监控

monitor-stakeholders

christopheryeo

Scans Gmail for recent emails from tracked stakeholders and presents an executive digest grouped by stakeholder category. Reads each AI workforce member's own Knowledge/Stakeholder_Monitoring.md file to discover who to monitor, then searches Gmail for all matching email addresses. Use this skill whenever the user says "monitor stakeholders", "check stakeholder emails", "stakeholder digest", "stakeholder update", "any emails from stakeholders", or any similar request to review communications from tracked contacts. Also trigger when the user asks about emails from a specific stakeholder group (e.g., "any emails from NKF?", "what did Cap Vista send?") if a stakeholder list exists.

eve-job-debugging

Incept5

Monitor and debug Eve jobs with CLI follow, logs, wait, and diagnose commands. Use when work is stuck, failing, or you need fast status.

log-driven-debugging

bakrrrrr

"Guides systematic verification-based debugging for JavaScript/TypeScript (Node.js, Bun, browser). Use when: (1) User reports unexpected behavior, errors, or bugs, (2) Need to trace data flow or state changes without assuming root causes, (3) Issue requires identifying exactly where code deviates from expected behavior."

kubernetes

kprsnt2

Kubernetes deployment best practices including resource management, security, and observability.

eval-frameworks

cuba6112

Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.

Dual-Process Reasoning (System 1/2 + Metacognitive Control)

sovr610

This skill should be used when the user asks to "implement dual-process reasoning", "add System 1/2 router", "implement metacognitive control", "add confidence calibration", "implement temperature scaling", "add iterative refinement", "implement convergence detection", "add effort budget", "implement reasoning trace", "add novelty scoring", "implement routing policy", "add System 2 early stopping", "implement calibrated confidence", "add isotonic calibration", "implement GRU reasoning loop", "add selective S2 execution", "implement halt criteria", "add reasoning budget enforcement", "implement route score computation", or mentions dual-process reasoning, System 1/2 routing, metacognitive control, confidence calibration, convergence criteria, or reasoning traces in the cognitive pipeline.

monitor-openapi

janwilmake

Monitor API integration of Parallel. Use when building applications with Parallel Monitor API.

reload

gyumaruya

Restart the current Claude Code session from within tmux. Writes a handoff file, launches a restart script in a new tmux window, which stops the current Claude and resumes with --resume. Triggers: /reload, "reload", "restart", "reboot", "再起動"

laminar-quickstart-trace

lmnr-ai

"Create a minimal Laminar trace demo in minutes with no external LLM calls. Use when a user asks for a Laminar example, a quickstart demo, or wants to see traces appear in the Laminar UI quickly (cloud or self-hosted)."

Neuromodulation + Eligibility Traces (Three-Factor Learning)

sovr610

This skill should be used when the user asks to "implement eligibility traces", "add three-factor learning", "implement neuromodulation", "add DA/ACh/NE/5-HT modulators", "implement STDP eligibility", "add synaptic plasticity", "implement online plasticity", "add reward-modulated learning", "implement trace dynamics", "add Dutch traces", "implement accumulating traces", "add replacing traces", "implement neuromodulatory gate", "add plasticity gain", "implement delayed reward association", "add eligibility decay", "implement spike-based traces", "add rate-based traces", "implement three-factor weight update", "add fast memory adapter", "implement bioplausible learning", or mentions eligibility traces, three-factor learning rules, neuromodulatory signals, STDP-based eligibility, reward-modulated plasticity, DA/ACh/NE/5-HT computation, or online synaptic updates in the cognitive pipeline.

SKILL.md - Neko Futures Trader

lukmanc405

```

debug-stacktrace

ShotaIuchi

Stack trace and error message analysis. Apply when investigating exceptions, error chains, failure propagation paths, and crash logs to pinpoint failure locations.

stock-monitor-cn

yangshourong

"全功能中国 A 股监控系统，由戎哥使用 OpenCode 开发。支持 7 大预警规则、100 分复合评分、守护进程调度。专注 A 股特色技术指标（红涨绿跌、乖离率、三周期 RSI）。"

bg-remover

yemyat

Remove backgrounds from images using FAL.ai's BiRefNet model. Use when users ask to remove background, make transparent PNG, extract subject from image, or create cutouts. Trigger phrases include "remove background", "transparent background", "cut out", "extract subject", or any background removal request.

macbook-desktop-mode

terrylica

Configure a MacBook as an always-on-AC desktop workstation with USB device resilience, battery longevity, and self-healing audio device.

benchmark

hoangsonww

Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band.

systematic-debugging

hrdtbs

A rigorous debugging protocol to find root causes before attempting fixes. Use this when encountering bugs, test failures, or unexpected behavior to avoid "thrashing" and random guessing.

teams

khaki4

문제를 분석하여 Agent Teams를 자동 구성하고, 4가지 조율 패턴(distribute/monitor/discourse/sequence) 중 최적 패턴으로 협업한다. "/teams {문제 설명}"으로 호출한다.

running-chaos-tests

micsapp

Execute chaos engineering experiments to test system resilience. Use when performing specialized testing. Trigger with phrases like "run chaos tests", "test resilience", or "inject failures".

ckvd-research

terrylica

Research CKVD codebase for implementation details, patterns, or architecture questions. TRIGGERS - how does FCP work, understand data flow, find code, explore codebase, architecture questions.

AI Notes — Consolidate

ianphil

log-skill

maxoreric

记录执行过程的 Skill。当需要保存执行记录、工作日志时触发。触发词：记录、log、日志、work log、保存记录。

campaign-planner

aiagentskills

Creates comprehensive influencer marketing campaign plans including objectives, strategy, influencer selection criteria, content requirements, timeline, budget allocation, and success metrics. Your campaign blueprint.

agent-behavior

bfmcneill

Use at the start of any coding session to establish activity tracking and working patterns. Defines how the agent should document its work and communicate progress.