agentleFS
marsyanggomarsyanggo/marsyang-claude-skills/skills/load/SKILL.md

load

Skill0 starsChanged 6 months agoMITView on GitHub

Load last session's progress on startup. Reads SAVE.md for session context and TARGET.md for remaining tasks, then outputs a concise summary and incomplete task list. Use when the user invokes /load to resume work.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the last saved progress and give the user a quick briefing so they can pick up where they left off.

    line 8
  2. Distinctive:

    Read both files in parallel before generating any output

    line 13
  3. Very specific:

    Read SAVE.md and TARGET.md simultaneously.

    line 21
  4. Very specific:

    If SAVE.md doesn't exist or has no entries: say "找不到 SAVE.md,尚未有 session 記錄。請先跑 /save 儲存進度。"

    line 37
  5. Distinctive:

    If all tasks are done: congratulate the user.

    line 56
  6. Very specific:

    If TARGET.md doesn't exist: say "找不到 TARGET.md,請先執行 /target 建立計畫。"

    line 58

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Load — Session Resume

Read the last saved progress and give the user a quick briefing so they can pick up where they left off.

How to behave

  • Both files live at <project-root>/ — use the current working directory as the project root
  • Read both files in parallel before generating any output
  • Be concise — this is a briefing, not a full dump
  • Output in Traditional Chinese (same language as TARGET.md)

Workflow

Step 1 — Read both files

Read SAVE.md and TARGET.md simultaneously.

Step 2 — Generate the briefing

Output the following sections in order:


上次 Session 摘要

From the most recent entry in SAVE.md:

  • Date of last session
  • What was completed (bullet list, keep it short)
  • Session notes / blockers (if any)
  • Where to pick up next

If SAVE.md doesn't exist or has no entries: say "找不到 SAVE.md,尚未有 session 記錄。請先跑 /save 儲存進度。"


剩餘未完成的 Tasks

From TARGET.md, list only the unchecked tasks (- [ ]), grouped by Goal:

## Goal: <goal name>
- [ ] <task>
- [ ] <task>

## Goal: <goal name>
- [ ] <task>

Show the count: 共 N 個 tasks 未完成

If all tasks are done: congratulate the user.

If TARGET.md doesn't exist: say "找不到 TARGET.md,請先執行 /target 建立計畫。"


建議下一步

Based on:

  1. The "下次從這裡繼續" field in SAVE.md
  2. The first incomplete task in the current active Goal (infer from context which week/goal is in progress)

Give one concrete suggestion of what to work on next. One sentence only.


After the briefing

Ask: 「準備好了嗎?要開始哪個 task?」

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.