一键在 Manus 中运行任何 Skill

inspect-live-graph

星标6

分支0

更新时间2026年7月23日 23:12

Dump a running StreamLib node's live processor graph — processors, ports, links, channel names, states, and metrics — as JSON, to use as ground truth before mutating or tapping it. Use when you need the current topology of a running app: to find a channel name for `tap-live-channel`, to learn the exact port names before a `connect`, to confirm a `submit`/`replace` landed, or to diff before/after a hot-swap. Wraps `streamlib graph`.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

tatolab

tatolab/streamlib

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

inspect-live-graph

The read-only ground-truth verb. Everything else keys off names that only the live graph knows — processor ids, port names, and channel data-service names ({source_processor}/{source_output_port}). Never guess these; dump the graph and read them.

Steps

1. Export the live graph

Target the node with the same flag you pinned in drive-running-node:

streamlib graph --node <runtime_id>
# or
streamlib graph --url <control_url>
# or, when exactly one node is live:
streamlib graph

The result is the graph MCP tool's JSON (pretty-printed): processors, links, states, metrics.

2. Read what you need out of it

Processor ids — the --processor-id for remove, and the from_processor / to_processor for connect.
Port names — the from_port / to_port for connect, and the local_port in a submit --connect spec.
Channel names — form the tap target {source_processor}/{source_output_port} from the source processor and its output port; feed it to tap-live-channel.
States / metrics — confirm a processor is running and moving data (non-zero counters) rather than merely instantiated.

3. Save it when it is evidence

To freeze the topology for a PR or a before/after diff, redirect to a file (graph has no --output flag — use shell redirection):

streamlib graph --node <runtime_id> > /tmp/graph-before.json

For a full evidence bundle (graph + tapped frames + logs), use capture-node-evidence.

Notes

Pure read: graph never mutates the node.
A non-zero exit is a resolver or transport error, not an empty graph — an empty pipeline still returns valid JSON with empty arrays. See drive-running-node for resolver error messages.

同仓库更多 Skills

同仓库

milestone-loop

tatolab/streamlib

Run one reconciler pass of the standing milestone-loop — the turn procedure each `/work-on-milestone` firing invokes. Use when a loop firing (or the owner directly) needs to move the focused milestone one bounded step toward "merged, or waiting on the owner or on blockers." Checks the kill switch, probes rig capability, launches the milestone-loop workflow, and surfaces anything needing the owner. To START the loop on a milestone rather than run a single pass, use work-on-milestone.

2026-07-256

work-on-milestone

tatolab/streamlib

Drive a whole milestone to done with the standing loop — resolve the milestone, set the goal, and register the recurring reconciler that runs passes until every issue is merged or parked. Use when the owner says "work on <milestone>", "start the loop on <milestone>", "close out <milestone>", or wants the loop running without hand-typing a /loop invocation. Also the place to stop or re-target a running milestone driver.

2026-07-256

work-on-ticket

tatolab/streamlib

Take one ticket end-to-end in the current session with the owner present — the interactive counterpart to the standing loop. Use when they say "work on issue N", "let's do this ticket", "pick up X and I'll answer questions as you go", or want to drive a single issue to a PR now. Same workflow, same composed stages, same verifier as the loop — but questions come inline instead of parking.

2026-07-256

loop-status

tatolab/streamlib

Render the milestone-loop's current picture into one status board — what it's acting on, what's waiting on the owner (oldest first), what it's watching, recent outcomes, and spend. Use when asked "what's the loop doing", "loop status", "what's waiting on me", or before deciding whether to nudge or pause the loop. Read-only — it reports, it never acts.

2026-07-256

draft-design

tatolab/streamlib

Architecture-first entry point — recon the current code with the relevant domain experts, then produce a design brief for the owner (mermaid diagram, trade-offs, decisions taken, and an explicit decisions-for-owner list) posted to the issue. Use before building anything engine-zone, when a feature needs a shape decided, or when the owner asks to "design X first" or "draft the approach for this issue". Nothing builds until they approve in a comment.

2026-07-246

author-and-submit-processor

tatolab/streamlib

Write a brand-new processor from source and submit it into a running StreamLib node as a fresh instance, optionally wiring its ports to existing processors in one transactional step, then confirm it landed and is producing. Use when adding a new stage to a live pipeline during development — a new filter, sink, or generator — without restarting the app. Wraps `streamlib submit` then `graph` + `tap` to confirm.

2026-07-236

name

inspect-live-graph

description

inspect-live-graph

Steps

1. Export the live graph

Target the node with the same flag you pinned in drive-running-node:

streamlib graph --node <runtime_id>
# or
streamlib graph --url <control_url>
# or, when exactly one node is live:
streamlib graph

The result is the graph MCP tool's JSON (pretty-printed): processors, links, states, metrics.

2. Read what you need out of it

Processor ids — the --processor-id for remove, and the from_processor / to_processor for connect.
Port names — the from_port / to_port for connect, and the local_port in a submit --connect spec.
Channel names — form the tap target {source_processor}/{source_output_port} from the source processor and its output port; feed it to tap-live-channel.
States / metrics — confirm a processor is running and moving data (non-zero counters) rather than merely instantiated.

3. Save it when it is evidence

To freeze the topology for a PR or a before/after diff, redirect to a file (graph has no --output flag — use shell redirection):

streamlib graph --node <runtime_id> > /tmp/graph-before.json

For a full evidence bundle (graph + tapped frames + logs), use capture-node-evidence.

Notes

Pure read: graph never mutates the node.
A non-zero exit is a resolver or transport error, not an empty graph — an empty pipeline still returns valid JSON with empty arrays. See drive-running-node for resolver error messages.