agentleFS
paslavskyipaslavskyi/llm-wiki/.claude/skills/kb-dashboard/SKILL.md

kb-dashboard

Skill1 starsChanged 32 days agoMITView on GitHub

Use to start (or point the user to) the live PM dashboard of this knowledge base — "де ми зараз", активні цілі, backlog, відкриті ризики/питання, пульс KB. Runs a local read-only server; data is always current (computed from knowledge/ frontmatter + git at request time).

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Start the server (if not already running):

    line 12
  2. Distinctive:

    Do not add write endpoints.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

kb-dashboard — live PM dashboard

Goal: give the human a visual, always-fresh view of project state without any regeneration step. Architecture: hand-written SPA + read-only REST API.

Steps

  1. Start the server (if not already running):
    • npm run dashboard (foreground; Ctrl+C to stop), or run it in the background if the session needs to continue working.
    • Port: 4321 by default (KB_DASH_PORT env var to override). Binds 127.0.0.1.
  2. Tell the user to open http://localhost:4321 (Windows: start http://localhost:4321).
  3. Data refreshes on every browser reload (F5) or the «оновити» button — no regeneration command exists or is needed.

What it shows

  • Prompt-line header: branch, last commit, live note count, uncommitted knowledge/ changes.
  • «Де ми зараз» — Current focus + Phase from STATE.md.
  • Stat tiles: живі нотатки, активні цілі (accepted MIL-*), backlog, відкриті RISK-/Q-.
  • Milestones (фільтр: активні/заплановані/всі), Backlog (tag backlog + proposed MIL-*).
  • Health: відкриті question/risk/assumption (same rule as index/health.md).
  • Charts: нотатки за доменами; пульс KB (created/updated by month).

Rules

  • The dashboard is a VIEWER. The API is GET-only and never writes to the KB; all knowledge writes still go exclusively through the write pipeline.
  • tools/dashboard/ is hand-maintained SOURCE code (not a generated artifact — it does not live in index/). Vendored libs live in tools/dashboard/public/vendor/.
  • Do not add write endpoints. Ever.

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.