agentleFS
kv0906kv0906/pm-kit/.claude/skills/update/SKILL.md

update

Skill138 starsChanged 7 months agoMITView on GitHub

Check for and apply PM-Kit framework updates from GitHub releases. Reads local VERSION, queries latest release, shows changelog, and runs update script.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 56 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Check for new PM-Kit releases and safely apply framework updates without touching your notes or config.

    line 10
  2. Very specific:

    Read the local VERSION file to determine the installed version.

    line 24
  3. Very specific:

    If VERSION doesn't exist, tell the user to run ./scripts/setup.sh first.

    line 30
  4. Distinctive:

    If local version matches latest: report "You're on the latest version (vX.Y.Z)"

    line 49
  5. Distinctive:

    If update available: show the version diff and changelog excerpt

    line 50
  6. Distinctive:

    Run the update script, passing through any flags the user provided:

    line 54
  7. Distinctive:

    Never touch user content (notes, meetings, etc.)

    line 72
  8. Very specific:

    Update the VERSION file

    line 73
  9. Distinctive:

    After the script completes, summarize:

    line 77

“Common” is measured: kept by at least 6 in 10 of the 56 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

/update — Framework Updates

Check for new PM-Kit releases and safely apply framework updates without touching your notes or config.

Usage

/update           # Check + apply if available
/update --check   # Check only, no download
/update --dry-run # Preview what would change without applying

What This Skill Does

1. Check Current Version

Read the local VERSION file to determine the installed version.

cat VERSION

If VERSION doesn't exist, tell the user to run ./scripts/setup.sh first.

2. Check Latest Release

Query the GitHub API for the latest release:

# Detect repo from git remote, fallback to kv0906/pm-kit
REPO_SLUG="kv0906/pm-kit"
REMOTE_URL="$(git remote get-url origin 2>/dev/null || true)"
if [ -n "$REMOTE_URL" ]; then
  REPO_SLUG="$(echo "$REMOTE_URL" | sed -E 's#.*[:/]([^/]+/[^/.]+)(\.git)?$#\1#')"
fi

curl -sS "https://api.github.com/repos/${REPO_SLUG}/releases/latest"

3. Compare Versions

  • If local version matches latest: report "You're on the latest version (vX.Y.Z)"
  • If update available: show the version diff and changelog excerpt

4. Apply Update (if user confirms)

Run the update script, passing through any flags the user provided:

# If user ran /update --check:
./scripts/update.sh --check

# If user ran /update --dry-run:
./scripts/update.sh --dry-run

# If user ran /update (no flags):
./scripts/update.sh

The script will:

  • Back up current framework files to _archive/_updates/{date}/
  • Download and extract the latest release
  • Overwrite framework files (skills, templates, scripts, docs)
  • Skip hybrid files (_core/config.yaml, .gitignore) — shows diff instead
  • Never touch user content (notes, meetings, etc.)
  • Update the VERSION file

5. Post-Update Summary

After the script completes, summarize:

  • Files updated and files skipped
  • Backup location
  • Any hybrid files that need manual merge
  • Remind user to run /push to commit changes

What Gets Updated vs Preserved

CategoryExamplesAction
FrameworkCLAUDE.md, _templates/*, .claude/**, scripts/*, handbook/*Overwrite (backed up first)
Hybrid_core/config.yaml, .gitignoreDiff shown, user merges
User content00-inbox/, daily/, decisions/, blockers/, meetings/Never touched

Download now (ZIP)

  • Other versions59 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 59

    1. anthropics/knowledge-work-plugins★ 34ksame name
    2. Q00/ouroboros★ 6.3ksame name
    3. vellum-ai/vellum-assistant★ 1.5ksame name
    4. patrickjaja/claude-desktop-extra★ 713same name
    5. me2resh/apexyard★ 532same name
    6. daloopa/investing★ 489same name
    7. TokenRollAI/cc-plugin★ 483same name
    8. egregore-labs/egregore★ 293same name
    9. k1p1l0/claude-telegram-supercharged★ 141same name
    10. buildomator/buildomator★ 101same name

    49 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use end, create and 6 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

    • jholhewresSkill

      backup

      Backup and restore — files, databases, and system backups

      Also in 3 projects that use this

    • kubesharkSkill

      install

      Kubeshark installation and deployment skill. Use this skill whenever the user wants to install Kubeshark, deploy Kubeshark to a Kubernetes cluster, set up Kubeshark, configure Kubeshark helm values, generate a Kubeshark config file, customize Kubeshark deployment, troubleshoot Kubeshark installation, upgrade Kubeshark, uninstall Kubeshark, or manage the Kubeshark Helm release. Also trigger when the user mentions "kubeshark tap", "kubeshark clean", "helm install kubeshark", "get kubeshark running", "set up traffic capture", "deploy kubeshark", "kubeshark not starting", "kubeshark pods not ready", "configure namespaces", "persistent storage", "cloud storage for snapshots", "kubeshark ingress", "kubeshark auth", "kubeshark SAML", "kubeshark license", "kubeshark config", "custom helm values", "kubeshark on EKS/GKE/AKS", "kubeshark on OpenShift", "kubeshark on KinD/minikube/k3s", "air-gapped", "offline install", or any request related to getting Kubeshark installed, configured, and running in a Kubernetes cluster.

      Also in 3 projects that use this

    • +1 more from microsoft
  • In this repository41 other files it gives its agents.

Does it work?

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

Reviews can't be read right now.

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.