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…
Capture an observation — something that went wrong or worked well — to LEARNINGS.md for future reference. Quick in-session capture, not full analysis.
$ npx -y skills add isvlasov/rageatc-oss --skill learn --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/learnContext preview
The summary Claude sees to decide when to auto-load this skill.
Capture an observation — something that went wrong or worked well — to LEARNINGS.md for future reference. Quick in-session capture, not full analysis.
name: learn description: Capture an observation — something that went wrong or worked well — to LEARNINGS.md for future reference. Quick in-session capture, not full analysis. disable-model-invocation: true
Capture an observation to `LEARNINGS.md` so it is preserved for future sessions and later `/codify` sweeps.
This is **quick capture, not analysis** — root cause analysis happens later, when the user runs `/codify`. Record what happened clearly enough that a future reader can understand it without this session's context.
1. **Locate or create `LEARNINGS.md`** in the project root. If it does not exist, create it using the LEARNINGS.md template in the scaffolding-project skill (current frontmatter format lives there). 2. **Draft the entry from session context.** With no arguments, the user is signalling "that was noteworthy — record it": draft your best understanding and ask "Here's what I'd capture — does this match how you see it?". With an argument, fold the user's pointer or perspective into the draft. Either way you write the entry; the user confirms or corrects — they should not have to explain the event from scratch. 3. **Append the entry** following the format in the file's frontmatter comment. Distil, do not transcribe. 4. **Confirm** — tell the user what was recorded and where. Nothing else needed.
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…