j.dashboard-share
Skill0 starsChanged 22 days agoApache-2.0View on GitHub
Snapshot the project dashboard and upload it to a configured cloud storage remote in one step, by sequencing j-dashboard's snapshot script and E47_S05_T01's rclone upload script.
In this repository151 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- j.brainstormSkill
- j.breakSkill
- j.btwSkill
- j.check-inSkill
- j.clearifySkill
- j.close-storySkill
- j.cloud-connectSkill
- j.commitSkill
- j.connectSkill
- j.continueSkill
- j.conventionsSkill
- j.dashboardSkill
- j.deep-diveSkill
- j.distributeSkill
- j.docSkill
- j.doc-syncSkill
- j.doooSkill
- j.doSkill
- j.jenga-configSkill
- j.jenga-permission-levelSkill
- j.jengaSkill
- j.errorSkill
- j.evaluateSkill
- j.examplifySkill
- j.gitignoreSkill
- j.helpSkill
- j.ideaSkill
- j.improveSkill
- j.initSkill
- j.jbpSkill
- j.lgtmSkill
- j.pi-planSkill
- j.playbook-newSkill
- j.playbookSkill
- j.proceedSkill
- j.publishSkill
- j.reconcile-originSkill
- j.reconcileSkill
- j.redoSkill
- j.skillifySkill
- j.smoke-testSkill
- j.spinoffSkill
- j.statusSkill
- j.testSkill
- j.todoSkill
- j.toolsSkill
- j.unchartedSkill
- j.wtfSkill
- skill-nameSkill
- j.brainstormSkill
- j.breakSkill
- j.btwSkill
- j.check-inSkill
- j.clearifySkill
- j.close-storySkill
- j.cloud-connectSkill
- j.commitSkill
- j.connectSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 59
If the user's request already names a specific remote (e.g.
- Distinctive: line 67
Exactly one remote configured: use it automatically, no prompt needed.
- Distinctive: line 68
More than one remote configured: ask the user which one to use, following CLAUDE.md's standard Interaction Pattern (numbered list of the …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Dashboard Share — Snapshot + Cloud Upload
Purpose
E47_S05 chains two already-implemented, independently-scoped capabilities into one step: capturing
a point-in-time dashboard snapshot and uploading it to a configured cloud storage remote. Both halves
already exist as standalone scripts — skills/j-dashboard/scripts/snapshot.sh (E47_S04_T02/T03,
capture + single-file bundle) and skills/j-dashboard-share/scripts/upload-snapshot.sh
(E47_S05_T01, templated-path rclone copyto upload). Per this repo's "Scripts Over Inline Logic"
principle (CLAUDE.md), this SKILL.md introduces no new capture or upload logic of its own — it
only sequences those two scripts and relays their output, plus the minimal remote-selection judgment
call described in step 2 below (interpreting rclone listremotes output and presenting a choice to
the user, not reimplementing any config/upload behavior).
This is upload only — this skill never runs rclone link or any other share-link-creating
command, matching the story's explicit, deliberate scope decision (see E47_S05's Purpose section in
PROJECT_SUMMARY.md): upload and link-creation are two distinct actions with a real permission
consequence, and creating a public link stays a separate, manual, deliberate step the user takes on
their own, never something this skill chains automatically.
Instructions
Capture the snapshot. Invoke:
bash skills/j-dashboard/scripts/snapshot.sh [--out <path>]Forward
--out <path>only if the user explicitly requested a specific local output path; otherwise let it default.snapshot.shinstalls dependencies and rebuilds the dashboard UI itself when that is necessary (dev checkout,dist/missing or stale), so no separate install-and-build step is needed here. Relay the script's own stdout/stderr as-is if it fails — do not reinterpret its error output. On success, read the local snapshot file's path from its documentedSnapshot dashboard written to: <path>line (the exact linesnapshot.shemits on completion) — do not guess or re-derive the path any other way. If this step fails (non-zero exit), stop here; do not proceed to step 2 or 3.- Determine which remote to upload to.
upload-snapshot.sh(step 3) requires an explicit--remote <name>naming an already-configured rclone remote — it does not pick one on its own. Resolve this before invoking it:- If the user's request already names a specific remote (e.g. "upload it to my gdrive remote"), use that name directly and skip straight to step 3.
- Otherwise, run
rclone listremotesto see what's currently configured (a plain read-only enumeration — not upload or config logic, so it stays within this repo's inline-judgment carve-out for interpreting output and presenting results to the user):- Zero remotes configured: tell the user to run
j.cloud-connectfirst to configure one, and stop here — do not invokeupload-snapshot.shat all in this case (it would only reproduce the same "not configured" message after the fact). - Exactly one remote configured: use it automatically, no prompt needed.
- More than one remote configured: ask the user which one to use, following CLAUDE.md's standard Interaction Pattern (numbered list of the configured remote names, "Other" as the final option).
- Zero remotes configured: tell the user to run
Upload the snapshot. Invoke:
bash skills/j-dashboard-share/scripts/upload-snapshot.sh --file <path-from-step-1> --remote <name-from-step-2>Relay its stdout/stderr to the user as-is, including the final printed destination path on success (
JengaAI/<repo-directory-name>/<datetime>-board-snapshot.htmlon the chosen remote) or its own actionable error message on failure (e.g. it independently re-checks the remote is configured and points atj.cloud-connectif not, in case that state changed between step 2's enumeration and this call). Do not reinterpret, summarize away, or suppress its output.
Out of Scope
- Any new dashboard capture, HTML bundling, or single-file export logic — that is entirely
skills/j-dashboard/scripts/snapshot.sh's scope (E47_S04). Do not duplicate or reimplement any part of it here. - Any new
rclone copytoinvocation, destination-path templating, or "remote not configured" detection logic — that is entirelyskills/j-dashboard-share/scripts/upload-snapshot.sh's scope (E47_S05_T01). ThisSKILL.mdonly decides which configured remote name to pass to it (step 2 above); it never re-derives the destination path or re-implements the configured-remote check. - Running
rclone linkor any other share-link-creating command, automatically or on request routed through this skill — that is a deliberate, permanent scope exclusion forE47_S05(see Purpose above), not a gap to close later. rcloneinstallation, backend configuration, or OAuth authentication — that is entirelyj.cloud-connect's scope (E60_S01). This skill only points the user at it when no remote is configured; it does not run any part of that flow itself.
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
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.

