agentleFS
Sign inStart free
DATA-AI-XYZDATA-AI-XYZ/Tandem/skills/update/SKILL.md

update

Skill0 starsChanged 6 months agoMITView on GitHub

Pull Tandem kit improvements into an already-installed project without touching your work — refresh only kit-owned files (templates, standards, tooling) + regenerate the dashboard, never the operator's artefacts or folder structure. Use when the user asks to update Tandem, upgrade the PM kit, pull kit changes, refresh tooling, or invokes /tandem:update. Thin wrapper over the canonical update.js (pm:update); shows the change diff and confirms before applying.

61 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use end, create 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.
  • torarnvSkill

    end

    Wrap up a work session. Updates memory files, logs decisions and lessons, appends to the session log.

    Also in 3 projects that use this

  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • bitwize-music-studioSkill

    tutorial

    Provides interactive guided album creation for new users. Use when the user is new to the plugin or asks for a walkthrough of the album creation process.

    Also in 3 projects that use this

  • MicrosoftSkill

    note

    Use this skill to record progress, partial findings, hypotheses, and page-anchored evidence while investigating a long document. Call Note aggressively — any time you read a page and confirm, narrow, or update your understanding of the user's question. Triggers include "jot that down", "save this finding", "note that page 7 says X", or (more often) implicit internal signals — you just learned something and want it recoverable later. Notes persist in the session and Review can select among them. Never paraphrase notes back from memory; write them as you go.

    Also in 4 projects that use this

  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 4 projects that use this

  • jholhewresSkill

    backup

    Backup and restore — files, databases, and system backups

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 59 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check for drift first: npm run pm:doctor prints update available when the installed kitVersion is behind the shipped one (read-only — it …

    line 26
  2. Distinctive:

    Keep deterministic logic in the script — the skill only previews (diff), confirms, and reports.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 59 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

Tandem: update (non-destructive refresh)

Refresh an already-installed project's kit to the current version without ever touching the operator's work. This skill is the entry point; the deterministic, safety-critical work lives in the canonical update.js script (pm:update).

Source of truth

_00-Project-Management/93-Scripts/update.js (run as npm run pm:update). See ADR-0073 (update is manually triggered; pm:doctor only reports drift) and ADR-0072 (kit/user ownership boundary).

The non-destructive contract (load-bearing)

  • Refreshes only ownership:kit content — manifest kit seed files (templates, standards, the PM-folder CLAUDE.md) + the 93-Scripts/ tooling.
  • Never writes an ownership:user path (PROJECT-CONTEXT.md, MONITOR.md, ACTIVE.md, settings.json) or any work folder (epics/stories/…) — they stay byte-identical.
  • Never creates, removes, or moves a folder — the folder set is unchanged.

How to run it

  • Preview the change diff first (recommended): node _00-Project-Management/93-Scripts/update.js --dry-run
  • Apply: npm run pm:update (or --target <dir> for another project root)
  • Check for drift first: npm run pm:doctor prints update available when the installed kitVersion is behind the shipped one (read-only — it writes nothing).

Conversational steps this skill owns

  • Show the diff — run --dry-run and present the list of kit files that would refresh + the kitVersion bump, so the operator sees exactly what changes.
  • Confirm before applying — only run the real pm:update after the operator confirms the diff.
  • Report — after applying, surface the count of refreshed files, the new kitVersion, and the regenerated dashboard path.
  • Remind on restart — if the plugin itself (not just kit files) was updated this session, the final output must remind the operator to restart their Claude Code session; transient hook errors referencing the old version's cache path are expected until they do (BUG-20260718-02).

Non-negotiable rules

  • Adds no destructive behaviour beyond update.js. Never deletes or moves the operator's work.
  • Keep deterministic logic in the script — the skill only previews (diff), confirms, and reports.

Next

Next: /tandem:session-start to re-orient after a refresh, or /tandem:weekly-monitor to fold the change into the Friday cadence.

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