agentleFS
Sign inStart free
CipherNovaaCipherNovaa/agent-skills/skills/myos/resume/SKILL.md

resume

Skill0 starsChanged 13 days agoMITView on GitHub

Cold-start orientation — reconstruct exactly where work stands, on any device, losing no thread. Use at the start of a session or after a laptop↔desktop switch.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pause, status and 10 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.
  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 7 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 15 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 7 projects that use this

  • MicrosoftSkill

    config

    Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 4 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 4

    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:

    Start of every session.

    line 18
  2. Distinctive:

    After a device switch (laptop ↔ desktop).

    line 19
  3. Very specific:

    All under <architect_memory> = python $MYOS_ENGINES/myos_paths.py get architect_memory, except the build log:

    line 22
  4. Very specific:

    If Active Threads.md updated: is older than other recently-edited memory files → flag a possibly stale anchor.

    line 33
  5. Distinctive:

    Read-only: Never edits Active Threads, the build log, or memory.

    line 40
  6. Very specific:

    The RESUME callout wins: If it's missing or contradicts the build log's last entry → don't guess: say so, show both, and …

    line 41
  7. Distinctive:

    Start of every session and every device switch.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 51 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

resume

The first thing to run at the start of a session or after a device switch. Turns "where was I?" into a 20-second answer. Read-only — it orients; it does not change vault state. Background/why: [[NOTES]].

When to Use

  • Start of every session.
  • After a device switch (laptop ↔ desktop).

Source of truth (read in this order)

All under <architect_memory> = python $MYOS_ENGINES/myos_paths.py get architect_memory, except the build log:

  1. Active Threads.md — the ▶ RESUME callout is the single source of truth for where we are + next step.
  2. MEMORY.md — the memory index (terse). Pull the one project memory the RESUME block names.
  3. <myos>/myOS Build Log.md (myos_paths.py get myos) — the last entry is the current frontier (cross-check against RESUME).
  4. Escalations.md — any Status: OPEN items Hermes queued.

Procedure

  1. Device / sync check first (the cross-device guard):
    • git -C "<vault>" log -1 --format='%cd %s' → last backup.
    • git -C "<vault>" status -s → uncommitted local changes (count).
    • systemctl --user is-active syncthing → if active, files auto-sync (anchors are current); else warn this device may be stale.
    • If Active Threads.md updated: is older than other recently-edited memory files → flag a possibly stale anchor.
  2. Read the anchors (order above). Quote, don't paraphrase, the RESUME block.
  3. Triage the threads into 🟢 Active · 🟡 Deferred · 📌 Pinned/Paused · ⚠️ Watch · 🔺 OPEN escalations. For each 🟢: name — one-line state — next action.
  4. Emit the resume brief (tight): Where we are (1–2 lines) · ▶ Next action (single step) · Threads (triaged; parked/dead collapsed to a count) · Escalations (count + one-liners, or "none") · Device/sync (last backup · N uncommitted · syncthing?).
  5. Then stop and ask whether to start the next action. Do not auto-execute it.

Pitfalls

  • Read-only. Never edits Active Threads, the build log, or memory. (Updating those at the end of work is a separate discipline.)
  • The RESUME callout wins. If it's missing or contradicts the build log's last entry → don't guess: say so, show both, and escalate-to-architect (or hand to the user).
  • Don't re-derive what's already written — surface the anchors, don't reconstruct from code/git.
  • Hermes-lite (offline): Hermes presents anchors + triage + device/sync line verbatim. It must not attempt a judgment/multi-step next action — that's the architect's; leave it for the user or escalate.

Verification

  • The brief names a single ▶ Next action taken from the RESUME callout (not invented).
  • The device/sync line is present (last backup · uncommitted count · syncthing state) so drift is visible at a glance.

Cadence

Start of every session and every device switch.

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.

Check your setup, free