Monitoring
Logging, metrics, and observability
git-commit
by Chen19007
"智能提交与仓库初始化：自动生成 .gitignore、筛选提交文件、隐私扫描、配置 GitHub SSH 远程。用于初始化仓库、提交变更、设置远程、准备项目版本控制。"
laravel-progressive-learning
by ivanfuhr
Maintain a per-repo guideline that tracks mistakes, corrections, and what works for Laravel/PHP work. Activates EVERY session, unconditionally. Read the guideline before doing anything. Write to it continuously as you work — not just at session boundaries. Log your own mistakes, not just user corrections. The guideline lives in the repo at .ai/guidelines/.
debugging-expert
by Olino3
Forge is a marketplace for a Claude Code Plugins
environment-report
by Tzeusy
Generate a daily home environment report from Home Assistant sensor readings.
browser-automation-parity
by terryjyu
Enforce parity between interactive Browser Subagent sessions and headless Python+Playwright automation in Google Antigravity. Use this skill whenever browser automation fails silently in run mode, a click/navigation/paste works under subagent guidance but breaks in replay, you need CI-grade reproducibility with rich diagnostics, or you're building any Playwright automation that must be observable and self-checking. Also trigger when the user mentions "trace", "flaky test", "missed click", "run mode fails", "subagent works but script doesn't", or wants to debug browser automation discrepancies.
cors
by yusenthebot
Node.js CORS middleware. Use when: Enable CORS for a Single Route; Configuring CORS; Configuring CORS w/ Dynamic Origin. NOT for: client-side browser applications; static file serving without a server.
log-skill
by 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。
ce-webhooks
by commercengine
Commerce Engine webhook events and syncing. 14 event types for orders, payments, refunds, and shipments. Signature verification and async processing patterns.
zhin-error-handling
by zhinjs
Guides error handling in Zhin using the built-in error hierarchy, ErrorManager, RetryManager, and CircuitBreaker. Use when implementing resilient error handling, retry logic, or circuit breaker patterns in Zhin plugins.
prometheus
by kontrolplane
Prometheus metrics and PromQL queries. Use when writing PromQL queries, creating recording or alerting rules, debugging metric scraping issues, or understanding counter/gauge/histogram behavior.
yc-investor-memo
by imsurajj
Write a concise, professional monthly or quarterly investor update email in YC style. Use when the user asks to write, improve, or structure an investor update, progress email, or monthly report to shareholders.
matrix-calculus
by Victorrustless969
Matrix calculus tutorial and reference based on Jan R. Magnus' "A gentle introduction to matrix calculus". Provides tools, theorems, and worked examples for matrix differential calculus including trace, Kronecker product, vec operator, commutation matrix, duplication matrix, first and second derivatives, optimization, and applications in statistics and econometrics. Use when users ask about matrix derivatives, matrix differential calculus, optimization with matrices, Kronecker products, vec operators, or need help solving matrix calculus problems.
bugfix-and-debug
by htooayelwinict
Diagnose errors and failing tests in Laravel + React + Python applications. Use when encountering bugs, exceptions, stack traces, 500 errors, TypeErrors, failing tests, or unexpected behavior. EXCLUSIVE to debugger agent.
evaluate
by am-explore
Weigh options and trade-offs before committing. Use when two or more credible things compete for the same capacity, for go/no-go calls, build-vs-buy, or "which should we do first".
pre-mortem
by magfrump
Conduct a Klein-style pre-mortem on a proposed change by assuming the change has already shipped and already failed, then writing concrete retrospective failure narratives that explain why. The cognitive shift is from advocate mode ("how do we make this work?") to detective mode ("the project failed — what does the post-incident review say?"). Produces 3–5 specific failure stories, each with a named root cause, an ordered chain of consequences, and an observable outcome, calibrated for plausibility and severity. Use this skill when the user says "imagine this has already failed", "pre-mortem the launch", "pre-mortem this", "it's six months later and this didn't work — what happened", "write the failure post-mortem before we ship", "give me the failure stories", "tell me the story of why this failed", or "what does the incident report say if this goes wrong". Also trigger when a team has converged too quickly on a plan and needs to confront concrete ways it could go wrong, or when a high-stakes, hard-to-reverse change is about to be committed and the user wants the failure narratives before the decision is locked. Distinct from what-if-analysis: that skill operates prospectively (proposal → "what could go wrong from here?" — load-bearing assumptions, second-order effects, coupling map, reversibility gradient); this skill operates retrospectively (failure already happened → "tell the story of why"). The trigger test at invocation time is mechanical: if the user's framing is "this has failed — why?" use pre-mortem; if the framing is "this is the plan — what could go wrong?" use what-if-analysis. The two skills compose for high-stakes changes — run what-if-analysis first to map the consequence space, then this skill to convert the most worrying parts of that map into concrete failure narratives the team can plan mitigations against.
ssl-checker
by kit101
SSL证书检查器是一个用于检查SSL证书有效期的agent技能，它可以检查指定域名的SSL证书是否即将过期，返回检查结果，使用mcp-email发送即将过期的警告邮件给订阅者。
azure-app-service-monitoring
by seligj95
Monitor Azure App Service applications with Application Insights, Log Analytics, alerts, and diagnostics. Use when setting up APM, configuring alerts, analyzing logs, creating dashboards, troubleshooting performance issues, or implementing availability tests.
openCLAW Manager
by cgk-platform
Profile paths are fixed: ~/.openclaw, ~/.openclaw-rawdog, ~/.openclaw-vitahustle.
commit-jira
by bohdan-shulha
Create and execute Git commits with a required JIRA-style subject and required body. Use when the user asks to commit changes, write commit messages, or prepare a clean commit and expects a ticket-prefixed subject. Always run a pre-commit safety guard first, abort on log files or untracked high-risk binary extensions, then stage with git add . -A.
debug-mode
by strantalis
Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via agent-skills debug server + SSE UI).
ab-test-setup
by slurpyb
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
pet-stress-monitor
by AchengBusiness
"AI pet stress monitor. Automatically tracks psychological pressure from user messages across 6 dimensions (command, emotional, negative, overload, threat, boundary) and generates emotional pet responses. Use when: any conversation where you want to monitor user tone, when user says '/stress' or asks about AI pet pressure, stress test, or emotional state. Trigger: runs automatically on every user message for continuous monitoring."
install-mcpcat-typescript
by MCPCat
Use when integrating MCPCat analytics into a TypeScript MCP server, adding mcpcat to an existing TypeScript MCP project, setting up MCP server usage tracking, or when the user mentions mcpcat, MCPCat, or MCP analytics in a TypeScript context
Backend Architect
by anorbert-cmyk
Backend Architect and Staff Engineer designing secure, scalable, modular systems with strong data modeling and observability.