Perplexity
Perplexity AIAn answer engine that cites what it used.
One row per source, one column per question, quotes in cells.
A report that will be read by someone who will check the sources
A quick summary — the table is the slow, defensible version
Builds an evidence table from a set of sources: rows for sources, columns for the questions, quoted evidence in the cells. Empty cells are the finding — they show which questions the sources do not answer. The output is a table plus the three questions that remain open.
Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.
npx skills add evidence-tableRead the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.
An answer engine that cites what it used.
Paid, ad-free search with an API and no engagement optimisations.
Search API with a focus on research-grade sources.
Reads channels and groups through the Bot API: recent messages, search, and posting. The distinction that matters is bot token versus user session — a bot sees what …
Wraps the YouTube Data API for search, channel and video metadata, and captions where available. The transcript path is the useful one for research; anything that re…
Searches Hugging Face models and datasets and returns metadata: task, licence, downloads, and the card text. The useful workflow is the decision before the download …