status
Render the state of the work in flight as an ASCII status board in the terminal, instead of a status paragraph.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- status
- description
- Render the state of the work in flight as an ASCII status board in the terminal, instead of a status paragraph.
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml242 B
03 SKILL.md 正文
Status board
Show me where everything stands as a board in the terminal. The board replaces the status paragraph. Do not write both.
- Group rows under a short uppercase header with a rule line, one section per phase or stream of work.
- One row per item: a short name, a dotted leader to a fixed column, one status mark, then a terse note. Keep names short and put the detail in the note.
- Use one glyph per state, the same across the whole board: ✅ done, ? in progress, ? blocked or waiting, ⬜ not started, ✖ dropped or closed. Marks go in the mark column only.
- Write a dependency in the note as
← waits on X. If everything waits on the same thing, say it once. - Close with a section for what waits on the human: decisions, approvals, anything only they can do. Add one line for what is running right now if agents or jobs are in flight.
- Include only rows you can vouch for. Unknown state is ⬜ with "not verified". Never guess a mark.
- Fit about 80 columns, align the columns, and use no box-drawing tables and no prose paragraphs.
INTAKE ──────────────────────────────────────────────────────────────
scope note ......................... ✅ 3 items, agreed
source data ........................ ✅ 1.2k rows, spot checked
field mapping ...................... ✅ 12 of 12 mapped
access keys ........................ ? ← waits on your approval
BUILD ───────────────────────────────────────────────────────────────
importer ........................... ✅ handles the 3 known formats
dedupe pass ........................ ? running, ~200 dupes so far
report layout ...................... ⬜ not started
csv export ......................... ✖ dropped, nobody asked for it
RELEASE ─────────────────────────────────────────────────────────────
staging run ........................ ⬜ ← waits on dedupe pass
team review ........................ ⬜ not scheduled
rollback note ...................... ⬜ not verified
WAITING ON YOU ──────────────────────────────────────────────────────
approve the access keys, which closes intake
pick the report layout: one page, or one per region
RUNNING NOW: dedupe pass, about 5 minutes left
04 同仓库更多 Skills
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
wait-what
Stop. That last message did not land: re-pitch it.
unslop
Cut AI tells from any writing.