Evidence Table

One row per source, one column per question, quotes in cells.

Single skill Verified 20 Nov researchsynthesisevidence

Use it for

A report that will be read by someone who will check the sources

Skip it if

A quick summary — the table is the slow, defensible version

What it is

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.

Install

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.

Terminal
npx skills add evidence-table

How to judge it

Read 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.

Other research skills

  • Source Dating — Add the date and context to claims that need them.
  • Interview Note Cluster — Group interview notes into themes while keeping the participant.
  • Market Map — Lay out a category by segment and player, with what each claims.

Tools it pairs with

All tools

Servers it runs on

All servers
  • 01
    Telegram MCPCommunity

    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 …

    #chat#monitoring#research
    Pythonstdio
  • 02
    YouTube MCPCommunity

    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…

    #video#research#transcripts
    Pythonstdio
  • 03
    Hugging Face MCPCommunity

    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 …

    #models#datasets#research
    Pythonstdio