Skills for Real Engineers. Straight from my .agents directory.
todos
Agent skill fromJetBrains/thinkrail
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
How to install todos
npx skills add JetBrains/thinkrail# or add only this skill to Claude Code: copy the folder
packages/pi-todos/skills/todos/
# into
~/.claude/skills/todos/ (all projects)
.claude/skills/todos/ (one project)
1# Chat TODO plan23## What it is45- A plan **scoped to this chat** — your tasks for the conversation. Shown to the user in the Todo6 panel; lives with the session (not committed to the repo).7- **Group = task, item = step.** One user ask = one group; its title is the *outcome* ("Fix login8 redirect"), not the process. The steps inside are the items — each has a **title**, a **status**9 (`pending` → `in_progress` → `done`), and an optional **note**. The note is **agent-facing working10 detail** — the human's default plan view shows titles + status and keeps notes behind a disclosure —11 so it's where your own tracking, reminders, and the done-criterion live (e.g. "login e2e green"),12 never a place the user must read to follow along. A task's own status is never stored — it derives from its steps.13- **Loose items are the shared raw-input queue — and they sit at the END of the plan.** Both sides14 write there: the user adds from the UI, and you may drop an unprocessed note with `todo_add` (no15 `group`, no `after`). Loose is *pre-work* — raw kernels and half-formed asks, never a step you are16 about to execute. `todo_list` renders them **last**, after every group, on purpose: an item added17 mid-task queues *after* your current work. So **finish (or resume) the task you're on before you pick18 up a loose item** — don't jump to a freshly-added item and abandon a step you had in progress.19…
Excerpt shown under the repository's Apache-2.0 license.
More skills in thinkrail
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
