Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

observe-trace

Estrelas0

Forks0

Atualizado24 de maio de 2026 às 20:11

Trace agent execution by collecting spans and building a trace tree for a task

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

sparkling

sparkling/ruflo

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	observe-trace
description	Trace agent execution by collecting spans and building a trace tree for a task
argument-hint	<task-id>
allowed-tools	mcp__ruflo__memory_search mcp__ruflo__memory_list mcp__ruflo__agentdb_semantic-route mcp__ruflo__agentdb_context-synthesize mcp__ruflo__agentdb_pattern-search Bash

Observe Trace

Collect distributed trace spans for a task and build a visual trace tree showing the execution flow, timing, and bottlenecks.

When to use

When you need to understand how a task was executed across agents -- which spans ran, how long each took, where bottlenecks occurred, and how agents coordinated.

Note (ADR-0238 S3): Spans collected via memory_search --namespace observability are application-emitted records (this skill's domain). The AgentDB-substrate telemetry-introspection MCP tools that previously returned in-process spans were removed (the bound class has no getSpans method); use the working stat tools (agentdb_resource_usage, agentdb_circuit_status, agentdb_rate_limit_status, agentdb_query_stats) for live substrate health, and continue using memory_search for application traces.

Steps

Collect spans -- call mcp__ruflo__memory_search --namespace observability (or memory_list) to retrieve all spans matching the <task-id>. The memory_* tool family routes by namespace; agentdb_hierarchical-* does NOT (it routes by tier working|episodic|semantic), so use memory_* here. See ruflo-agentdb ADR-0001 §"Namespace convention".
Build trace tree -- organize spans into a parent-child hierarchy using parentSpanId references, with the root span at the top
Calculate timing -- for each span, compute duration (endTime - startTime), and identify the critical path (longest chain of sequential spans)
Identify bottlenecks -- flag spans where duration exceeds the p95 for that operation type, or where gaps between spans suggest idle time
Synthesize -- call mcp__ruflo__agentdb_context-synthesize to combine span metadata into a narrative summary of the execution flow
Report -- display the trace tree with: span name, agent, duration, status (OK/ERROR), and bottleneck flag; include total trace duration and critical path duration

CLI alternative

npx @sparkleideas/cli@latest memory search --query "trace spans for task TASK_ID" --namespace observability

Mais deste repositório

mesmo repositório

adr-index

sparkling/ruflo

Build or rebuild the ADR index + dependency graph in AgentDB by running the in-process `agentdb index` command (one cold-start, all surfaces in one pass — no per-record npx round-trips). Handles v3-style and plugin-style ADR formats.

2026-06-100

adr-create

sparkling/ruflo

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

2026-06-070

hive-mind-advanced

sparkling/ruflo

Hive Mind orchestration patterns — queen-led multi-agent coordination with Byzantine/Raft/Gossip/CRDT consensus, typed collective memory, dialectic council, and session checkpoint/resume. Use for decision-bearing work; use swarm-advanced for parallel execution without consensus.

2026-06-060

diff-analyze

sparkling/ruflo

Analyze git diffs for risk scoring, reviewer recommendations, and change classification

2026-06-040

test-gaps

sparkling/ruflo

Detect missing test coverage and generate test suggestions

Observe Trace

Collect distributed trace spans for a task and build a visual trace tree showing the execution flow, timing, and bottlenecks.

When to use

When you need to understand how a task was executed across agents -- which spans ran, how long each took, where bottlenecks occurred, and how agents coordinated.

Note (ADR-0238 S3): Spans collected via memory_search --namespace observability are application-emitted records (this skill's domain). The AgentDB-substrate telemetry-introspection MCP tools that previously returned in-process spans were removed (the bound class has no getSpans method); use the working stat tools (agentdb_resource_usage, agentdb_circuit_status, agentdb_rate_limit_status, agentdb_query_stats) for live substrate health, and continue using memory_search for application traces.

Steps

Collect spans -- call mcp__ruflo__memory_search --namespace observability (or memory_list) to retrieve all spans matching the <task-id>. The memory_* tool family routes by namespace; agentdb_hierarchical-* does NOT (it routes by tier working|episodic|semantic), so use memory_* here. See ruflo-agentdb ADR-0001 §"Namespace convention".

Build trace tree -- organize spans into a parent-child hierarchy using parentSpanId references, with the root span at the top

Calculate timing -- for each span, compute duration (endTime - startTime), and identify the critical path (longest chain of sequential spans)

Identify bottlenecks -- flag spans where duration exceeds the p95 for that operation type, or where gaps between spans suggest idle time

Synthesize -- call mcp__ruflo__agentdb_context-synthesize to combine span metadata into a narrative summary of the execution flow

Report -- display the trace tree with: span name, agent, duration, status (OK/ERROR), and bottleneck flag; include total trace duration and critical path duration

CLI alternative

npx @sparkleideas/cli@latest memory search --query "trace spans for task TASK_ID" --namespace observability