测试与安全技能

Designs risk-based test strategy for software delivery. Use when defining coverage, setting CI gates, managing flaky tests, choosing test layers, or establishing release criteria.

中文简介正在准备中。当前显示原文说明。

Designs Android testing with Espresso, UI Automator, Robolectric, and Compose. Use when planning device matrices, emulator CI, Compose test migration, screenshots, or flakes.

中文简介正在准备中。当前显示原文说明。

Builds accessibility testing for WCAG 2.2 audits, CI gates, mobile audits, and EAA/ADA/VPAT evidence. Use when adding axe-core, Lighthouse, or screen-reader tests; not fixes.

中文简介正在准备中。当前显示原文说明。

Builds security testing pipelines for SAST, DAST, SCA, secrets, containers. Use when wiring scanners into CI or regression gates.

中文简介正在准备中。当前显示原文说明。

Designs and tests distributed-system resilience. Use when adding retries, deadlines, hedging, circuit breakers, overload protection, chaos experiments, or SLO reliability gates.

中文简介正在准备中。当前显示原文说明。

Refactors code while preserving behavior. Use when reducing technical debt, planning codemods, applying strangler migrations, or tightening CI guardrails around risky changes.

中文简介正在准备中。当前显示原文说明。

Tests apps as an ICP persona through browser automation and reports friction, fixes, and risks. Use when running persona-based, ICP, or synthetic-user testing.

中文简介正在准备中。当前显示原文说明。

Implements OpenTelemetry logs/metrics/traces, SLI/SLO gates, burn-rate alerts, and APM integrations. Use when adding or validating observability.

中文简介正在准备中。当前显示原文说明。

Tests API contracts for REST, GraphQL, gRPC, AsyncAPI, and webhooks. Use when adding schema validation or breaking-change gates (Pact, can-i-deploy, oasdiff, buf); not API design.

中文简介正在准备中。当前显示原文说明。

Builds QA harnesses and agent evals. Use when evaluating tool, trace, red-team, regression, multi-agent, or carried-workspace coding trajectories. Not for metric design (ai-evals).

中文简介正在准备中。当前显示原文说明。

Designs and troubleshoots NUKE-based CI/CD pipelines for .NET services. Use when refactoring target graphs, splitting test flows, publishing reports, or diagnosing slow pipelines.

中文简介正在准备中。当前显示原文说明。

Audits SaaS, cloud, payment, and AI spend. Use when analyzing bills, right-sizing plans, sizing Savings Plans or CUDs, cutting payment-processing fees, or LLM self-host breakeven.

中文简介正在准备中。当前显示原文说明。

Audits whether scores, benchmarks, LLM judges, or surveys measure what we think. Use when a benchmark is saturated, a score unreliable, or judge agreement untrustworthy.

中文简介正在准备中。当前显示原文说明。

Chooses under uncertainty: value of more data, cost-based thresholds, abstention, when to stop a test and ship, robust choice. Use when deciding, not estimating.

中文简介正在准备中。当前显示原文说明。

Tests whether changes caused a metric move without a clean A/B test: DiD, synthetic control, IV, RDD. Use when asking did a launch cause lift.

中文简介正在准备中。当前显示原文说明。

Audits and enforces documentation quality. Use when checking coverage, freshness, runbook validity, AI-instruction coverage, or cleaning stale/duplicate markdown after LLM edits.

中文简介正在准备中。当前显示原文说明。

Debugs crashes, regressions, flakes, and production bugs systematically. Use when diagnosing stack traces, logs, or profiling data; not perf tuning or incident command.

中文简介正在准备中。当前显示原文说明。

Guides dependency audits and upgrades. Use when auditing dependencies, upgrading vulnerable packages, managing lockfiles or package managers, SBOMs, or update and monorepo policy.

中文简介正在准备中。当前显示原文说明。

Creates and audits agent skills: SKILL.md, references, scripts, runtime metadata. Use when writing, validating, or security-reviewing a skill, or fixing truncated skill listings.

中文简介正在准备中。当前显示原文说明。

Configures Claude Code hooks and Codex hooks.json/notify. Use when adding PreToolUse guards, Stop hooks, managed hooks, format-on-save, preflight, audits, or worktree/budget hooks.

中文简介正在准备中。当前显示原文说明。

Designs LLM, agent, responsible-AI, and multimodal evals. Use when measuring quality, fairness, grounding, safety, or judge reliability. Not for test harnesses (qa-agent-testing).

中文简介正在准备中。当前显示原文说明。

Designs cross-session agent memory: point-in-time facts, consolidation, tenant isolation. Use when auditing user memory or Mem0/Zep. Not for repo context (dev-context-engineering).

中文简介正在准备中。当前显示原文说明。

Owns instruction files: AGENTS.md, CLAUDE.md, personal and repo rules. Use when writing, pruning, auditing them, sharing rules across Claude and Codex, or fixing ignored rules.

中文简介正在准备中。当前显示原文说明。

Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.

中文简介正在准备中。当前显示原文说明。