{"id":"3d2b4875-ed6a-4d16-9d0a-d254ed9af100","shortId":"Dn7Vtp","kind":"skill","title":"bootstrap-template-evaluation","tagline":"Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start without building judgment configs from scratch.","description":"# Bootstrap Template Evaluation\n\nUse this skill when a pre-built template likely covers the target use case.\n\n## Interactive Q&A protocol (mandatory)\n\n<HARD-GATE>\nBEFORE the first scoping question, search for a structured question tool (e.g., `AskUserQuestion` or similar interactive widget) and load it. Use that tool for EVERY scoping question. Fall back to plain-text lettered options ONLY if no such tool exists in the environment.\n</HARD-GATE>\n\nIf template choice is ambiguous, ask one question at a time using the structured question tool (loaded per the HARD-GATE above).\n\nExample question structure:\n\n```\nWhich template family best matches your goal?\nA) AI writing detection\nB) Code quality\nC) Unsure, list all templates first\n```\n\nRules:\n- Ask one question per message.\n- Use the structured question tool for every question. Structure each with a short header, 2-4 options with labels and descriptions, and place the recommended option first. Do not add \"(Recommended)\" or similar annotations to option labels.\n- Ask one follow-up only when needed.\n\n## Workflow\n\n1. Discover templates:\n   - Call `list_templates`.\n2. Select template:\n   - Match use case to template `slug`.\n3. Provision private dataset:\n   - Call `provision_template(slug)`.\n4. Deploy live evaluation:\n   - Call `create_and_deploy_evaluation(dataset_id)`.\n   - Capture `api_key` immediately because it is returned only once.\n5. Verify:\n   - Run `run_eval` with representative inputs.\n6. Return deployment artifacts:\n   - `dataset_id`\n   - `live_evaluation_id`\n   - verification result\n\n## Guardrails\n\n- If no template fits, hand off to `create-evaluation`.\n- Do not skip verification after deployment.\n\n## Scopes reference\n\n- `list_templates` requires `datasets:read`\n- `provision_template` requires `datasets:write`\n- `create_and_deploy_evaluation` requires `evaluations:write`, `live-evaluations:write`\n- `run_eval` requires `live-evaluations:execute`","tags":["bootstrap","template","evaluation","truesight","mcp","skills","goodeye-labs","agent-skills","ai-evaluation","chatgpt","claude","cursor"],"capabilities":["skill","source-goodeye-labs","skill-bootstrap-template-evaluation","topic-agent-skills","topic-ai-evaluation","topic-chatgpt","topic-claude","topic-cursor","topic-llm","topic-mcp","topic-truesight","topic-vscode","topic-windsurf"],"categories":["truesight-mcp-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Goodeye-Labs/truesight-mcp-skills/bootstrap-template-evaluation","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Goodeye-Labs/truesight-mcp-skills","source_repo":"https://github.com/Goodeye-Labs/truesight-mcp-skills","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 6 github stars · SKILL.md body (1,929 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":"2026-05-18T13:22:56.777Z","embedding":null,"createdAt":"2026-05-18T13:22:56.777Z","updatedAt":"2026-05-18T13:22:56.777Z","lastSeenAt":"2026-05-18T13:22:56.777Z","tsv":"'-4':167 '1':198 '2':166,204 '3':213 '4':221 '5':242 '6':250 'add':181 'ai':134 'ambigu':104 'annot':185 'api':233 'artifact':253 'ask':105,147,189 'askuserquest':68 'b':137 'back':84 'best':129 'bootstrap':2,33 'bootstrap-template-evalu':1 'build':28 'built':16,43 'c':140 'call':201,217,225 'captur':232 'case':50,209 'choic':102 'code':138 'config':30 'cover':46 'creat':226,270,290 'create-evalu':269 'dataset':216,230,254,283,288 'deploy':9,222,228,252,277,292 'descript':172 'detect':136 'discov':199 'e.g':67 'environ':99 'eval':246,302 'evalu':4,11,35,224,229,257,271,293,295,299,306 'everi':80,158 'exampl':123 'execut':307 'exist':96 'fall':83 'famili':128 'fastest':5 'first':58,145,178 'fit':265 'follow':192 'follow-up':191 'gate':121 'goal':132 'guardrail':261 'hand':266 'hard':120 'hard-gat':119 'header':165 'id':231,255,258 'immedi':235 'input':249 'interact':51,71 'judgment':29 'key':234 'label':170,188 'letter':89 'like':45 'list':142,202,280 'live':10,223,256,298,305 'live-evalu':297,304 'load':74,116 'mandatori':55 'match':130,207 'messag':151 'need':196 'one':106,148,190 'option':90,168,177,187 'per':117,150 'place':174 'plain':87 'plain-text':86 'pre':15,42 'pre-built':14,41 'privat':215 'protocol':54 'provis':214,218,285 'q':52 'qualiti':139 'question':60,65,82,107,114,124,149,155,159 'quick':25 'read':284 'recommend':176,182 'refer':279 'repres':248 'requir':282,287,294,303 'result':260 'return':239,251 'rout':6 'rule':146 'run':244,245,301 'scope':59,81,278 'scratch':32 'search':61 'select':205 'short':164 'similar':70,184 'skill':38 'skill-bootstrap-template-evaluation' 'skip':274 'slug':212,220 'source-goodeye-labs' 'start':26 'structur':64,113,125,154,160 'target':48 'templat':3,18,34,44,101,127,144,200,203,206,211,219,264,281,286 'text':88 'time':110 'tool':66,78,95,115,156 'topic-agent-skills' 'topic-ai-evaluation' 'topic-chatgpt' 'topic-claude' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-truesight' 'topic-vscode' 'topic-windsurf' 'truesight':17 'unsur':141 'use':12,19,36,49,76,111,152,208 'user':22 'verif':259,275 'verifi':243 'want':23 'widget':72 'without':27 'workflow':197 'write':135,289,296,300","prices":[{"id":"25ffc931-3016-4caf-b98e-7311ee7fbeb9","listingId":"3d2b4875-ed6a-4d16-9d0a-d254ed9af100","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Goodeye-Labs","category":"truesight-mcp-skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:22:56.777Z"}],"sources":[{"listingId":"3d2b4875-ed6a-4d16-9d0a-d254ed9af100","source":"github","sourceId":"Goodeye-Labs/truesight-mcp-skills/bootstrap-template-evaluation","sourceUrl":"https://github.com/Goodeye-Labs/truesight-mcp-skills/tree/main/skills/bootstrap-template-evaluation","isPrimary":false,"firstSeenAt":"2026-05-18T13:22:56.777Z","lastSeenAt":"2026-05-18T13:22:56.777Z"}],"details":{"listingId":"3d2b4875-ed6a-4d16-9d0a-d254ed9af100","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Goodeye-Labs","slug":"bootstrap-template-evaluation","github":{"repo":"Goodeye-Labs/truesight-mcp-skills","stars":6,"topics":["agent-skills","ai-evaluation","chatgpt","claude","cursor","llm","mcp","truesight","vscode","windsurf"],"license":"mit","html_url":"https://github.com/Goodeye-Labs/truesight-mcp-skills","pushed_at":"2026-03-26T06:15:56Z","description":"Agent skills for the Truesight MCP. Step-by-step workflow playbooks for scoring inputs, building live evaluations, error analysis, and the review loop. Works with Claude Code, Cursor, ChatGPT, VS Code, Windsurf, and any client that supports the agent skills standard.","skill_md_sha":"92b5415ceaed79293fd70d7e7d2fcb8091be238c","skill_md_path":"skills/bootstrap-template-evaluation/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Goodeye-Labs/truesight-mcp-skills/tree/main/skills/bootstrap-template-evaluation"},"layout":"multi","source":"github","category":"truesight-mcp-skills","frontmatter":{"name":"bootstrap-template-evaluation","description":"Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start without building judgment configs from scratch."},"skills_sh_url":"https://skills.sh/Goodeye-Labs/truesight-mcp-skills/bootstrap-template-evaluation"},"updatedAt":"2026-05-18T13:22:56.777Z"}}