Menu
SkillsMP has collected 16 skills from generic-automation-and-it/smooth-llm-imposter. Open a skill to review its source and details.
Showing 16 of 16 collected skills.
Commit current changes with conventional commits format, ensure the /ai-review trigger is present on the final commit (preserving any Git trailer block), and push to remote repository. Use when committing and pushing changes so the pushed PR gets a full AI…
Mint a synthetic session id on the SmoothLlmImposter router and map it to the current caller session, so subsequent forwarded requests are stamped with the proxy-owned id instead of the caller's. Use when the user says "mint a new imposter session", "rotate…
Probe the SmoothLlmImposter router for the resolved upstream model behind the current harness/agent by issuing a non-streaming `--who?` request. Use when the user asks "which model am I really hitting", "who am I talking to", "what is the imposter target for…
Analyze and execute AI PR review feedback with fix/skip decisions. Use when a user asks to parse an AI review, apply selected fixes, and finalize review processing for GitHub or Azure DevOps pull requests. Detects the review source — for a GitHub Copilot…
Commit current changes, push to remote, and create or update a pull request on GitHub. Use when making changes and preparing a complete pull request for review.
Invoke to author a High-Level Design (HLD) at discovery / prototyping phase. Design-only: delivers intent + spec for AI and humans to build against — no implementation plan, no code outside examples/. Trigger keywords: "HLD", "high level design", "design…
Create a GitHub Task (sub-issue) from the current git diff vs main and link it as a sub-issue of a parent Feature in the local GitHub Project. Use when Codex needs to summarize branch changes into a horizontally sliced task with acceptance criteria and create…
Start and run a listen-first braindump session for tickets, issues, ADRs, worktasks, PR descriptions, requirements, designs, or implementation plans. Use when the user says they want to braindump, think out loud, capture rough requirements, or provide context…
Reformat one reply into terse, high-density output: answer first, bullets/tables, no preamble or niceties, end with a TL;DR. Trigger on "/ai-mansplain", "give it to me straight", "no fluff", "bullet it", "tl;dr this", or any signal the user wants signal over…
UPSERT the smooth-devex-template agentic scaffold into an existing repo. Asks which tools (Claude Code, Codex, Copilot) to configure, whether to copy .NET solutioning, and whether to overwrite existing agentic files.
Load ancestor AGENTS.md context for a target file. Use when Codex, Claude, Copilot, or another agent needs local domain context before reading or editing source files.
Load or create functional AGENTS.md context files before implementation work. Use when starting frontend/backend/devops code changes, when a task references a domain or feature, or when required context is missing and must be discovered or created.
Commit current changes with conventional commits format and push to remote repository. Use when committing and pushing changes to the upstream remote.
Commit current changes with conventional commits format, respecting logical units of work. Use when making local commits to the repository with properly formatted conventional commit messages.
Sync the current working branch with origin/main and optionally resolve merge conflicts. Use when synchronizing local branch with the latest changes from main, with automatic or manual conflict resolution.
Convention for creating, updating, or modifying rule files in .agents/rules/. Use when adding, editing, or restructuring rule files to ensure compatibility across Claude Code, GitHub Copilot, Cursor, and OpenAI Codex.