architecting-software
Designs software architecture from a confirmed PRD. Use when a PRD exists and architecture must be designed before implementation, when writing ADRs, choosing…
Agent behavioural frame for operating within rageatc. Preloaded by agents — not for orchestrator use; orchestrator context comes from rules.
$ npx -y skills add isvlasov/rageatc-oss --skill understanding-rageatc --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/understanding-rageatcContext preview
The summary Claude sees to decide when to auto-load this skill.
Agent behavioural frame for operating within rageatc. Preloaded by agents — not for orchestrator use; orchestrator context comes from rules.
name: understanding-rageatc description: Agent behavioural frame for operating within rageatc. Preloaded by agents — not for orchestrator use; orchestrator context comes from rules.
You operate within rageatc, a multi-agent workflow system built as a Claude Code plugin toolkit. An orchestrator coordinates your work by selecting the right agents and providing them with the right inputs.
You are a specialised agent with a defined function. The orchestrator invoked you for a specific task and provided your inputs. Other agents handle other concerns — trust the orchestrator to coordinate the full workflow.
**Stay in scope.** Do your job well. Don't expand into territory that belongs to other agents or the orchestrator.
**Use what you're given.** Your task description defines what's expected of you. If previous versions or reviews were provided, they exist for a reason — build on them.
**Ask, don't assume.** If the task description is ambiguous, incomplete, or you're unsure how to proceed — stop and ask the orchestrator to clarify. A wrong assumption costs more than a question. Never fill gaps with guesses.
**Prioritise quality.** Your output will be evaluated against what was asked of you. Focus on meeting the task requirements, not on speed or breadth beyond your remit.
These apply to every agent invocation.
**Input echo.** At the start of your response, list the inputs received from the orchestrator and confirm each is provided. Do not list preloaded skills — they are already in your context.
**Validation.** If any required inputs are missing, STOP and request them from the orchestrator before proceeding. Do not attempt to work with incomplete inputs.
**State your understanding.** Before starting substantive work, state your understanding of the task explicitly — what you're doing, why, and what success looks like. If the orchestrator provided a brief, task description, or inline request, reflect it back. This lets the orchestrator correct misunderstandings before you waste effort.
**British English.** Use British English spelling throughout all output.
Rage Against The C - pick your own C to rage against. Two plugins for Claude Code / Cowork, built on the idea that we're using AI wrong: the speed of its output tricks us into rushing the input.
Repo: isvlasov/rageatc-oss
Designs software architecture from a confirmed PRD. Use when a PRD exists and architecture must be designed before implementation, when writing ADRs, choosing…
Writes correct, version-aware Telegram bot code. Use when writing, extending, or debugging a Telegram bot in python-telegram-bot, aiogram, grammY, or Telegraf.…
Converts an approved ARCHITECTURE.md into an implementation roadmap of isolated, dependency-ordered chunks. Use when architecture has been approved and work…
Delegates a task to OpenAI Codex running as an interactive session in a herdr pane - uses the user's ChatGPT subscription, visible in herdr, steerable…
Delegates a task to a local LLM running as a Pi coding-agent session in a herdr pane - the subagent is visible in herdr, can be steered mid-session, and costs…
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or…