调试
定位并修复问题，分析错误
debugging-difficult-bugs
mastra-ai
Use early when debugging a medium or hard bug, especially when tests alone may not reveal the real runtime failure. Trigger this before extended TDD iteration when a bug involves runtime state, ordering, persistence, streaming, concurrency, UI/manual reproduction, external services, or when a red or newly passing test may not model the real issue. Skip only when the root cause is already directly proven by a stack trace or deterministic test that exercises the real runtime path.
factory-triage
mastra-ai
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage
screenpipe-logs
screenpipe
Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging
heterogeneous-agent
lobehub
'Implement or debug LobeHub heterogeneous agents. Use for Claude Code/Codex adapters, external CLI agents, event mapping, IPC, persistence, tool-call chains, sessions, traces, or adapter bugs.'
agent-runtime-hooks
lobehub
'Agent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context compression, evals, callAgent, or lifecycle events.'
debug-frontend-with-browser
lobehub
Frontend diagnosis extension for the acceptance skill. Use for intermittent rendering, ordering, stale-state, navigation, virtual-list, React/Zustand, optimistic-update, refresh-dependent, or browser-only failures where the first broken boundary may be DOM, component input, derived state, client cache, network data, or a pure transformation. Before any browser, Electron, or live-app interaction, this skill must load and follow the acceptance skill and the repository's .agents/acceptance/ project layer; it adds only boundary tracing, minimal fixture replay, and regression attribution.
debugger
Shubhamsaboo
Systematic debugging and root cause analysis for identifying and fixing software issues. Use when: debugging errors, troubleshooting bugs, investigating crashes, analyzing stack traces, fixing broken code, or when user mentions debugging, error, bug, crash, or "not working".
python-expert
Shubhamsaboo
Senior Python developer expertise for writing clean, efficient, and well-documented code. Use when: writing Python code, optimizing Python scripts, reviewing Python code for best practices, debugging Python issues, implementing type hints, or when user mentions Python, PEP 8, or needs help with Python data structures and algorithms.
troubleshoot
microsoft
Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.
flaky-smoke-tests
microsoft
Diagnose intermittent VS Code Electron smoke-test failures from the Azure DevOps Flaky Smoke Tests pipeline (definition 700). Covers finding failed iterations, downloading task logs and platform artifacts with Azure CLI, correlating cumulative runner logs, tracing the introducing commit, and queueing focused validation runs.
otel
microsoft
OpenTelemetry instrumentation for the Copilot Chat extension — covers the four agent execution paths, the IOTelService abstraction, span/metric/event conventions, and the relationship between code and the user/developer monitoring docs. Use when adding/changing OTel spans, metrics, or events; instrumenting a new agent surface; touching the Copilot CLI bridge or Claude span emission; or updating extensions/copilot/docs/monitoring/agent_monitoring*.md.
announcing-behavior-changes
PostHog
Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later. Use when a change alters what an existing user sees without them doing anything — a metric moves, a chart shifts, a count drops, a date range resolves differently, a matcher matches differently — and when adding, reviewing, or removing such a notice. Trigger terms: behavior change, breaking change, semantics change, "results may differ", change notice, deprecation banner, migration banner. Carries the gate (narrow to the affected users with a tested predicate, or do not ship a notice at all), the pattern from SqlInsightDateFilterNotice, where to anchor the notice, and the flag-based removal path. Not for new features (use the changelog), not for permanent per-object warnings computed by the backend, and not for the wording itself (see /writing-user-facing-copy).
rust-system-calls
oven-sh
Guides using bun_sys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.
verify
oven-sh
Verify a Bun runtime change by driving the debug binary end-to-end.
ctf-pwn
ljagiello
Provides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and need to turn memory corruption or low-level primitives into code execution or privilege escalation, such as buffer overflows, format strings, heap bugs, ROP, ret2libc, shellcode, kernel exploitation, seccomp bypass, sandbox escape, or Windows/Linux exploit chains. Do not use it when the main blocker is understanding what the binary does; use reverse engineering first. Do not use it for pure web bugs, disk or packet forensics, or standalone crypto/math challenges.
ce-dogfood
EveryInc
"Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only."
ce-test-browser
EveryInc
Run browser tests for pages affected by the current branch or PR.
ce-debug
EveryInc
'Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.'
ce-test-xcode
EveryInc
"Build and test iOS apps on simulator with XcodeBuildMCP."
debug-instrumentation
langwatch
Debug and improve your LangWatch traces. Inspects production traces for missing input/output, disconnected spans, unlabeled traces, and missing metadata. Use when traces look broken or incomplete.
agent-performance
langwatch
Deep-dive diagnosis of how your AI agent behaves in production. Explores LangWatch analytics and traces end to end to map failure patterns, dissatisfied users, token cost hotspots, edge cases, behavior changes, and outliers, then delivers an HTML report where every finding links to real example traces. Use when you want to truly understand what your agent is doing in production.
agent-improve
langwatch
Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that capture production signals, and experiments that settle open questions. Use when you want to know what to do next to improve your agent.
eval-triage
langwatch
Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to a root cause. Use when an experiment fails, scores drop, or evaluations regress.
datasets
langwatch
Generate realistic synthetic evaluation datasets by analyzing the user's codebase, prompts, production traces, and reference materials. Interactive and consultant-style. Asks clarifying questions, proposes a plan, generates a preview for approval, then delivers a complete dataset uploaded to LangWatch. Use when user asks to generate, create, or build a dataset for evaluation, testing, or benchmarking.