{"id":"0eb1620c-c822-4381-b16d-0850fe3fbfd9","shortId":"jLNtDn","kind":"skill","title":"Iteratively optimize prompts and text-based agent configs against scored eval sets with GEPA","tagline":"Use reflective search to improve prompts or text-configured agent components against a real eval set instead of manual prompt tweaking.","description":"# Iteratively optimize prompts and text-based agent configs against scored eval sets with GEPA\n\nUse reflective search to improve prompts or text-configured agent components against a real eval set instead of manual prompt tweaking.\n\n## Prerequisites\n\nPython environment, GEPA package, train and validation examples with a scoring function, model provider credentials or local models, target prompt or text configuration to optimize\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install gepa\n- pip install git+https://github.com/gepa-ai/gepa.git\n\nRequirements and caveats from upstream:\n- <a href=\"https://pypi.org/project/gepa/\"><img src=\"https://img.shields.io/pypi/v/gepa?logo=python&logoColor=white&color=3776ab\" alt=\"PyPI\"></a>\n\nBasic usage or getting-started notes:\n- <a href=\"https://gepa-ai.github.io/gepa/guides/quickstart/\"><strong>Quick Start</strong></a> &ensp;|&ensp;\n- bash\n- To install the latest from main:\n\n- Source: https://github.com/gepa-ai/gepa\n- Extracted from upstream docs: https://raw.githubusercontent.com/gepa-ai/gepa/HEAD/README.md\n\n## Documentation\n\n- https://gepa-ai.github.io/gepa/\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa/)","tags":["iteratively","optimize","prompts","and","text","based","agent","configs","against","scored","eval","sets"],"capabilities":["skill","source-agentskillexchange","skill-iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa","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/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa","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 (1,329 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":"2026-05-18T19:10:58.407Z","embedding":null,"createdAt":"2026-05-18T13:17:15.198Z","updatedAt":"2026-05-18T19:10:58.407Z","lastSeenAt":"2026-05-18T19:10:58.407Z","tsv":"'/gepa-ai/gepa':146 '/gepa-ai/gepa.git':121 '/gepa-ai/gepa/head/readme.md':153 '/gepa/':157 '/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa/)':164 'agent':8,26,45,63,159 'agentskillexchange.com':163 'agentskillexchange.com/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa/)':162 'base':7,44 'bash':136 'basic':127 'caveat':124 'compon':27,64 'config':9,46 'configur':25,62,98 'credenti':90 'doc':150 'document':154 'environ':77,112 'eval':12,31,49,68 'exampl':83 'exchang':161 'extract':147 'function':87 'gepa':15,52,78,115 'gepa-ai.github.io':156 'gepa-ai.github.io/gepa/':155 'get':131 'getting-start':130 'git':118 'github.com':120,145 'github.com/gepa-ai/gepa':144 'github.com/gepa-ai/gepa.git':119 'improv':20,57 'instal':101,105,114,117,138 'instead':33,70 'iter':1,38 'latest':140 'local':92 'main':142 'manual':35,72 'match':110 'model':88,93 'note':133 'optim':2,39,100 'packag':79 'path':108 'pip':113,116 'prerequisit':75 'prompt':3,21,36,40,58,73,95 'provid':89 'python':76 'quick':134 'raw.githubusercontent.com':152 'raw.githubusercontent.com/gepa-ai/gepa/head/readme.md':151 'real':30,67 'reflect':17,54 'requir':122 'score':11,48,86 'search':18,55 'set':13,32,50,69 'setup':107 'skill':160 'skill-iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa' 'sourc':143,158 'source-agentskillexchange' 'start':132,135 'target':94 'text':6,24,43,61,97 'text-bas':5,42 'text-configur':23,60 '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' 'train':80 'tweak':37,74 'upstream':104,126,149 'usag':128 'use':16,53,102 'valid':82","prices":[{"id":"688efaa1-9a15-4433-a756-d8077797d4fa","listingId":"0eb1620c-c822-4381-b16d-0850fe3fbfd9","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":"2026-05-18T13:17:15.198Z"}],"sources":[{"listingId":"0eb1620c-c822-4381-b16d-0850fe3fbfd9","source":"github","sourceId":"agentskillexchange/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa","isPrimary":false,"firstSeenAt":"2026-05-18T13:17:15.198Z","lastSeenAt":"2026-05-18T19:10:58.407Z"}],"details":{"listingId":"0eb1620c-c822-4381-b16d-0850fe3fbfd9","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa","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":"560bafef4295a34abe40ca70ba12c49bc383dc79","skill_md_path":"skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Iteratively optimize prompts and text-based agent configs against scored eval sets with GEPA","description":"Use reflective search to improve prompts or text-configured agent components against a real eval set instead of manual prompt tweaking."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/iteratively-optimize-prompts-and-text-based-agent-configs-against-scored-eval-sets-with-gepa"},"updatedAt":"2026-05-18T19:10:58.407Z"}}