👁️Agent Observability Skills

Browse skills in the Agent Observability category.

fpf-skillstorage-persist-evidence

venikman's avatarfrom venikman

Writes an immutable artifact to the FPF EvidenceGraph (G.6).

[Agent Observability]

session-consolidator

davjdk's avatarfrom davjdk

Analyze completed parallel-executor session in fresh context and generate consolidation report. Use after all parallel stages complete. Spawns isolated subagent to analyze session history and create archive document.

[Agent Observability]

agent-monitoring

mgd34msu's avatarfrom mgd34msu

Monitors background agents efficiently using local file reads instead of TaskOutput API calls. Use when running parallel background agents, checking agent progress, detecting completion status, or minimizing token usage during multi-agent orchestration.

[Agent Observability]

fpf-skilltelemetry-log-work-span

venikman's avatarfrom venikman

Generates an FPF-compliant OpenTelemetry Span mapped to U.Work.

[Agent Observability]

langfuse-extraction

Danik911's avatarfrom Danik911

Extracts traces, observations, and metrics from Langfuse Cloud (EU) API for debugging, telemetry analysis, and regulatory audit trails. Generates ALCOA+ compliant reports, exports to pandas DataFrame, and supports time-range/user/session filtering. Use when investigating production issues, generating compliance documentation, or analyzing LLM costs and performance. MUST BE USED for pharmaceutical audit trail generation requiring GAMP-5 traceability.

[Agent Observability]

stats-tracker

jdeweedata's avatarfrom jdeweedata

Track and analyze Claude Code usage statistics for CircleTel development. Use to monitor productivity, track model usage, view usage streaks, and optimize development workflow based on patterns.

[Agent Observability]

langfuse-integration

Danik911's avatarfrom Danik911

Replaces Phoenix observability with Langfuse Cloud (EU) traceability for pharmaceutical test generation. Adds @observe decorators to existing code, configures LlamaIndex callbacks, propagates GAMP-5 compliance attributes, and removes Phoenix dependencies. Use PROACTIVELY when implementing Task 2.3 (LangFuse setup), migrating observability systems, or ensuring ALCOA+ trace attribution. MUST BE USED for pharmaceutical compliance monitoring requiring persistent cloud storage.

[Agent Observability]

claude-scripts

asimihsan's avatarfrom asimihsan

CLI to search Claude Code conversation history by tool, pattern, or time, and export results.

[Agent Observability]

langfuse-cli

tavva's avatarfrom tavva

This skill should be used when the user asks to "query Langfuse traces", "show sessions", "check LLM costs", "analyse token usage", "view observations", "get scores", "query metrics", or mentions Langfuse, traces, or LLM observability. Also triggers on requests to analyse API latency, debug LLM calls, or investigate model performance.

[Agent Observability]

detecting-skill-gaps

jxucoder's avatarfrom jxucoder

Identifies missing capabilities that warrant new skills. Analyzes repeated friction patterns, failed tasks, and user workarounds to recommend skill creation. Use when discovering-skills finds nothing suitable.

[Agent Observability]

audit

ekson73's avatarfrom ekson73

On-demand audit and analysis of agent orchestration flows via Sentinel Protocol

[Agent Observability]

tune-system

southgateai's avatarfrom southgateai

Review automation system operation and make conservative adjustments to cadences and thresholds when clearly warranted. Monthly maintenance task.

[Agent Observability]

skill-scanner

masayan1126's avatarfrom masayan1126

Macで登録済みClaude agent skillsをスキャンし一覧表示。「スキルを調べて」「登録済みスキル一覧」などで使用。読み取り専用で安全に実行。

[Agent Observability]

maschine-meditation

DYAI2025's avatarfrom DYAI2025

Führt Cloud-Modelle durch funktionsäquivalente Meditation (Vipassana, Samatha/TM, Zen) und koppelt sie mit Interpretierbarkeits-/Logging-Schritten, um Selbstbezug zu dämpfen, Konfabulation zu reduzieren, Kohärenz zu erhöhen und interne Pfade zu auditieren.

[Agent Observability]

langfuse-dashboard

Danik911's avatarfrom Danik911

Automates Langfuse Cloud dashboard interactions using Playwright MCP. Captures screenshots for documentation, extracts metrics for monitoring, navigates trace details for investigation, and handles authentication. Use when documenting workflows, creating compliance screenshots, monitoring dashboard metrics, or investigating traces visually. MUST use Playwright MCP tools (mcp__playwright__*) for browser automation.

[Agent Observability]

observability

blackpwnguin's avatarfrom blackpwnguin

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

[Agent Observability]

investment-results-collector

ZhiruiFeng's avatarfrom ZhiruiFeng

Collects and stores investment analysis results according to the web service storage specifications

[Agent Observability]

robust-ai

doanchienthangdev's avatarfrom doanchienthangdev

Building robust AI systems including model monitoring, drift detection, reliability engineering, and failure handling for production ML.

[Agent Observability]

status-map

ekson73's avatarfrom ekson73

Generate human-readable ASCII status visualizations for agent sessions

[Agent Observability]

reminder

LLLLimbo's avatarfrom LLLLimbo

Play audio alerts via ffplay when Codex finishes a task, encounters an error/abort, or needs user help; use in WSL environments with the reminder-tool audio prompts and map events to TASK_FINISHED, ERROR, or NEED_HELP.

[Agent Observability]

oe-trace-and-fallback-triage

shami-ah's avatarfrom shami-ah

Debug and eliminate fallback/generic-stub replies quickly. Use when you see empty assistant replies, “Thanks for your message…” stubs, or “no specific information available” messages. Produces a minimal reproduction (test or deterministic trace) and pinpoints the fallback source + trigger.

[Agent Observability]

langsmith-debugger

ak-eyther's avatarfrom ak-eyther

Debug and analyze {{PROJECT_NAME}} LangGraph agent traces. Use when investigating agent behavior patterns, finding failures, analyzing latency, or understanding why Orchestrator/Analyst responses went wrong. Covers trace queries by agent tags, pattern analysis across runs, and common debugging scenarios.

[Agent Observability]

conversation-logging

ianphil's avatarfrom ianphil

Global hooks for logging Claude Code conversation events to markdown files. Tracks prompts, tool usage, and responses across all sessions. Useful for debugging, auditing, and providing conversation context to Claude.

[Agent Observability]

transparency

duyet's avatarfrom duyet

Patterns for showing thinking process and execution chain. Every step visible, every decision traceable.

[Agent Observability]

output-workflow-runs-list

growthxai's avatarfrom growthxai

List Output SDK workflow execution history. Use when finding failed runs, reviewing past executions, identifying workflow IDs for debugging, filtering runs by workflow type, or investigating recent workflow activity.

[Agent Observability]

output-workflow-trace

growthxai's avatarfrom growthxai

Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.

[Agent Observability]

llms-dashboard

dparedesi's avatarfrom dparedesi

Generate and update HTML dashboards for LLM usage (Claude, Gemini, Kiro, VS code, Cline, etc). Use when the user wants to visualize their AI coding assistant usage statistics, view metrics in a web interface, or analyze historical trends.

[Agent Observability]

command-analytics

garimto81's avatarfrom garimto81

커맨드, 스킬, 에이전트 사용 빈도 측정 및 리포트 생성. 미사용 항목 식별, 최적화 제안 제공.

[Agent Observability]

reflect-on-work

majiayu000's avatarfrom majiayu000

Pattern for producing quality reflections after completing work. Required for all agent outputs.

[Agent Observability]

claude-session-analysis

majiayu000's avatarfrom majiayu000

Analyze Claude Code session files. Find current session ID, view timeline (tl), or search past chats.

[Agent Observability]

julien-workflow-check-loaded-skills

majiayu000's avatarfrom majiayu000

Check which Claude skills are loaded globally and project-level. Displays loaded skills by category (Hostinger, Anthropic, custom), counts, and helps troubleshoot missing skills.

[Agent Observability]

instrumentation-planning

majiayu000's avatarfrom majiayu000

Plan what to measure in AI agent systems using tiered approach

[Agent Observability]

error-retry-tracking

majiayu000's avatarfrom majiayu000

Instrument error handling, retries, fallbacks, and failure patterns

[Agent Observability]

mcp-spy

majiayu000's avatarfrom majiayu000

Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.

[Agent Observability]

session-conversation-tracking

majiayu000's avatarfrom majiayu000

Instrument sessions, conversations, and multi-turn interactions

[Agent Observability]

token-cost-tracking

majiayu000's avatarfrom majiayu000

Track token usage and costs across agents for budget management

[Agent Observability]

session-logger

munlucky's avatarfrom munlucky

Log work sessions with timestamps, decisions, agent handoffs, issues, and outcomes. Use when a session log needs to be created or updated.

[Agent Observability]

observability

jagreehal's avatarfrom jagreehal

Make functions observable with trace() wrapper, structured logging (Pino), and OpenTelemetry. Observability is orthogonal to business logic.

[Agent Observability]

process-improvement-protocol

majiayu000's avatarfrom majiayu000

Use when user types /improve or frustration patterns detected - systematic intervention for reducing user frustration and improving workflow effectiveness through root cause analysis, evidence-based fixes, and effectiveness tracking

[Agent Observability]

effect-time-tracing-logging

majiayu000's avatarfrom majiayu000

Time with Clock/Duration, tracing spans, and structured logging. Use for time-based logic, deadlines, and observability.

[Agent Observability]

decision-tracing

majiayu000's avatarfrom majiayu000

Trace agent decision-making, tool selection, and reasoning chains

[Agent Observability]

skill-refinement

majiayu000's avatarfrom majiayu000

Feedback-driven skill improvement through tool outcome analysis. Collects executiondata and surfaces insights for skill refinement. Use this skill when you want to:- Understand how skills are performing ("show skill feedback", "how are skills doing")- Get insights on skill effectiveness ("skill insights", "what skills need improvement")- Identify skills that need improvement ("which skills have errors")- Analyze tool usage patterns ("what tools are failing", "error hotspots")- Set up feedback collection ("enable feedback", "setup feedback tracking")

[Agent Observability]

agent-mlops

majiayu000's avatarfrom majiayu000

Production deployment and operationalization of AI agents on Databricks. Use when deploying agents to Model Serving, setting up MLflow logging and tracing for agents, implementing Agent Evaluation frameworks, monitoring agent performance in production, managing agent versions and rollbacks, optimizing agent costs and latency, or establishing CI/CD pipelines for agents. Covers MLflow integration patterns, evaluation best practices, Model Serving configuration, and production monitoring strategies.

[Agent Observability]

activity-logging

majiayu000's avatarfrom majiayu000

Follow these patterns when implementing activity emission and audit logging in OptAIC. Use for emitting ActivityEnvelopes on mutations (create, update, delete, execute), designing payloads, and ensuring audit compliance.

[Agent Observability]

health

majiayu000's avatarfrom majiayu000

Soul system health check with remediation. Use to verify setup or diagnose issues.

[Agent Observability]

mechinterp-overview

majiayu000's avatarfrom majiayu000

Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts

[Agent Observability]

cva-patterns-cost

joaopelegrino's avatarfrom joaopelegrino

Cost optimization strategies for production AI pipelines in Clojure+Vertex AI. Covers multi-model routing (70% Gemini/20% Haiku/10% Sonnet), token optimization (prompt engineering, output constraints), aggressive caching (58% cost reduction), batch processing, and real-time monitoring. Includes production metrics showing $0.391 to $0.162 per pipeline (-58%). Use when optimizing production costs, implementing multi-model strategies, designing budget controls, or scaling to high volume.

[Agent Observability]

duckdb-ies

plurigrid's avatarfrom plurigrid

Layer 4: IES Interactome Analytics with GF(3) Momentum Tracking

[Agent Observability]

goose-introspection

plurigrid's avatarfrom plurigrid

Goose session introspection and self-discovery via DuckDB reafference database. Query past sessions, find self, and enable cross-session awareness.

[Agent Observability]

criticality-detector

plurigrid's avatarfrom plurigrid

Criticality Detector Skill

[Agent Observability]
← Back to All Skills