{"enrichment":{"faq":[{"a":"asking-with-evidence lets you query what was said about any topic in a video you've already watched. The skill searches its persistent index and returns the exact transcript excerpt along with the timestamp where it appears and a confidence score, so you have proof of what was stated without rewatching.","q":"What did they say about X in the video?"},{"a":"asking-with-evidence indexes all watched videos and can locate specific error codes or technical details at their exact moments. When you ask for an error code, it returns the timestamp, confidence score, and surrounding context so you can jump directly to that part of the video.","q":"How does asking-with-evidence find error codes with timestamps?"},{"a":"Yes. asking-with-evidence supports semantic and keyword search across your entire library of watched videos. Instead of re-watching or manually scanning, you query the indexed content and get back matching moments with timestamps and confidence scores for each result.","q":"Can I search all my watched videos at once?"},{"a":"asking-with-evidence refuses unclear answers honestly and escalates automatically when confidence is too low. This prevents hallucination, saves tokens by avoiding re-processing, and ensures you only get answers backed by real evidence from the video index.","q":"What happens when asking-with-evidence is uncertain?"},{"a":"asking-with-evidence extracts transcript excerpts and frames at exact timestamps as evidence. Query the video by topic, phrase, or moment, and the skill returns the relevant text or frame along with its precise timestamp and confidence score.","q":"How do I get transcript excerpts with exact timestamps?"},{"a":"Yes. asking-with-evidence maintains a persistent index of watched videos, so follow-up questions are answered by querying that index rather than re-processing the video. This saves time and tokens while keeping your answers consistent and traceable to specific timestamps.","q":"Can asking-with-evidence answer follow-up questions without rewatching?"}],"shadow_tags":["persistent-indexing","timestamp-evidence","confidence-scoring","video-qa","multi-language-support","moment-extraction","hybrid-search","transcript-retrieval","ocr-detection","refusal-handling"],"summary_rewrite":"Query any video you've already watched to get answers backed by timestamps and confidence scores, drawn from a persistent index rather than re-processing. The skill refuses unclear answers honestly and escalates automatically when uncertain, saving tokens in the process."},"files":[{"bytes":2031,"path":"adapters/claude-skill/skills/asking-with-evidence/SKILL.md","sha256":"d8de2e07e73606d9011a7a1e828b87e93b657dd64b9a8304a3a7d13365b8788f","url":"https://skillfed.io/files/oxbshw/watch-skill/asking-with-evidence/f0ec84b8/SKILL.md"}],"id":"oxbshw/watch-skill/asking-with-evidence","links":{"html":"https://skillfed.io/oxbshw/watch-skill/asking-with-evidence","md":"https://skillfed.io/oxbshw/watch-skill/asking-with-evidence.md","repo":"https://github.com/oxbshw/watch-skill"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":36,"language":"Python","last_updated":"2026-07-12","license":"MIT","name":"asking-with-evidence","publisher":"oxbshw","stars":236},"relations":{"categories":["video-analysis","information-retrieval","knowledge-extraction"],"similar":[{"id":"oxbshw/watch-skill/watch"},{"id":"oxbshw/watch-skill/learning-from-mistakes"},{"id":"oxbshw/watch-skill/video-memory"},{"id":"oxbshw/watch-skill/watching-videos"},{"id":"oxbshw/watch-skill/the-loop"},{"id":"oxbshw/watch-skill/extracting-structure"},{"id":"oxbshw/watch-skill/configuring-vision"},{"id":"oxbshw/watch-skill/sharing-results"},{"id":"oxbshw/watch-skill/recovering-from-errors"},{"id":"syahiidkamil/Software-Engineer-AI-Agent-Atlas/learning-from-mistakes"}]},"slug":{"owner":"oxbshw","repo":"watch-skill","skill":"asking-with-evidence"},"version":"f0ec84b8"}