agentleFS
Sign inStart free
revealui-studiorevealui-studio/revskills/skills/revealui-tracker/SKILL.md

revealui-tracker

Skill2 starsChanged 40 days agoMITView on GitHub

Fleet TRACKER auto-sync (GAP-318 + goal spine). Use when /tracker, /next, free surfaces, roadmap, goals, or after gap/lane/init membership edits. Owner never runs shell commands — agents and SessionStart call tracker.js sync. Do not invent parallel queues or paste CLI recipes for the owner.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Public-repo hygiene: never hardcode private clone paths or private repo names.

    line 22
  2. Very specific:

    Do not add this skill to .leakignore.

    line 24
  3. Distinctive:

    If something is deferred (daemon down, license FREE), report that in one line and keep going with the file TRACKER board — do not invent …

    line 30
  4. Distinctive:

    Do not invent parallel boards under harness homes.

    line 95
  5. Distinctive:

    Do not hand-edit TRACKER / dashboards / graph / snapshot.

    line 96
  6. Distinctive:

    Do not paste multi-line shell recipes into owner chat.

    line 97
  7. Distinctive:

    Do not put security gap names on public surfaces.

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Fleet TRACKER (/tracker) — owner-zero shell

Public-repo hygiene: never hardcode private clone paths or private repo names. Resolve planning checkout via $JV_REPO from session-state.sh only. Do not add this skill to .leakignore.

Owner experience (non-negotiable)

The owner talks in chat (“what’s next”, “roadmap”, “sync the board”).
Agents never tell the owner to run node scripts/… or systemd recipes.
If something is deferred (daemon down, license FREE), report that in one line and keep going with the file TRACKER board — do not invent workarounds that require owner shell steps.

/next is this board only. “What now?”, “what should we do now?”, and “what should we do next?” are the shared status line, not /next alone:

node "$JV_REPO/scripts/handoff-status.js"
node "$JV_REPO/scripts/tracker.js" sync

Lead with the handoff classes (done, owner-gated merge lines, agent-doable). Then print the free surfaces. Do not auto-claim. Do not start handoff work from this status line — continuing it is /pickup.

What agents run (silently)

. "$REVEALFLEET_ROOT/revskills/scripts/lib/session-state.sh"
node "$JV_REPO/scripts/tracker.js" sync

sync (default entry):

  1. Refresh derived TRACKER / graph / snapshot if missing
  2. Soft-project snapshot → daemon goals when the licensed daemon is up
    (also soft-activates unblocked open free gaps so propose-task works)
  3. Print free surfaces for claiming
  4. Where-are-we — goal % + nextActions + suggested gap (soft if offline)

Soft-project / goals overlay never fail the session
(TRACKER_SKIP_PROJECT=1, TRACKER_SKIP_GOALS_OVERLAY=1 to disable).

TriggerAgent duty
SessionStartAlready calls tracker-session-check → sync
After editing gap / lane / initiative YAMLRun sync before wrap-up
Owner asks free surfaces / roadmap / goals / /nextRun sync, answer from output
Owner asks “what now?” / “what should we do now?” / “what should we do next?”handoff-status.js, then sync. Do not auto-claim. Do not start /pickup work
Daemon/license deferredNote once; use TRACKER.md free surfaces

Commands (agents only — not owner paste)

CommandUse
sync / ensureDefault auto path (all four steps above)
statusRead-only free surfaces (no project)
nextFree-surface menu (--json, --owner-gates)
where / goalsGoal progress overlay only
query …Deterministic roadmap query (list, progress, events, where)
projectForce goal project (when diagnosing)
stateRegenerate docs/.generated/STATE.json
snapshot / graphMachine views

Slash: /tracker, /next (free surfaces only). Continue-from-handoff is /pickup, not /next.

Claim flow after sync

  1. Pick an open gap or active lane (not INIT id alone).
  2. Claim on the workboard.
  3. Worktree from origin/test in the product repo.

Do not

  • Do not invent parallel boards under harness homes.
  • Do not hand-edit TRACKER / dashboards / graph / snapshot.
  • Do not paste multi-line shell recipes into owner chat.
  • Do not put security gap names on public surfaces.

Related

  • $JV_REPO/scripts/tracker.js
  • $JV_REPO/scripts/tracker-session-check.js
  • Sibling: revealui-checkpoint, revealui-pickup (/pickup consumes CURRENT-HANDOFF; /next stays this board)

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.

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.

Check your setup, free