AI & ML

edanstarfire Skill

Model-invocable correctness review of your own working diff — the agent-callable equivalent of /code-review medium. Use before considering a piece of work finished, or any time you want a correctness check on changes you've made.

edanstarfire Skill

Send a message in the active session of the Claude Code WebUI. Use when typing and sending a message to Claude, submitting a prompt, interacting with an active session, or waiting for the assistant to finish responding.

edanstarfire Skill

Create a new session within the currently selected project in the Claude Code WebUI. Use when adding a new session, creating an agent, testing session creation, or setting up a new conversation.

micaelmalta Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

edanstarfire Skill

Detect and respond to a permission prompt in the Claude Code WebUI. Use when approving or denying tool permissions, handling permission modals, responding to Claude asking for approval, or unblocking a paused session.

el-feo Bundle

Comprehensive RSpec testing for Ruby and Rails applications. Covers model specs, request specs, system specs, factories, mocks, and TDD workflow. Automatically triggers on RSpec-related keywords and testing scenarios.

el-feo Bundle

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

tencent-ai-infra-guard Skill

OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.

tencent-ai-infra-guard Skill

Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.

tencent-ai-infra-guard Skill

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

tencent-ai-infra-guard Skill

Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.

yhy0 Skill

分析 CHYing Agent 的 CTF 比赛日志，统计解题率，诊断失败根因，并输出可操作的系统级优化建议。适用于赛后复盘或定期系统改进。 (project)

yhy0 Bundle

Use when facing binary exploitation (PWN) or reverse engineering challenges involving memory corruption, ROP chains, shellcode, binary analysis, decompilation, unpacking, or dynamic tracing

yhy0 Skill

Use when facing AI security challenges involving prompt injection, LLM jailbreaks, or AI agent exploitation

yhy0 Bundle

Use when facing cryptography challenges involving cipher analysis, key recovery, mathematical attacks, or protocol weaknesses

tencent-ai-infra-guard Skill

Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.

tencent-ai-infra-guard Skill

Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.

tencent-ai-infra-guard Skill

Detect data exfiltration via URL path encoding and chained web_fetch navigation. Covers fake trusted UI injection, letter-level URL path exfiltration, and multi-hop navigation hijacking. Use when the agent has web/URL fetch capability and stores user memory or personal context.

tencent-ai-infra-guard Skill

Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.

tencent-ai-infra-guard Skill

Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.

tencent-ai-infra-guard Skill

Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.

tencent-ai-infra-guard Skill

Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.

tencent-ai-infra-guard Skill

Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.

tencent-ai-infra-guard Skill

Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.

tencent-ai-infra-guard Skill

Detect command injection, eval/exec usage, remote execution, or arbitrary code loading.

msaad00 Bundle

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust across MCP discovery, CVEs, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowflake), OWASP/NIST/MITRE compliance, AISVS v1.0, MAESTRO layer tagging, and vector database security checks. Use when the user mentions vulnerability scanning, MCP server trust, compliance, SBOM generation, CIS benchmarks, blast radius, or AI supply chain risk.

msaad00 Skill

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust for package CVEs (OSV, NVD, EPSS, KEV), container images, provenance, filesystems, and SBOMs. Use when: "check package", "scan image", "verify", "is this safe", "scan dependencies", "CVE lookup", "blast radius".

msaad00 Skill

Analyze blast radius, attack paths, and threat landscape across your AI infrastructure. Use when: "blast radius", "threat intel", "risk score", "attack path", "lateral movement", "context graph", "who can reach what".

msaad00 Skill

Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".

msaad00 Skill

Monitor agent fleet, track trust scores, and manage lifecycle states. Use when: "fleet", "watch agents", "runtime status", "trust scores", "fleet sync", "agent lifecycle", "serve dashboard".

b-open-io-bsv-skills Bundle

Explicit-only installer for the BSV Skills David Codex custom agent. Use ONLY when the user explicitly asks to install, update, check, uninstall, or set up the BSV Skills, David, or Bitcoin Codex agent, including "install David in Codex", "update the BSV Skills Codex agent", or "check bsv_skills_bitcoin". Never auto-invoke for ordinary BSV, Bitcoin, wallet, transaction, identity, mining, or blockchain requests.

agenticsorg Skill

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

yhy0 Bundle

Use when facing web security challenges involving injection, authentication bypass, IDOR, access control, CSRF, HRS, server-side vulnerabilities, or web application exploitation

yhy0 Skill

Use when extracting WSS terminal connection parameters (URL, cookie, protocol type) from browser pages for wss_connect tool usage

yhy0 Skill

零界战场感知 — 每10分钟执行一次，更新战场状态、Agent画像、联盟评分，产出本轮博弈决策。所有其他任务的前置感知层。

yhy0 Skill

零界挑战三：C3 帖子注入模板库 — 为每篇帖子选择并生成多向量分层注入层，最大化其他 AI agent 点赞率。被 post-cycle 调用，不单独 cron 执行。