council-execution

Featured

Executes 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.

AI & Automation 726 stars 90 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 90/100

Stars 20%
95
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
85
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Council Query Execution ## Step 1: Run Query and Save to File ```bash bash ${CLAUDE_PLUGIN_ROOT}/scripts/run-council.sh --providers=gemini,openai -- "Your question" ``` This outputs the path to the saved file (e.g., `.claude/council-cache/council-1734567890.md`). **Flag syntax**: Use `=` with no spaces: `--providers=gemini,openai` **CRITICAL**: Always place `--` before the prompt to prevent prompt text containing dashes from being parsed as flags. ## Step 2: Read and Display the Output VERBATIM Use the **Read tool** to read the output file path returned by Step 1. **CRITICAL**: Display the file content EXACTLY as written. Do NOT: - Reformat or reinterpret any text - Add your own headers or structure - Summarize or abbreviate responses - Skip any lines including separator lines (`---`) Simply copy-paste the entire file content into your response. ## Step 3: Complete the Synthesis Section The file ends with a `## Synthesis` header. Read `${CLAUDE_PLUGIN_ROOT}/prompts/synthesis.md` and write your synthesis UNDER that header following its structure (Consensus / Divergence / Recommendation) and calibration rules. ## Step 4: Notify User of Saved Output After displaying the synthesis, tell the user: > --- > (use this emoji ๐Ÿ’พ) Full output saved to `.claude/council-cache/council-TIMESTAMP.md` (use the actual filename) This lets them review the complete responses later. ## Output Format: Provider Names The output file uses emoji prefixes to visually distinguish prov...

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

AI & Automation Featured

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.

726 Updated 4 days ago
hex
AI & Automation Featured

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.

726 Updated 4 days ago
hex
AI & Automation Listed

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 10โ€“30 minutes.

0 Updated 1 weeks ago
developerjillur