跳到正文
cccskills
免费在 GitHub 公开

agent-carnet

Save research findings, fixes, and decisions in a shared Markdown notebook on disk. Search and organize notes across sessions, record when they inform actual work, and let unused notes expire automatically.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

查看安装方法

适用场景

  • Saving research findings for future sessions
  • Reusing fixes for difficult bugs
  • Recording design decisions and their reasoning
  • Keeping notes for work to resume later

包含的文件(3)

  • SKILL.md4.6 KB
  • references/cookbook.md4.5 KB
  • references/frontmatter.md6.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agent Carnet

A tiny CLI that gives you a shared markdown notebook on disk under .carnet/<category>/<slug>.md. Notes have a 30-day default lifespan that resets every time they are read or applied; useful ones survive, stale ones drift to .trash/ automatically.

Quick reference

# Save (always pass --summary and --agent claude-code)
echo "body content" | agent-carnet save deps/iconv-issue \
  --summary "iconv-esm v0.7 types broken — pin to v0.6" \
  --agent claude-code \
  --tags compat,esm

# Recall
agent-carnet find iconv               # search summaries (does NOT bump lifespan)
agent-carnet list                     # category-grouped overview, sorted by last_used
agent-carnet list --sort use_count    # most-applied notes first
agent-carnet show deps/iconv-issue    # read full content (bumps last_used; weak use signal)

# Mark as actually applied (strong use signal — bumps last_used + use_count)
agent-carnet used deps/iconv-issue

# Maintain
agent-carnet move <from> <to>
agent-carnet rm <path> --yes

When unsure of a subcommand's full flag set, run agent-carnet <command> -h (e.g. agent-carnet save -h, agent-carnet used -h). Each subcommand prints its own focused help — required arguments, options, and examples — without invoking filesystem operations.

When to save

Save proactively when you discover something worth preserving across sessions:

  • Research findings that took effort to derive
  • Non-obvious patterns / gotchas in the codebase
  • Solutions to tricky problems
  • Architectural decisions and the reasoning behind them
  • In-progress work that may be resumed later

When to recall

Before starting related work or when context might exist:

  • agent-carnet find <topic> — quick scan of summaries
  • agent-carnet list <category> — browse a folder
  • agent-carnet show <path> — actually read (resets last_used; only use when the content matters)

When to call used

Call agent-carnet used <path> after a carnet actually shaped your work:

  • You applied the recorded fix and it solved the bug.
  • You consulted the carnet before retrying a hypothesis and skipped a dead-end.
  • You used the canonical name from a vocab carnet in new code instead of inventing your own.

used increments use_count — a durable importance signal that survives across sessions and lets future readers (and agent-carnet list --sort use_count) surface load-bearing notes.

Reading a carnet does NOT count. show already keeps it alive (weak signal); used records that the note was worth keeping for a real reason (strong signal).

Hard rules

  • --summary is required. Make it decisive — reading the summary in isolation tells the next reader (or the next agent) whether to read further.
  • --agent claude-code is required.
  • find does NOT bump anything. show bumps last_used. used bumps last_used AND increments use_count.
  • updated tracks content modification only (save, save --update). It is independent of last_used and is not the lifespan driver.
  • The 30-day expiry is automatic — do not manually clean up. keep: true pins permanent notes.
  • Auto-prune runs on every CLI invocation; deleted carnets land in .carnet/.trash/ for 7 days before hard delete.

Path conventions

  • <category>/<slug> — kebab-case, no leading slash, no ...
  • Categories are folders; create new ones freely as needed.
  • Subcategories are allowed: deps/esm/iconv-issue works.

When to read references/

This SKILL.md is enough for everyday note-keeping. Open the references/ files only when one of these specific cases applies — they are not always-on context, so do not load them speculatively.

Read this fileWhen
references/cookbook.mdYou are about to use (or are being asked about) a tag-based pattern such as tags: [vocab] for project terminology or tags: [hypothesis] for debugging dead-ends. The file shows the full pattern, including how to structure the body and meta: for that pattern.
references/frontmatter.mdYou need to write or read the meta: extension namespace, set a non-trivial lifespan / keep, or understand why an unfamiliar frontmatter field is or is not preserved on save.

If neither case applies, do not read references/. The base of this file already covers daily save/find/show/touch/move/rm flows.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Develop and maintain the WXT browser extension that adds a Repomix button to GitHub repository pages. The skill covers Chrome, Firefox, and Edge compatibility, extension scripts, translation files, and commands for building, linting, and testing.

中文简介正在准备中。当前显示英语简介。

  • Maintaining the GitHub Repomix button extension
  • Checking Chrome, Firefox, and Edge compatibility
  • Updating translations or adding a language
yamadashy/repomix2.9万2026年10月18日 更新

Write Git commit messages that preserve why changes were made. The skill keeps Conventional Commits subject lines and adds structured body entries for user intent, decisions, rejected alternatives, constraints, and lessons supported by the session context.

中文简介正在准备中。当前显示英语简介。

  • Recording the purpose behind a feature
  • Preserving design decisions and rejected alternatives
  • Documenting constraints and implementation lessons
yamadashy/repomix2.9万2026年10月18日 更新

repomix

免费

Combine code from local directories or GitHub into one structured file for AI analysis. Examine project structure, search for related code, and check estimated tokens, the units AI models use to process text.

中文简介正在准备中。当前显示英语简介。

  • Preparing a single codebase file for AI analysis
  • Reviewing a project's directory structure
  • Finding authentication code and database models
yamadashy/repomix2.9万2026年10月18日 更新

Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.

中文简介正在准备中。当前显示英语简介。

  • Understanding an unfamiliar project's structure
  • Locating authentication code and API endpoints
  • Checking file counts and estimated AI tokens
yamadashy/repomix2.9万2026年10月18日 更新

Maintain the Repomix documentation website by editing guides, navigation, and search labels across languages. Follow its VitePress file structure to add a language and keep translations aligned with the English source.

中文简介正在准备中。当前显示英语简介。

  • Updating the Japanese installation guide
  • Changing navigation and sidebar labels
  • Adding a new language to the documentation
yamadashy/repomix2.9万2026年10月18日 更新

查看 yamadashy 的全部技能

报告此技能的问题