{"id":"1c1586af-c101-4d10-a001-0ac32e465feb","shortId":"tQZu47","kind":"skill","title":"Regression-test prompts, agents, and RAG outputs before shipping changes","tagline":"Use promptfoo when an agent needs to evaluate prompt, agent, or RAG behavior against saved assertions before a change goes live. The value here is the repeatable evaluation workflow, not a generic AI tooling catalog entry.","description":"# Regression-test prompts, agents, and RAG outputs before shipping changes\n\nUse promptfoo when an agent needs to evaluate prompt, agent, or RAG behavior against saved assertions before a change goes live. The value here is the repeatable evaluation workflow, not a generic AI tooling catalog entry.\n\n## Prerequisites\n\nNode.js, CI pipeline, model provider credentials\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- npm install -g promptfoo\n- Also available via brew install promptfoo and pip install promptfoo. You can also use npx promptfoo@latest to run any command without installing.\n\nRequirements and caveats from upstream:\n- Requires [Node.js](https://nodejs.org/en/download) ^20.20.0 or >=22.22.0 for npm and npx usage.\n- Most LLM providers require an API key. Set yours as an environment variable:\n- [Node.js Package](https://www.promptfoo.dev/docs/usage/node-package/)\n\nBasic usage or getting-started notes:\n- <a href=\"https://www.promptfoo.dev/docs/getting-started/\">Getting Started</a> ·\n- sh\n- promptfoo init --example getting-started\n\n- Source: https://github.com/promptfoo/promptfoo\n- Extracted from upstream docs: https://raw.githubusercontent.com/promptfoo/promptfoo/HEAD/README.md\n\n## Documentation\n\n- https://www.promptfoo.dev/docs/intro/\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes/)","tags":["regression","test","prompts","agents","and","rag","outputs","before","shipping","changes","skills","agentskillexchange"],"capabilities":["skill","source-agentskillexchange","skill-regression-test-prompts-agents-and-rag-outputs-before-shipping-changes","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,446 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:03.940Z","embedding":null,"createdAt":"2026-05-18T13:18:48.846Z","updatedAt":"2026-05-18T19:12:03.940Z","lastSeenAt":"2026-05-18T19:12:03.940Z","tsv":"'/docs/intro/':207 '/docs/usage/node-package/)':176 '/en/download)':150 '/promptfoo/promptfoo':196 '/promptfoo/promptfoo/head/readme.md':203 '/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes/)':214 '20.20.0':151 '22.22.0':153 'agent':5,16,21,52,63,68,209 'agentskillexchange.com':213 'agentskillexchange.com/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes/)':212 'ai':44,91 'also':118,130 'api':164 'assert':27,74 'avail':119 'basic':177 'behavior':24,71 'brew':121 'catalog':46,93 'caveat':143 'chang':11,30,58,77 'ci':97 'command':138 'credenti':101 'doc':200 'document':204 'entri':47,94 'environ':113,170 'evalu':19,39,66,86 'exampl':189 'exchang':211 'extract':197 'g':116 'generic':43,90 'get':181,184,191 'getting-start':180,190 'github.com':195 'github.com/promptfoo/promptfoo':194 'goe':31,78 'init':188 'instal':102,106,115,122,126,140 'key':165 'latest':134 'live':32,79 'llm':160 'match':111 'model':99 'need':17,64 'node.js':96,147,172 'nodejs.org':149 'nodejs.org/en/download)':148 'note':183 'npm':114,155 'npx':132,157 'output':8,55 'packag':173 'path':109 'pip':125 'pipelin':98 'prerequisit':95 'prompt':4,20,51,67 'promptfoo':13,60,117,123,127,133,187 'provid':100,161 'rag':7,23,54,70 'raw.githubusercontent.com':202 'raw.githubusercontent.com/promptfoo/promptfoo/head/readme.md':201 'regress':2,49 'regression-test':1,48 'repeat':38,85 'requir':141,146,162 'run':136 'save':26,73 'set':166 'setup':108 'sh':186 'ship':10,57 'skill':210 'skill-regression-test-prompts-agents-and-rag-outputs-before-shipping-changes' 'sourc':193,208 'source-agentskillexchange' 'start':182,185,192 'test':3,50 'tool':45,92 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'upstream':105,145,199 'usag':158,178 'use':12,59,103,131 'valu':34,81 'variabl':171 'via':120 'without':139 'workflow':40,87 'www.promptfoo.dev':175,206 'www.promptfoo.dev/docs/intro/':205 'www.promptfoo.dev/docs/usage/node-package/)':174","prices":[{"id":"70f31bfb-d939-415a-ab1f-6798ca3b6312","listingId":"1c1586af-c101-4d10-a001-0ac32e465feb","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:18:48.846Z"}],"sources":[{"listingId":"1c1586af-c101-4d10-a001-0ac32e465feb","source":"github","sourceId":"agentskillexchange/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes","isPrimary":false,"firstSeenAt":"2026-05-18T13:18:48.846Z","lastSeenAt":"2026-05-18T19:12:03.940Z"}],"details":{"listingId":"1c1586af-c101-4d10-a001-0ac32e465feb","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"regression-test-prompts-agents-and-rag-outputs-before-shipping-changes","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"3d71f5db0f94881c7001f6853b612178bc2bb9ad","skill_md_path":"skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Regression-test prompts, agents, and RAG outputs before shipping changes","description":"Use promptfoo when an agent needs to evaluate prompt, agent, or RAG behavior against saved assertions before a change goes live. The value here is the repeatable evaluation workflow, not a generic AI tooling catalog entry."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/regression-test-prompts-agents-and-rag-outputs-before-shipping-changes"},"updatedAt":"2026-05-18T19:12:03.940Z"}}