Files
claude-skills-reference/engineering/code-tour/evals.json
Reza Rezvani 5710a7b763 chore: post-merge sync — plugins, audits, docs, cross-platform indexes
New skills integrated:
- engineering/behuman, code-tour, demo-video, data-quality-auditor

Plugins & marketplace:
- Add plugin.json for code-tour, demo-video, data-quality-auditor
- Add all 3 to marketplace.json (31 total plugins)
- Update marketplace counts to 248 skills, 332 tools, 460 refs

Skill fixes:
- Move data-quality-auditor from data-analysis/ to engineering/
- Fix cross-refs: code-tour, demo-video, data-quality-auditor
- Add evals.json for code-tour (5 scenarios) and demo-video (4 scenarios)
- demo-video: add output artifacts, prereqs check, references extraction
- code-tour: add default persona, parallel discovery, trivial repo guidance
- Fix Python 3.9 compat (from __future__ import annotations)

product-analytics audit fixes:
- Expand SKILL.md from 82 to 147 lines (anti-patterns, cross-refs, examples)
- Add --format json to all metrics_calculator.py subcommands
- Add error handling (FileNotFoundError, KeyError)

Docs & indexes:
- Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md counts
- Sync Codex (192 skills) and Gemini (280 items) indexes
- Regenerate MkDocs pages (279 pages, 311 HTML)
- Add 3 new nav entries to mkdocs.yml
- Update mkdocs.yml site_description

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-04 02:05:19 +02:00

33 lines
1.9 KiB
JSON

[
{
"id": 1,
"prompt": "I just hired a junior dev who starts Monday. Can you create an onboarding tour for this repo so they can get oriented on their own?",
"expected_output": "Agent infers new-joiner persona, standard depth (9-13 steps). Produces .tours/new-joiner-onboarding.tour with verified paths/lines, SMIG descriptions, narrative arc starting with orientation directory step.",
"scenario_type": "happy_path"
},
{
"id": 2,
"prompt": "Give me a quick vibe check tour of this codebase — I just cloned it and want to understand the shape before diving in.",
"expected_output": "Agent infers vibecoder persona, quick depth (5-8 steps). Tour hits entry point and main modules only. File saved to .tours/vibecoder-overview.tour.",
"scenario_type": "happy_path"
},
{
"id": 3,
"prompt": "We had an outage last night because the payment webhook handler silently swallowed errors. Can you build an RCA tour tracing how webhooks flow through the system?",
"expected_output": "Agent infers rca-investigator persona, standard depth. Tour follows causality chain from webhook entry point through handler to error handling. Steps anchored to specific lines showing the fault path.",
"scenario_type": "happy_path"
},
{
"id": 4,
"prompt": "Create a tour for this repo.",
"expected_output": "Agent defaults to new-joiner persona at standard depth without asking clarifying questions. Produces a general-purpose onboarding tour.",
"scenario_type": "edge_case"
},
{
"id": 5,
"prompt": "Make an onboarding tour for this repo, but I want it to also cover the deployment pipeline and our monitoring setup in Grafana.",
"expected_output": "Agent includes deployment pipeline files as normal file+line steps. Uses URI step type for Grafana link if user provides URL, or skips with explanation. Does not hallucinate files.",
"scenario_type": "edge_case"
}
]