Althing Poll — AI skill for Claude Code
Run a one-question synthetic poll across AI personas and synthesize the themes.
How to install Althing Poll
Installs to ~/.claude/skills/dataviking-tech-synthpanel-althing-poll/SKILL.md
mkdir -p ~/.claude/skills/dataviking-tech-synthpanel-althing-poll && curl -fsSL https://raw.githubusercontent.com/DataViking-Tech/SynthPanel/HEAD/commands/althing-poll.md -o ~/.claude/skills/dataviking-tech-synthpanel-althing-poll/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Althing Poll does
description: Run a one-question synthetic poll across AI personas and synthesize the themes allowed-tools:
- mcp__althing__run_quick_poll
- mcp__althing__list_persona_packs
- mcp__althing__get_persona_pack argument-hint:
Run a quick synthetic poll using the Althing MCP server. One question, a handful of AI personas, one synthesized writeup.
Question: $ARGUMENTS
What to do
- Resolve the question. If
$ARGUMENTSis empty, ask the user for the
Alternatives in AI
- Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
- Wiki Query — Query the LLM Wiki and synthesize an answer 2.3k ★
- User Research Skill — Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, syn 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Midjourney MCP
RunAPI Midjourney MCP server for image and video generation: create tasks, poll results, and check pricing acr
onWatch
Open-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHu
HydraMCP
Connect agents to agents. MCP server for querying any LLM through your existing subscriptions: compare, vote,
Labcoat
Polycentric Labcoat — a rigorous multi-model, hard-skeptic research engine: fan a question across a live fleet
Agentic Sdlc Personas
Twenty-four persona kits for an AI-native software development lifecycle. Validated primitives for GitHub Copi
Bench Watch
Launch or attach to a Plumbline benchmark slice, poll it to completion, and emit the canonical anti-Goodhart p
Related Agents
Question Forger
Generates evaluation questions with gold answers and gold evidence from real graph paths and from the syntheti
Vaultspec Researcher
Gather, analyze, and synthesize information on a question. Use for general
Hcs Eval Reviewer
Reviews regression-trap quality and eval harness coverage for HCS. Ensures traps capture real failure classes