council-execution
FeaturedExecutes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.
Install
Quality Score: 90/100
Skill Content
Details
- Author
- hex
- Repository
- hex/claude-council
- Created
- 8 months ago
- Last Updated
- 4 days ago
- Language
- Shell
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content โ not just same category
deep-execution
Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions, and return structured insights with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions are detected.
local-council-execution
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council offer after no providers are found. This is a same-model (Claude-only) panel, not a cross-vendor council.
council
Put a decision to four models across three vendors, have them rank each other blind, then synthesise. Use in plan mode before committing to an approach; before an architecture, schema, security or concurrency decision that is expensive to reverse; when a review is uncertain or two reviewers disagree; before verifying that a design actually holds; and when about to ship something whose failure mode is data loss, a breach, or a production outage. Do NOT use for questions with a knowable answer โ read the code, run the test, grep. Costs 10โ30 minutes.