Skip to main content
hashgraph-online
GitHub 创作者资料

hashgraph-online

按仓库查看 11 个 GitHub 仓库中的 374 个已收集 skills。

已收集 skills
374
仓库
11
更新
2026年9月29日
这里展示前 8 个仓库;完整仓库列表在下方继续。
仓库浏览

仓库与代表性 skills

design-helper
未分类

Use whenever anything visible must be decided — a CSS value, spacing, radius, shadow, border, color, layout, wireframe, state, motion. Never describe the options in prose or a table and ask the user to pick; render them side by side in one HTML file, open it…

2026年9月26日
jev-social
未分类

Run browser-grounded, read-only social research through Jev Social when a user wants posts, profiles, comments, video evidence, or a source-linked report from Instagram, TikTok, or LinkedIn and the local socai CLI reports support for that platform. Do not use…

2026年9月26日
centricmem-agent
未分类

Organises and retrieves Markdown memory on the hosted CentricMem librarian (search, notes, decisions, transcripts). Use when starting a session, resuming after context compress / checkpoint / new chat, filing Non-Micro work, searching project memory,…

2026年9月26日
unified-ai-gateway
未分类

Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.

2026年9月26日
eval
未分类

Eval-Driven Development (EDD) for AI workflows. pass@k metrics, capability evals, regression evals. Triggers: eval, edd, pass@k, capability, regression, benchmark.

2026年9月26日
chapter-writing
未分类

This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project.

2026年9月26日
character-management
未分类

This skill should be used when the user asks to "create a character", "update a character", "add a character", "build a family tree", "character relationships", "character timeline", "character arc", "character profile", "relationship graph", "name a…

2026年9月26日
discovery-drafting
未分类

This skill should be used when the user asks to "pantsing", "discovery write", "write without an outline", "discovery draft", "write into the dark", "story kernel", "reconcile a chapter", "reverse outline", "cut a subplot", "dead end", "drafting sprint",…

2026年9月26日
已展示 8 / 342 个已收集 Skill。
已展示 8 / 13 个已收集 Skill。
plugin-scanner
未分类

Scan AI agent skills, plugins, MCP servers, and agent tooling locally for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

2026年9月16日
hol-guard
未分类

Use when setting up local HOL Guard protection, reviewing local Guard approvals or receipts, or scanning agent skills, plugins, MCP servers, packages, and harness configuration before trust or execution.

2026年9月16日
hol-guard
计算机系统分析师

Protects local AI coding-agent workflows with HOL Guard pre-execution controls, approvals, receipts, and verification. Use when enabling Guard for a supported local harness, reviewing a Guard block, or validating protection before trusted tool execution.…

2026年9月8日
plugin-scanner
计算机系统分析师

Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them. Use when evaluating agent ecosystem content before installation, publication, or…

2026年9月8日
hol-guard
信息安全分析师

Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, scanning Codex plugins, skills, MCP servers, marketplace packages, or running plugin-scanner verification before release.

2026年8月25日
plugin-scanner
信息安全分析师

Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

2026年8月21日
hol-guard
其他计算机职业

Install, initialize, repair, or check local HOL Guard security protection for OpenClaw.

2026年8月10日
已展示 11 / 11 个仓库
已展示全部仓库