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

save

Skill0 starsChanged 6 months agoMITView on GitHub

Save current session progress. Auto-detects completed tasks from TARGET.md, lets user add unlisted completions, records detailed breakdown, and writes a structured session journal entry to SAVE.md. Use when the user invokes /save.

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ingest, query and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 8 projects that use this

  • ArtemXTechSkill

    query

    Query data from this vault. USE WHEN user asks about projects, clients, tasks, daily notes. Use grep to extract frontmatter - do NOT read full files.

    Also in 4 projects that use this

  • szweibelSkill

    idea

    Generate a wide field of options when the user is brainstorming, exploring, expanding, or pressure-testing — not recommending or implementing

    Also in 3 projects that use this

  • GoogleSkill

    dashboard

    Configures and launches the GKE Capacity & Triage Dashboard scoped to a GCP project ID, GKE cluster name, or target ML workload ID. Uses the configure-and-launch-dashboard action and launch-workload-dashboard workflow to verify local dashboard health, discover cluster capacity, trigger live scans, and generate deep-linked URLs. Use when the user types "/dashboard", says "launch dashboard", "open dashboard", "show capacity", or "view triage dashboard" with a project, cluster, or workload. Don't use for general workload log querying or automated failure attribution (use the troubleshoot skill).

    Also in 4 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 5 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 7

    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 both files before doing anything

    line 13
  2. Distinctive:

    After writing, confirm what was saved

    line 15
  3. Very specific:

    Read TARGET.md and SAVE.md simultaneously.

    line 21
  4. Distinctive:

    Wait for user's reply before proceeding.

    line 41
  5. Distinctive:

    If no good match, append under the most relevant Goal

    line 48
  6. Very specific:

    If SAVE.md doesn't exist yet, create it with this header first:

    line 79
  7. Distinctive:

    If no tasks at all: still write SAVE.md entry with notes

    line 97
  8. Distinctive:

    If TARGET.md missing: warn and skip task update

    line 98
  9. Very specific:

    If SAVE.md has no prior entries: treat all current [x] as this session's work

    line 99
  10. Distinctive:

    Never delete or overwrite existing SAVE.md entries — always prepend after header

    line 100

“Common” is measured: kept by at least 6 in 10 of the 31 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

Save — Session Progress Recorder

Save this session's progress with full detail: auto-detect completed tasks, capture unlisted work, and write a structured journal entry to SAVE.md.

How to behave

  • Both files live at <project-root>/ — use the current working directory as the project root
  • Read both files before doing anything
  • Be conversational but efficient — ask in one go, not one question at a time
  • After writing, confirm what was saved

Workflow

Step 1 — Read both files in parallel

Read TARGET.md and SAVE.md simultaneously.

Step 2 — Auto-detect completed tasks (diff)

From TARGET.md: collect all [x] tasks (with parent Goal name). From last SAVE.md entry: collect tasks listed under ### 完成的 tasks. Diff = [x] tasks NOT in last SAVE.md entry = newly completed this session.

Step 3 — Present diff + ask for additions in one message

Show the user everything at once:

「偵測到這次 session 新完成的 tasks:

  • 建立開發日誌 (Goal: 法律合規準備)

還有沒有這次做了、但還沒在 TARGET.md 的事? (直接列出來,我會加進 TARGET.md 並標 [x],例如:「設定 git / GPG / SSH」「建 GitHub repo」)

這次 session 的詳細紀錄:(選填,有的話請描述,例如:用了什麼工具、踩了什麼坑、做了什麼決定)」

Wait for user's reply before proceeding.

Step 4 — Update TARGET.md

For each task the user listed as "extra completed":

  1. Find the most appropriate Goal section (fuzzy match by topic)
  2. Append as - [x] <task> under that Goal's sub-tasks
  3. If no good match, append under the most relevant Goal

Also mark any newly detected [x] items (already done in file, just confirming).

Update _Last updated_ timestamp.

Step 5 — Write SAVE.md

Prepend a new session entry at the top of SAVE.md (newest first), after the header block:

## Session: YYYY-MM-DD HH:MM TZ

### 完成的 tasks
- <task>  _(Goal: <goal>)_
- <extra task added this session>  _(Goal: <goal>)_

### 詳細紀錄
<structured breakdown of what was done — tools used, decisions made, problems solved>
If user skipped this, write "無".

### 卡點 / 重要決定
<blockers encountered or key decisions made — extracted from user's notes>
If none, write "無".

### 下次從這裡繼續
<one concrete sentence: the exact next action to take, inferred from first incomplete task in active Goal>

---

If SAVE.md doesn't exist yet, create it with this header first:

# Session Journal — ATF Validator

_Auto-generated by /save. Newest entries at the top._

---

Step 6 — Confirm

Show the user a summary:

  1. Tasks marked [x] in TARGET.md (auto-detected + newly added)
  2. The full SAVE.md entry written

Edge cases

  • If no tasks at all: still write SAVE.md entry with notes
  • If TARGET.md missing: warn and skip task update
  • If SAVE.md has no prior entries: treat all current [x] as this session's work
  • Never delete or overwrite existing SAVE.md entries — always prepend after header

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.