
allinherog-star/ai-skills/skills/creator-commercial-value-benchmark Skill
no license47★ repo业务诊断助手适合运营、市场营销、内容媒体、电商在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
Knowledge base launch quality check
allinherog-star/ai-skills/skills/knowledge-base-launch-quality-check Skill
no license47★ repo文案诊断助手适合technical、管理者、software、知识库在用户提出“这段文案能打动人吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
addxai/enterprise-harness-engineering/skills/multi-worktree-dev Skill
47★ repoDesign and implementation guide for parallel multi-worktree development environments. Use whenever the user mentions multi-worktree development, git worktree, port conflicts, concurrent dev environments, feature branch isolation, local environment setup, or multi-developer collaboration conflicts. Even if the user casually says "we have several worktrees running simultaneously", this Skill should be triggered to guide them toward a proper layered environment.
addxai/enterprise-harness-engineering/skills/sre-agent Skill
47★ repoSRE Agent: oncall alert triage, diagnosis root cause analysis, patrol preventive inspection, iteration self-improvement. Use when the user says "oncall", "check alerts", "start oncall", "patrol", "health check", "retrospective", "iterate", "improve sre-agent", or provides PagerDuty alert content, or asks to query/acknowledge/resolve PagerDuty incidents. Should also trigger even if the user just says "check what alerts are there", "run a patrol", or "ack this alert".
Arize-ai/arize-skills/skills/arize-compliance-audit Skill
47★ repoINVOKE THIS SKILL when auditing an AI agent or LLM app for regulatory compliance. Covers EU AI Act, GPAI Code of Practice, GDPR, NIST AI RMF, Colorado AI Act, HIPAA, and ISO 42001. Scans the codebase for compliance gaps, cross-references Arize instrumentation for audit trail coverage, and produces an actionable remediation checklist tailored to the selected frameworks.
The same file is in 4 other repositories
Arize-ai/arize-skills/skills/arize-evaluator Skill
47★ repoHandles LLM-as-judge and code evaluator workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, code evaluator, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.
Arize-ai/arize-skills/skills/arize-prompt-optimization Skill
47★ repoOptimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
matteotitta/claude-code-marketing-quickstart/.claude/skills/level Skill
no license46★ repoScore your Claude Code environment on a fun 0-10 ladder (Tourist → Swarm) calibrated to the quickstart's 4 systems — Context, Skills, Integrations, Orchestration. Two front doors - an interactive quiz (zero setup, shareable) or a silent scan of your repo. Outputs a next-level roadmap plus a branded HTML dashboard or a paste-anywhere ASCII card. The default mastery skill of this quickstart. Triggers - "level", "what's my claude code level", "claude code level quiz", "assess my setup", "how good is my setup", "claude code maturity"
belumume/claude-skills/rlm-orchestrator Skill
no license46★ repoImplement RLM-style (Recursive Language Model) orchestration for complex tasks. This skill should be used when facing large context requirements, multi-part tasks that would benefit from parallel execution, or when context rot is a concern. Automatically decomposes tasks, spawns parallel subagents, aggregates results, and iterates until completion. Inspired by the RLM research paper (arXiv:2512.24601).
itallstartedwithaidea/google-ads-skills/skills/google-ads-mcp Skill
46★ repoMCP (Model Context Protocol) server configuration for live Google Ads API access. Activate when the user wants to connect Claude to their Google Ads account via MCP, set up the google-ads-mcp server, or configure credentials for live API queries. Provides setup instructions, server configuration, and troubleshooting.
The same file is in 1 other repository
xmm/codex-bmad-skills/skills/bmad-orchestrator Skill
no license46★ repoOrchestrates Codex BMAD workflows. Use for bmad:init, bmad:status, and bmad:next to manage project setup, state tracking, and phase routing.
The same file is in 1 other repository
BagelHole/DevOps-Security-Agent-Skills/devops/ai/agent-evals Skill
46★ repoBuild automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.
BagelHole/DevOps-Security-Agent-Skills/devops/ai/agent-observability Skill
46★ repoInstrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.
BagelHole/DevOps-Security-Agent-Skills/devops/ai/ai-pipeline-orchestration Skill
46★ repoOrchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster. Build reliable, observable, and retriable workflows for production AI systems.
BagelHole/DevOps-Security-Agent-Skills/devops/ai/llm-caching Skill
46★ repoImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.
BagelHole/DevOps-Security-Agent-Skills/devops/ai/llm-cost-optimization Skill
46★ repoReduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.
BagelHole/DevOps-Security-Agent-Skills/devops/ai/rag-observability-evals Skill
46★ repoMonitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.