Menu
Practical guide for llmlb assistant CLI commands replacing the legacy MCP server flow.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Create or update GitHub Pull Requests with the gh CLI, including deciding whether to create a new PR or only push based on existing PR merge status. Use when the user asks to open/create/edit a PR, generate a PR body/template, or says 'open a PR/create a PR/gh pr'. Defaults: base=develop, head=current branch (same-branch only; never create/switch branches).
Semantic search over project source files using vector embeddings. Use to find files related to a feature, bug, or concept.
Inspect GitHub PR for CI failures, merge conflicts, update-branch requirements, reviewer comments, change requests, and unresolved review threads. Create fix plans and implement after user approval. Reply to ALL reviewer comments with action taken or reason for not addressing, then resolve threads. Notify reviewers after fixes.
Check GitHub PR status with the gh CLI, including unmerged PR detection and post-merge new-commit detection for the current branch.
Migrate legacy spec sources to artifact-first GitHub Issue specs. Supports local `specs/SPEC-*` directories and body-canonical `gwt-spec` Issues using the bundled migration script.
PTY based communication tools for Project Mode orchestration (Lead/Coordinator/Developer).
| name | llmlb-cli-usage |
| description | Practical guide for llmlb assistant CLI commands replacing the legacy MCP server flow. |
| allowed-tools | Read, Grep, Bash |
Use llmlb assistant as the default interface for API inspection and curl execution.
llmlb assistant openapi to inspect endpoint schema.llmlb assistant guide --category <...> to load task-specific API notes.llmlb assistant curl --command "curl ..." to execute requests safely.llmlb assistant openapi
llmlb assistant guide --category overview
llmlb assistant curl --command "curl http://localhost:32768/v1/models" --json
LLMLB_URL (default: http://localhost:32768)LLMLB_API_KEY for /v1/*LLMLB_ADMIN_API_KEY for /api/*LLMLB_JWT_TOKEN fallback for /api/auth/*--no-auto-auth only when you must send custom auth headers.