agentleFS
Sign inStart free
zedarvateszedarvates/botte-secrete/skills/demo/SKILL.md

demo

Skill2 starsChanged 3 months agoMITView on GitHub

Live ANSI dashboard of the belt's decisions — routing, token savings, micro-NN outputs, escalations, cache hits — either a built-in scripted scenario (no LLM, no network, works on a bare machine) or tailing a real project's event log. Use when the user wants to see/demo what the routing belt is doing, record a README GIF, or watch live decisions while an agent works.

26 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 spec, implement 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.
  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 4 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    All three funnel through build_panels(events) -> list[Panel] and render_grid(panels) -> str.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 24 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

demo — watch the belt decide, live

Four panels, refreshed as decisions happen: ROUTING, SAVINGS, MICRO-NN, ESCALATIONS. Reads from [[events]] — same data source as dashboard --watch and session replay.

python -m skills.demo.cli scripted                    # built-in scenario, ~4s total
python -m skills.demo.cli scripted --speed 0 --no-clear # dump all frames, no timing
python -m skills.demo.cli live .                       # tail a real project while an agent works
python -m skills.demo.cli replay .botte/events.jsonl --speed 0.3   # the "black box" — replay a real session

Three modes, same renderer

  • scripted — 6 fixed steps (scenario.py) covering every filter of the belt: micro-NN routing, a deterministic classifier, a cache hit, a cloud escalation, a verification-failure escalation, an anomaly-detector output. Deterministic, no dependency on a running LLM or .botte/events.jsonl — this is the mode for a README GIF or a cold-machine walkthrough.
  • live — tails a real project's .botte/events.jsonl (written by [[auto_router]], [[cache]], …) while an agent works. Genuine decisions, genuine numbers.
  • replay — the "black box": replays a captured event log at real or sped-up pace. Accepts a raw .botte/events.jsonl (JSONL, exactly what events/auto_router write) or a JSON array (e.g. from events tail --json) via load_events_file(), which auto-detects the shape. Useful for debugging a real routing session after the fact, demoing with real data without a live agent running, or as raw material for the active-learning loop.

All three funnel through build_panels(events) -> list[Panel] and render_grid(panels) -> str.

Design

  • Pure stdlib ANSI (render.py) — no rich/textual dependency, degrades to plain text when NO_COLOR is set or stdout isn't a TTY.
  • Panels trim to a fixed width so the layout never breaks on a long task description.
  • --no-clear disables the screen-clear escape codes — use it for piping frames into a file (recording) or in this test harness.

Related: [[events]] (the data source), [[dashboard]] (the report counterpart).

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.

Check your setup, free