一键在 Manus 中运行任何 Skill

nightshift-update-table

星标20

分支0

更新时间2026年5月18日 15:36

Make bulk changes to a Nightshift shift's table.csv — add rows, update metadata, or reset failed items. Use when the user invokes /nightshift:update-table.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

johndaskovsky

johndaskovsky/nightshift

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

软件开发工程师计算机与数学类职业·SOC 15-1252

SKILL.md

readonly

name	nightshift:update-table
description	Make bulk changes to a Nightshift shift's table.csv — add rows, update metadata, or reset failed items. Use when the user invokes /nightshift:update-table.
disable-model-invocation	true
allowed-tools	Bash(qsv ) Bash(flock ) Bash(mv ) Bash(rm ) Bash(test ) Bash(ls )
argument-hint	["shift-name"]

Bulk-modify the table.csv of shift $ARGUMENTS.

Steps

Resolve the shift
- If $ARGUMENTS is non-empty, use it.
- Otherwise, list directories in .nightshift/ (excluding archive/); auto-select if exactly one exists, otherwise use AskUserQuestion to pick.

Show current table state

flock -x .nightshift/<shift>/table.csv qsv count .nightshift/<shift>/table.csv
flock -x .nightshift/<shift>/table.csv qsv headers --just-names .nightshift/<shift>/table.csv
flock -x .nightshift/<shift>/table.csv qsv table .nightshift/<shift>/table.csv

Per task column, also show counts:

flock -x .nightshift/<shift>/table.csv qsv search --exact todo --select <task-column> .nightshift/<shift>/table.csv | qsv count
flock -x .nightshift/<shift>/table.csv qsv search --exact done --select <task-column> .nightshift/<shift>/table.csv | qsv count
flock -x .nightshift/<shift>/table.csv qsv search --exact failed --select <task-column> .nightshift/<shift>/table.csv | qsv count

Determine the operation

Use AskUserQuestion:

"What do you want to do?"

Options:
- "Add rows" — append new items.
- "Update metadata" — modify metadata column values.
- "Reset failed items" — change failed statuses back to todo.

Execute the operation

Add rows:

Ask the user for the data (CSV paste, description, data source).
Set all task status columns to todo for new rows.

Write to a temp CSV with matching headers, then append:

flock -x .nightshift/<shift>/table.csv qsv cat rows .nightshift/<shift>/table.csv .nightshift/<shift>/newrows.csv > .nightshift/<shift>/table_tmp.csv && mv .nightshift/<shift>/table_tmp.csv .nightshift/<shift>/table.csv

Remove the temp file.

Update metadata:

Ask which column and which rows.
Show a preview of the changes.
Confirm via AskUserQuestion before applying.

Update cells:

flock -x .nightshift/<shift>/table.csv qsv edit -i .nightshift/<shift>/table.csv <column> <qsv_index> <new_value>

Reset failed items:

Ask which task column (or all).

List failed items:

flock -x .nightshift/<shift>/table.csv qsv search --exact failed --select <task-column> .nightshift/<shift>/table.csv

Show how many will be reset; confirm via AskUserQuestion.

Reset each:

flock -x .nightshift/<shift>/table.csv qsv edit -i .nightshift/<shift>/table.csv <task-column> <qsv_index> todo

Show result

## Table Updated: <shift>

**Operation:** <what was done>
**Rows affected:** N
**Current state:** X total items, Y todo, Z done, W failed

Guardrails

Always confirm before modifying existing data.
Preserve item ordering when adding rows.
Set all task columns to todo for new rows.
Never reorder existing rows.
Always show the diff before applying destructive changes.

同仓库更多 Skills

同仓库

nightshift-add-task

johndaskovsky/nightshift

Add a task definition to an existing Nightshift shift, registering it in manager.md and adding a status column to table.csv. Use when the user invokes /nightshift:add-task.

2026-05-1820

nightshift-archive

johndaskovsky/nightshift

Archive a Nightshift shift by moving its directory to .nightshift/archive/YYYY-MM-DD-<name>/. Use when the user invokes /nightshift:archive.

2026-05-1820

nightshift-create

johndaskovsky/nightshift

Create a new Nightshift shift — a structured unit of batch agent work — with manager.md and an empty table.csv. Use when the user invokes /nightshift:create.

2026-05-1820

nightshift-do-task

johndaskovsky/nightshift

Execute one Nightshift task on one item, self-validate, retry on failure, and emit a structured result. Invoked by manager via `claude -p` subprocess; runs in a fresh top-level Claude Code session and inherits all user-configured MCPs.

2026-05-1820

nightshift-doctor

johndaskovsky/nightshift

Verify that Nightshift's required system dependencies (qsv, flock, jq) are installed and on PATH. Use when the user invokes /nightshift:doctor.

2026-05-1820

nightshift-start

johndaskovsky/nightshift

Start or resume execution of a Nightshift shift by forking into the manager subagent. Use when the user invokes /nightshift:start.

2026-05-1820

name	nightshift:update-table
description	Make bulk changes to a Nightshift shift's table.csv — add rows, update metadata, or reset failed items. Use when the user invokes /nightshift:update-table.
disable-model-invocation	true
allowed-tools	Bash(qsv ) Bash(flock ) Bash(mv ) Bash(rm ) Bash(test ) Bash(ls )
argument-hint	["shift-name"]

Bulk-modify the table.csv of shift $ARGUMENTS.

Steps

Resolve the shift
- If $ARGUMENTS is non-empty, use it.
- Otherwise, list directories in .nightshift/ (excluding archive/); auto-select if exactly one exists, otherwise use AskUserQuestion to pick.

Show current table state

flock -x .nightshift/<shift>/table.csv qsv count .nightshift/<shift>/table.csv
flock -x .nightshift/<shift>/table.csv qsv headers --just-names .nightshift/<shift>/table.csv
flock -x .nightshift/<shift>/table.csv qsv table .nightshift/<shift>/table.csv

Per task column, also show counts:

flock -x .nightshift/<shift>/table.csv qsv search --exact todo --select <task-column> .nightshift/<shift>/table.csv | qsv count
flock -x .nightshift/<shift>/table.csv qsv search --exact done --select <task-column> .nightshift/<shift>/table.csv | qsv count
flock -x .nightshift/<shift>/table.csv qsv search --exact failed --select <task-column> .nightshift/<shift>/table.csv | qsv count

Determine the operation

Use AskUserQuestion:

"What do you want to do?"

Options:
- "Add rows" — append new items.
- "Update metadata" — modify metadata column values.
- "Reset failed items" — change failed statuses back to todo.

Execute the operation

Add rows:

Ask the user for the data (CSV paste, description, data source).
Set all task status columns to todo for new rows.

Write to a temp CSV with matching headers, then append:

flock -x .nightshift/<shift>/table.csv qsv cat rows .nightshift/<shift>/table.csv .nightshift/<shift>/newrows.csv > .nightshift/<shift>/table_tmp.csv && mv .nightshift/<shift>/table_tmp.csv .nightshift/<shift>/table.csv

Remove the temp file.

Update metadata:

Ask which column and which rows.
Show a preview of the changes.
Confirm via AskUserQuestion before applying.

Update cells:

flock -x .nightshift/<shift>/table.csv qsv edit -i .nightshift/<shift>/table.csv <column> <qsv_index> <new_value>

Reset failed items:

Ask which task column (or all).

List failed items:

flock -x .nightshift/<shift>/table.csv qsv search --exact failed --select <task-column> .nightshift/<shift>/table.csv

Show how many will be reset; confirm via AskUserQuestion.

Reset each:

flock -x .nightshift/<shift>/table.csv qsv edit -i .nightshift/<shift>/table.csv <task-column> <qsv_index> todo

Show result

## Table Updated: <shift>

**Operation:** <what was done>
**Rows affected:** N
**Current state:** X total items, Y todo, Z done, W failed

Guardrails

Always confirm before modifying existing data.
Preserve item ordering when adding rows.
Set all task columns to todo for new rows.
Never reorder existing rows.
Always show the diff before applying destructive changes.