Does data things.
日本語の概要は準備中です。原文の説明を表示しています。
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
So basically this skill is about data and you can use it for data related tasks like when there is data and something needs to happen with the data, for example transforming it or maybe looking at it, and the way you do this is you take the data and you process it, processing can mean different things depending on what the user wants which you should figure out somehow, also sometimes the data is in files and sometimes it is not in files, if it is in files you should open the files first obviously, and then do the processing we talked about earlier, oh and one more thing, if the data is big you should be careful because big data is harder than small data, everyone knows that, also this skill can help with databases too I guess since databases contain data, just connect to the database and get the data out and then it is basically the same as before, one thing I forgot to mention at the start is that you should always check the data first before doing anything, actually do that first, before all the other steps, and if anything goes wrong just try something else until it works, the user will tell you if it is wrong probably.
まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Diagnose failing HTTP API calls - 4xx/5xx responses, timeouts, TLS errors, and auth failures - by isolating the fault layer and producing a minimal reproduction. Use when the user reports an API request failing, pastes an HTTP error response or status code, or asks why a request works in one client but not another. Do not use for designing new APIs or for performance tuning of requests that already succeed.
日本語の概要は準備中です。原文の説明を表示しています。
Reduce a failing test case, script, or input file to the smallest version that still reproduces a bug. Use when the user has a large reproduction and asks to minimize, bisect, or isolate it, or says things like "it stops failing when I remove half the file". Do not use when there is no reliable reproduction yet - help build one first, then minimize it.
日本語の概要は準備中です。原文の説明を表示しています。
Generate or update a CHANGELOG.md from merged commits and pull requests, grouped by change type and written for end users. Use when the user asks to write release notes, update the changelog, or summarize what changed between two versions or tags. Do not use for writing individual commit messages or for API-reference documentation.
日本語の概要は準備中です。原文の説明を表示しています。
Apply the team style guide to source files - naming conventions, comment style, and file organization. Use when the user asks to align code with the style guide or clean up naming.
日本語の概要は準備中です。原文の説明を表示しています。
Run the project's configured formatter (prettier, black, gofmt, rustfmt) on changed files and fix formatting-only CI failures. Use when the user asks to format code, fix a lint/format CI step, or normalize whitespace and import order. Do not use for logic changes or refactoring.
日本語の概要は準備中です。原文の説明を表示しています。
Clean and normalize messy CSV/TSV files - fix malformed rows, inconsistent headers, mixed encodings, stray delimiters, and duplicated records - and deliver a valid, verified file. Use when the user mentions a broken, messy, or malformed CSV, a file a spreadsheet tool refuses to open, or asks to deduplicate or normalize tabular data. Do not use when the deliverable is analysis or a chart rather than a cleaned file, or for Excel-native features like formulas and pivot tables.
日本語の概要は準備中です。原文の説明を表示しています。