llm-council
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
83
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly articulates a unique, specialized capability with explicit 'Use when' guidance. The main weakness is that trigger terms lean technical (CLI agents, JSON outputs) rather than natural user language, which may reduce discoverability when users describe their needs in plain terms.
Suggestions
Add more natural user-facing trigger terms like 'compare implementation approaches', 'get multiple AI opinions', or 'consensus-based planning' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'orchestrate a configurable, multi-member CLI planning council', 'produce independent implementation plans', 'anonymize and randomize them', 'judge and merge into one final plan'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (orchestrate multi-member CLI planning council, produce/anonymize/judge/merge plans) AND when ('Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'planning council', 'Codex', 'Claude Code', 'Gemini', 'OpenCode', 'CLI agents', but these are fairly technical. Missing more natural user phrases like 'compare plans', 'get multiple opinions', or 'consensus planning'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: multi-agent CLI planning councils with specific tools named (Codex, Claude Code, Gemini, OpenCode). Unlikely to conflict with other skills due to the unique combination of anonymization, randomization, and multi-agent orchestration. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and good progressive disclosure. The JSON configuration examples and CLI commands are concrete and executable. Main weaknesses are some redundancy in session management instructions and missing explicit validation checkpoints in the multi-step workflow.
Suggestions
Remove duplicate session management instructions - consolidate the 30-minute timer guidance into either Workflow step 7 or Constraints, not both
Add explicit validation checkpoint after step 3 (e.g., 'Verify all planners launched successfully before proceeding') to strengthen the workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is mostly efficient but has some redundancy - session management instructions are repeated in both Workflow and Constraints sections, and some explanations could be tightened (e.g., the note about not panicking if stuck). | 2 / 3 |
Actionability | Provides concrete, executable commands (python3 scripts/llm_council.py run --spec), specific JSON configuration examples, clear file paths, and copy-paste ready agent configuration. The workflow steps are specific and actionable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (1-7) with some validation (retry up to 2 times, validate Markdown structure), but lacks explicit validation checkpoints between steps. The 'yield and alert user' on failure is mentioned but the recovery path is vague. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, well-organized sections, and one-level-deep references to architecture, prompts, templates, and CLI notes. Content is appropriately split between quick start, workflow, configuration, and constraints. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.