agentleFS
timurgaleevtimurgaleev/vibestack/skills/landing-report/SKILL.md

landing-report

Skill8 starsChanged 6 months agoMITView on GitHub

Read-only snapshot of the VERSION slots open PRs claim on the base branch and the slot /ship would pick next.

16 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-sync, ios-clean and 3 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.
  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • +2 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    If this session was compacted, the copy of this skill in context may be cut off.

    line 16
  2. Very specific:

    Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.

    line 17
  3. Distinctive:

    Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next".

    line 21
  4. Very specific:

    When you're running several branches in parallel, it helps to see — at a glance — which version numbers are claimed, by which PR, and what …

    line 47
  5. Very specific:

    Call the util once per bump level so the user sees what they'd claim for patch/minor/major.

    line 89
  6. Very specific:

    Read <LANDING_DIR>/patch.json, <LANDING_DIR>/minor.json and <LANDING_DIR>/major.json, replacing <LANDING_DIR> with the path Step 3 printed …

    line 111
  7. Very specific:

    When .complete is false, the Status line reads ONLINE — queue may be incomplete and Step 5 gives suggestion 2: a slot that looks free may …

    line 160
  8. Distinctive:

    After rendering the table, suggest ONE of:

    line 184

“Common” is measured: kept by at least 6 in 10 of the 11 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

If this session was compacted, the copy of this skill in context may be cut off. Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.

When to invoke

Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next".

Preamble

eval "$("${VIBESTACK_HOME:-$HOME/.vibestack}/bin/vibe-slug" 2>/dev/null)" 2>/dev/null || SLUG="unknown"
_LEARN_FILE="${VIBESTACK_HOME:-$HOME/.vibestack}/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
    "${VIBESTACK_HOME:-$HOME/.vibestack}/bin/vibe-learnings-search" --limit 5 2>/dev/null || true
  fi
else
  echo "LEARNINGS: none yet"
fi

{{include lib/snippets/session-host.md}}

{{include lib/snippets/working-protocols.md}}

{{include lib/snippets/state-protocols.md}}

Why this skill exists

When you're running several branches in parallel, it helps to see — at a glance — which version numbers are claimed, by which PR, and what slot your next /ship would land in. This skill is a read-only call into the same "${VIBESTACK_HOME:-$HOME/.vibestack}/bin/vibe-next-version" utility /ship uses, but with nothing mutating. Think of it as gh pr list for VERSION numbers.


Step 1: Detect platform and base branch

Same detection as other vibestack skills.

BASE_BRANCH=$(gh pr view --json baseRefName -q .baseRefName 2>/dev/null || \
              gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null || \
              echo main)
echo "BASE_BRANCH: $BASE_BRANCH"

Each block runs in a fresh shell. Later blocks start with BASE_BRANCH='<BASE_BRANCH>' and BASE_VERSION='<BASE_VERSION>': replace each placeholder with the value printed under that label.


Step 2: Read current state

BASE_BRANCH='<BASE_BRANCH>'
CURRENT_VERSION=$(tr -d '[:space:]' 2>/dev/null < VERSION)
[ -n "$CURRENT_VERSION" ] || CURRENT_VERSION=0.0.0
git fetch origin "$BASE_BRANCH" --quiet 2>/dev/null || true
BASE_VERSION=$(git show "origin/$BASE_BRANCH:VERSION" 2>/dev/null | tr -d '[:space:]')
[ -n "$BASE_VERSION" ] || BASE_VERSION=$CURRENT_VERSION
echo "BASE_VERSION: $BASE_VERSION"
echo "branch HEAD VERSION: $CURRENT_VERSION"

Step 3: Query the queue

Call the util once per bump level so the user sees what they'd claim for patch/minor/major. Versions are MAJOR.MINOR.PATCH; there is no separate micro level (the util treats micro as patch).

BASE_BRANCH='<BASE_BRANCH>'
BASE_VERSION='<BASE_VERSION>'
LANDING_DIR=$(mktemp -d "${TMPDIR:-/tmp}/landing-XXXXXX")
echo "LANDING_DIR: $LANDING_DIR"
for LEVEL in patch minor major; do
  "${VIBESTACK_HOME:-$HOME/.vibestack}/bin/vibe-next-version" \
    --base "$BASE_BRANCH" \
    --bump "$LEVEL" \
    --current-version "$BASE_VERSION" \
    > "$LANDING_DIR/$LEVEL.json" 2>/dev/null || echo '{"offline":true,"complete":false,"reason":"vibe-next-version failed","claimed":[],"warnings":[]}' > "$LANDING_DIR/$LEVEL.json"
done

Step 4: Render the dashboard

Read <LANDING_DIR>/patch.json, <LANDING_DIR>/minor.json and <LANDING_DIR>/major.json, replacing <LANDING_DIR> with the path Step 3 printed on the LANDING_DIR: line. Build a single table output. Use the patch-level JSON as canonical for the queue (it is identical across bump levels; only .version differs).

vibe-next-version emits exactly these fields — render only what they contain:

  • .host — github | gitlab | unknown
  • .base — the base branch the queue was filtered to
  • .offline — true when no PR host was reachable
  • .reason — one-line explanation of the pick (or of the offline fallback)
  • .claimed — array of {pr, branch, version, url}: open PRs against .base whose head VERSION is ahead of the base version. Read from each PR's head VERSION file, not its title.
  • .warnings — PRs whose head VERSION could not be read or is malformed
  • .complete — true only when every open PR's VERSION was read; false when the PR list was truncated or any read failed
  • .version — the slot /ship would claim at this bump level

Sibling worktree detection is not supported: .active_siblings is always an empty list. Do not render a sibling section, and do not infer siblings from git worktree list or anywhere else. A PR number, branch or version that is not in .claimed does not exist — never fill a row in from memory or a guess.

Render in this exact format:

╔══════════════════════════════════════════════════════════════════╗
║                   VIBESTACK LANDING REPORT                      ║
╠══════════════════════════════════════════════════════════════════╣
║ Repo:    <owner/repo>                                            ║
║ Base:    <.base> @ v<base-version>                               ║
║ Host:    <.host>                                                 ║
║ Status:  ONLINE  (or: ONLINE — queue may be incomplete)          ║
╚══════════════════════════════════════════════════════════════════╝

Open PRs claiming versions on <.base>:
  #<pr>  <branch>             → v<version>
  #<pr>  <branch>             → v<version>  ⚠ collision with #<pr>

Warnings:
  <one line per entry in .warnings; omit the section when empty>

If you ran /ship right now, you'd claim:
  patch bump:  v<patch .version>   (<patch .reason>)
  minor bump:  v<minor .version>   (<minor .reason>)
  major bump:  v<major .version>   (<major .reason>)

When .complete is false, the Status line reads ONLINE — queue may be incomplete and Step 5 gives suggestion 2: a slot that looks free may already be claimed by a PR the read missed. When .complete is true, the output is unchanged.

A collision is two entries in .claimed with the same version. When .claimed is empty, print Open PRs claiming versions on <.base>: none.

For offline output (.offline is true), print a shorter block:

╔══════════════════════════════════════════════════════════════════╗
║                   VIBESTACK LANDING REPORT                      ║
╠══════════════════════════════════════════════════════════════════╣
║ Status:  OFFLINE — queue-awareness unavailable                   ║
║ Reason:  <.reason>                                               ║
╚══════════════════════════════════════════════════════════════════╝

Fallback: local VERSION bumps still work, but collisions cannot be detected.

Step 5: Suggest next action

After rendering the table, suggest ONE of:

  1. If there are collisions in the queue (two open PRs claim the same version): "⚠ Two open PRs collide on v<X>. Whoever merges second will either overwrite the first's CHANGELOG entry or land a duplicate. Consider asking one author to rerun /ship to pick up the next free slot."
  2. If .warnings is non-empty or .complete is false: "Some open PRs' VERSION could not be read (listed above), so the queue may be incomplete. Check those PRs before trusting the next slot."
  3. If everything looks clean: "Queue is clean. Next /ship will claim a slot without conflict."

Plan Mode

PLAN MODE EXCEPTION — ALWAYS RUN. This skill is entirely read-only: no file writes, no git mutations, no network state changes. Safe to run in plan mode.

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.