agentleFS
Sign inStart free
anthonysuherlianthonysuherli/br8n/skills/activity/SKILL.md

activity

Skill1 starsChanged 3 months agoMITView on GitHub

Query your cross-repo ACTIVITY knowledge graph — what you've been working on across all repos (repos touched, branches, files, work sessions, and the tasks behind them). Use when the user asks "what was I working on", "what have I touched lately", "what's connected to <file/repo>", or wants a cross-repo rollup rather than a single repo+branch resume.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Follow edited/pursued/on_repo edges to connect a file or task back to the repos and sessions that touched it.

    line 35

≈ “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

br8n — Activity

The cross-repo lens. While /br8n:pickup replays one repo+branch, activity answers "what have I been doing, everywhere" — backed by a knowledge graph that accumulates automatically on every br8n_capture. Nothing to build; just query.

The graph's ontology: repo, branch, file, session, task nodes, related by on_repo, on_branch, in_repo, edited, viewed, pursued.

Step 1 — Query the graph

Call mcp__plugin_br8n_br8n__br8n_activity:

  • A natural-language query seeds a semantic subgraph ("what touches the store layer", "the KG work"). Omit it for the whole (capped) graph.
  • Optional repo narrows to one repository.

It returns {nodes, edges, summary} — summary is a ready-to-show natural-language rollup; nodes/edges are the graph slice for anything more detailed.

Step 2 — Answer

Lead with the summary (repos, tasks, files in view). Then, if the user wants specifics, read the nodes/edges:

  • Tasks (type: task) — the intents pursued, distilled from hypotheses.
  • Sessions (type: session) — individual captures; properties carry captured_at, repo, branch, hypothesis.
  • Files (type: file) — what was edited vs. viewed (the edge relation).
  • Follow edited/pursued/on_repo edges to connect a file or task back to the repos and sessions that touched it.

When to reach elsewhere

  • Single repo+branch "where was I" → /br8n:pickup (richer card for the here-and-now).
  • A question needing external knowledge → /br8n:search (grounds + fills the gap).

The activity graph is read-only here — it grows on its own as captures happen.

Download now (ZIP)

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. egregore-labs/egregore★ 293same name
    2. spmtitsolution/OpenBA-Kit★ 38same name
    3. gr219/OpenBA-Kit★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

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