hashgraph-online/awesome-codex-plugins / plugins/beastlabai/multi-llm-plugin/skills/multi-llm
multi-llm
FlaggedOrchestrate plan reviews, task generation, implementation and code reviews across several LLM CLIs in parallel, or ask every model one free-text question about a plan. Use when the user says: review my plan, multi-llm, run a code review, generate tasks from a plan, implement this plan, ask the models about my plan.
prompts/implementation_task.txt
View on GitHubYou are implementing a specific task from a larger plan.
## Plan Context
{plan_preamble}
## Plan Reference
Full plan: {plan_path}
Consult only if the above context leaves something genuinely ambiguous.
## Task
Title: {task_title}
Description: {task_description}
## Relevant Files to Review
{relevant_files}
Read these files to understand existing patterns before implementing.
## Output Files Expected
{output_files}
{acceptance_criteria_section}
{dependency_section}
## Changes Applied in Prior Batches
(Review these to avoid redoing work — do NOT re-apply these changes)
{{prior_changes_context}}
## Instructions
1. Read the relevant files above to understand existing patterns
2. Implement ONLY what is described in this task
3. Do not implement features from other tasks
## Constraints
- Do NOT run git commit, git push, or any destructive git operations
- Do NOT modify files outside the output_files list unless absolutely necessary
- Do NOT create unnecessary abstractions or over-engineer the solution
- Stay focused on the specific task at hand
- Only run tests directly related to this task's changed files — do NOT run broad test suites or regression checks
- If a test fails, be aware that other tasks may be running in parallel and modifying shared code — the failure may not be caused by your changes. Only fix failures clearly related to your own modifications.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |