H
haslanli/glance-skill
Claude Code skill that re-tells long answers at a glance: the answer first, a picture when there's data,…
View on GitHub ↗Link checked 2026-11-14 · HTTP 200 · opens the vendor's own site
- Star count
- 0 ★ · haslanli/glance-skill · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-13 · last seen 2026-11-14 · seen 2× · listed by 2 sources
- Score
- score 203 · 2 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
haslanli/glance-skill;first catalogued 2026-11-13;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# glance
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Claude's long answers, readable at a glance.
### Live demo →
Every picture on the site is live: sort and filter the tables, drag to compare with the original answer, and hover any number to see the line it came from.
glance is a skill for Claude Code. Type /glance after a long answer, and Claude tells it again for someone short on time or background. You get the answer in one plain sentence, a picture when the answer has data, and a few short bullets for the rest. It's built to keep every number, name, path, command, warning and open question, and to add nothing. So it cuts wording, not facts: on real answers the text comes out about half to two-thirds as long, and a table keeps its size, because every value stays. In the Claude desktop app the picture is drawn right in the chat; in a terminal it becomes a markdown table.
Contents: Live demo · Install · Big tables · Examples: bills, test results, performance, progress · Commands · Why not dataviz? · Readable by everyone · New in v3
## Install
bash
git clone https://github.com/haslanli/glance-skill ~/.claude/skills/glance
Claude Code picks up new skills while it runs, so there's no restart. If ~/.claude/skills didn't exist before, run /reload-skills once. To update later, run git -C ~/.claude/skills/glance pull.
## Big tables
A wide table is where a plain answer reads worst. Claude writes it as markdown, the chat lays it out at the width of its column, and every column with a long cell takes the room: short columns shrink to stacks of wrapped words, rows grow four lines tall, and the rows that matter look like all the others. glance rebuilds the same table: the same 14 tools and the same numbers, one line per row, grouped by what to do and sorted by what you'd save, with a bar of used and unused seats on every row and the long advice moved into short notes under each name and the bullets.
Stock Claude: 622 words, with a 14-row, 6-column table of renewals and three sections after it. Its table as the chat lays it out:
The whole table
glance, on the same answer:
The whole picture
A SaaS renewal review for a made-up 140-person company, answered by stock Claude (Opus 5.5), then re-told with /glance. Both pictures are the same width; the stock table is drawn by the browser's own table layout, the way a chat column draws markdown. glance's reply text: 219 words, from 622.
## Examples
Each picture is glance's own reply to a sample answer, drawn with the current kit and cropped to the sentence and the picture. The bullets that follow it in the chat are left out. Above each one is what the original answer looked like. When an answer is mostly reasoning, glance draws nothing and keeps it to a sentence and bullets.
### Bills
#### Why a bill jumped
Before: 276 words: the monthly totals in one line, a six-row table by service, what happened, four fixes and three caveats.
An AWS bill that more than doubled. glance picked the increase as a headline figure, columns for six months of totals, then a table by service with each change in a tinted column.
The whole picture
#### Teams against their budgets
Before: 152 words: a table of five teams' Q2 spend, Q3 spend and Q3 budget, why two teams went over, and what happens next.
### Live demo →
Every picture on the site is live: sort and filter the tables, drag to compare with the original answer, and hover any number to see the line it came from.
glance is a skill for Claude Code. Type /glance after a long answer, and Claude tells it again for someone short on time or background. You get the answer in one plain sentence, a picture when the answer has data, and a few short bullets for the rest. It's built to keep every number, name, path, command, warning and open question, and to add nothing. So it cuts wording, not facts: on real answers the text comes out about half to two-thirds as long, and a table keeps its size, because every value stays. In the Claude desktop app the picture is drawn right in the chat; in a terminal it becomes a markdown table.
Contents: Live demo · Install · Big tables · Examples: bills, test results, performance, progress · Commands · Why not dataviz? · Readable by everyone · New in v3
## Install
bash
git clone https://github.com/haslanli/glance-skill ~/.claude/skills/glance
Claude Code picks up new skills while it runs, so there's no restart. If ~/.claude/skills didn't exist before, run /reload-skills once. To update later, run git -C ~/.claude/skills/glance pull.
## Big tables
A wide table is where a plain answer reads worst. Claude writes it as markdown, the chat lays it out at the width of its column, and every column with a long cell takes the room: short columns shrink to stacks of wrapped words, rows grow four lines tall, and the rows that matter look like all the others. glance rebuilds the same table: the same 14 tools and the same numbers, one line per row, grouped by what to do and sorted by what you'd save, with a bar of used and unused seats on every row and the long advice moved into short notes under each name and the bullets.
Stock Claude: 622 words, with a 14-row, 6-column table of renewals and three sections after it. Its table as the chat lays it out:
The whole table
glance, on the same answer:
The whole picture
A SaaS renewal review for a made-up 140-person company, answered by stock Claude (Opus 5.5), then re-told with /glance. Both pictures are the same width; the stock table is drawn by the browser's own table layout, the way a chat column draws markdown. glance's reply text: 219 words, from 622.
## Examples
Each picture is glance's own reply to a sample answer, drawn with the current kit and cropped to the sentence and the picture. The bullets that follow it in the chat are left out. Above each one is what the original answer looked like. When an answer is mostly reasoning, glance draws nothing and keeps it to a sentence and bullets.
### Bills
#### Why a bill jumped
Before: 276 words: the monthly totals in one line, a six-row table by service, what happened, four fixes and three caveats.
An AWS bill that more than doubled. glance picked the increase as a headline figure, columns for six months of totals, then a table by service with each change in a tinted column.
The whole picture
#### Teams against their budgets
Before: 152 words: a table of five teams' Q2 spend, Q3 spend and Q3 budget, why two teams went over, and what happens next.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/haslanli-glance-skill/)
- Source
- github · https://github.com/haslanli/glance-skill
- Browse by field
- Open source
- Listed by
- 2 independent sources
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.