Ase Meta Quorum

@${CLAUDESKILLDIR}/../../meta/ase-control.md @${CLAUDESKILLDIR}/../../meta/ase-skill.md @${CLAUDESKILLDIR}/../../meta/ase-getopt.md

Query Multiple AIs for Quorum Answer

$ARGUMENTS

Find a quorum answer on an arbitrary question, by querying multiple AIs for an optimal consensus.

Prepare the LLM query by setting to the following :

. Please respond with facts and very concise and brief only, usually with just 1 to 7 corresponding bullet points and with short sentences. Optionally, mention potential cruxes which should be noticed. Beside bullet points, do not provide any additional explanations. Emphasize keywords or cruxes in your response with Markdown formatting. Format code parts with Markdown formatting.

For yourself (Anthropic Claude), first answer this in advance yourself by showing your own answer to the query as a sneak preview. For this, output the following :

Anthropic Claude (sneak preview in advance):

• [...]
• [...]

The user-selectable foreign models are restricted by the --models/-m option, parsed into as a comma-separated list of model tokens. The getopt parser validates only the first token, so you MUST validate each remaining token yourself against the allowed set all, chatgpt, gemini, deepseek, grok, glm, qwen. If any token is not in this set, only output the following and then immediately STOP processing the entire current skill:

⧉ ASE: ✪ skill: ase-meta-quorum, ▶ ERROR: invalid --models token: ****

The default is the single token all. If contains the token all, you MUST treat it as the full list chatgpt,gemini,deepseek,grok,glm,qwen (all models). Anthropic Claude (yourself) is always included, independent of this option.

Call the Agent tool:

``text Agent( name: "ase-meta-chat-", description: "Query Foreign LLM: ", subagent_type: "ase:ase-meta-chat", prompt: " " ) ``

Query only those foreign models whose token is contained in (where all selects every model); silently skip all others:

contains all OR contains chatgpt">

contains all OR contains gemini">

contains all OR contains deepseek">

contains all OR contains grok">

contains all OR contains glm">

contains all OR contains qwen">

You MUST NOT output anything in this step.

Agents which returned a response with an ERROR: prefix are silently skipped and are treated as not available.

Summarize all responses, of both yourself and all available agents with just 1 to 7 corresponding bullet points and with short sentences.

You MUST NOT output anything in this step.

First, count the number of available foreign AIs (those queried in STEP 2 which did not return an ERROR: response). If this count is zero -- i.e., every foreign AI errored out or none were reachable and only yourself (Anthropic Claude) remains -- a quorum is not possible. In this case, set and to empty and instead set to (no quorum: no foreign AIs were available), then skip the rest of this step.

Otherwise, let be the total number of responders (yourself plus all available foreign AIs above). Then determine, on a Likert scale of 0.., the amount of the overall consensus of all the responses. If all responses disagree, the consensus is zero. If all responses agree, is .

If not all AIs agree, determine information, formatted as (disagreement: , , [...]) where is a name of an AI which disagreed with the consensus. Else, if all AIs agree, set .

You MUST NOT output anything in this step.

Finally show the summary, the consensus and the complete and unmodified responses of yourself and each of the queried foreign AIs, based on the following output :

QUESTION:

● CONSENSUS ANSWER:

• [...]
• [...]

CONSENSUS RATE: /

When a quorum was not possible (see STEP 4), render this line instead as just **CONSENSUS RATE**: *n/a* (omitting the / fraction), as a single AI cannot form a consensus.

○ Anthropic Claude:

• [...]
• [...]

○ OpenAI ChatGPT:

• [...]
• [...]

○ Google Gemini:

• [...]
• [...]

○ DeepSeek:

• [...]
• [...]

○ xAI Grok:

• [...]
• [...]

○ Z.AI GLM:

• [...]
• [...]

○ Alibaba Qwen:

• [...]
• [...]

In this output, remove the sections of those AIs which were not queried (excluded via --models/-m) or were not available. You MUST NOT output any further explanations yourself.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: rse
• Source: rse/ase
• License: Apache-2.0
• Homepage: https://ase.tools

Install and usage instructions live in the source repository linked above.