Loading...
Loading...
Found 235 Skills
OpenHarmony Distributed Soft Bus Code Security Review Expert - Comprehensive inspection of C/C++ code against secure coding standards and logging specifications. Covers over 40 security rules, including key areas such as pointer safety, memory management, lock management, and sensitive information protection. Provides cross-file call analysis and control flow analysis, generating detailed code review reports. Only triggered when user input contains "软总线安全卫士" (Soft Bus Security Guard). ⚠️ Important: This skill is a read-only review tool and does not modify source files.
Compares current live GTM container against last known state from gtm-implementation-log.json. Shows what tags, triggers, and variables have been added, deleted, or modified since the last skill run. Read-only, no changes made. Prevents accidentally overwriting manual GTM changes. Trigger on - "what changed in GTM", "gtm diff", "check for manual changes", "gtm drift", "what's different in my container", "has anything changed".
Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.
Investigates completed flash-loan and atomic DeFi incidents across EVM and Solana from public txs—borrow-execute-repay fingerprints, oracle/pool/governance vectors, full trace reconstruction, impact quantification, and mitigations. Use when the user asks for flash loan exploit analysis, atomic attack post-mortems, large-borrow suspicious tx triage, or evidence-structured case studies from explorer data and read-only simulation—not for designing new attacks on live protocols.
Quick health checks for a Dockerized VPS. Use to verify services are running, check container status, view logs, or get a system overview (disk, memory, CPU). Read-only by design — anything that would change state is routed through the clipboard for the user to paste.
Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.
Smoke test for alicloud-media-vod. Validate minimal authentication, API reachability, and one read-only query path.
Smoke test for alicloud-ai-search-milvus. Validate minimal authentication, API reachability, and one read-only query path.
Smoke test for alicloud-compute-swas-open. Validate minimal authentication, API reachability, and one read-only query path.
Query the public PANews API for the currently bundled read-only workflows, article search, listings, rankings, and daily must-reads.
GitHub 审视 - Read-only GitHub triage for issues and PRs. 触发条件/Triggers: 需要分析 GitHub Issues 或 PRs、生成审查报告、或分类问题。 核心原则/Core Principles: - 只读不写/Read-only: 永不修改 GitHub 状态 - 证据支持/Evidence: 每个结论都需要 GitHub permalink 证明 - 并行分析/Parallel: 每个 Issue/PR 独立后台任务 - 报告输出/Reports: 写入临时目录，不操作 GitHub 命令/Commands: - /审视 analyze <repo> - 分析仓库所有开放 Issue 和 PR - /审视 issues <repo> - 只分析 Issues - /审视 prs <repo> - 只分析 PRs - /审视 <URL> - 分析特定 Issue 或 PR - /analyze <repo> - English command 能力/Capabilities: GitHub 数据读取、问题分类、证据收集、报告生成、后台并行处理。
Run ClickHouse queries for analytics, metrics analysis, and event data exploration. Use when you need to query ClickHouse directly, analyze metrics, check event tracking data, or test query performance. Read-only by default.