felipemelendez/llm-orchestrator
19 skills
$npx skills add felipemelendez/llm-orchestratorSkillInstalls
brainstormingYou MUST use this before any creative work — building a feature, adding functionality, designing a system, or changing behavior — before any code is written.dispatching-parallel-agentsUse when 3+ tasks are independent — no shared files, no order dependency — and can run concurrently. Fan-out only; per-task review happens after all return.dispatching-subagentsUse when running plan tasks sequentially with per-task two-stage review — the default for tasks with dependencies, sensitive code, or shared files another task…executing-plansUse when you have a written plan and need to drive it task-by-task to completion.finishing-a-branchUse when implementation is complete and tests pass. Decides between merge, PR, keep, or discard — without destructive actions unless the user confirms.handing-off-to-fresh-contextUse when context is filling on a long task and you should leave a short note so work resumes cleanly after the conversation is compacted.managing-memoryUse when the user says "remember", "save this", "I told you before", or "forget that".receiving-code-reviewUse when responding to code review feedback — from a human, from another agent, or from the two-stage review flow.requesting-code-reviewYou MUST use this when a diff is ready — before merge, before a PR, or before claiming any feature done.research-classifierUse when about to invoke brainstorming or writing-plans, before a spec or plan is committed. Decides whether to verify API surfaces against current docs first.systematic-debuggingYou MUST use this when ANY bug, test failure, exception, regression, or unexpected behavior appears — before proposing or applying any fix.templatesUse when <triggering condition>. <One more sentence on scope if needed.>test-driven-developmentYou MUST use this when implementing any feature or bugfix where tests are practical — before writing implementation code.using-git-worktreesUse when work needs isolation from the current branch — long-running feature, risky refactor, parallel attempt.using-orchestratorUse when starting any session in an LLM Orchestrator project. Establishes the Concise Agent Protocol response shapes and mandates skill invocation before any…using-workflowsUse when deciding whether an already-chosen fan-out (multi-dimension review, parallel implementation, multi-source research) runs on the Workflow tool or…verification-before-completionYou MUST use this before claiming any work is done, fixed, passing, or ready to merge. Forces a real run of the verifying command first.writing-plansYou MUST use this after a spec is approved and before any implementation work begins.writing-skillsUse when adding a new skill or editing an existing one. Keeps the catalog short, the frontmatter correct, and the body free of coercion and padding.