ucsc-vlaa/visualclaw/evidence-grounded-output

Claude Code and agent skill by ucsc-vlaa/visualclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Trigger when output must cite evidence — every factual claim or value must trace to a cited source; never fabricate unsupported values.

Install

npx vskill@latest install ucsc-vlaa/visualclaw/evidence-grounded-output

SKILL.md

Ground Every Value in Cited Evidence

  1. Cite every fact: Each factual value or claim must trace to a source — [clip @ MM:SS], [doc:...], [chat:...], [audio:...], [pdf:...], or [image:...].
  2. Use the citation format the task specifies: Match its conventions exactly; one valid citation form per fact.
  3. Do not invent: If a value is not supported by the workspace, the video, or the documents, do not state it — mark it unknown or escalate instead.
  4. Prefer the designated arbiter: When sources conflict, follow the source the task names as authoritative.

Example: An on-hand count must come from the document the task names as the arbiter, not from a guess.

Anti-pattern: Filling a required field with a plausible number that no cited source actually supports.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
57
Repository forks
4
7-day trend score
25

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ucsc-vlaa/visualclaw/evidence-grounded-output/badge)](https://verified-skill.com/skills/ucsc-vlaa/visualclaw/evidence-grounded-output)

Something wrong with this skill or its page? Tell us.