SKILLS & AGENTS/Skill 与 Agent·MULTI-AGENT
semantica-agi/semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
怎么装：Install: pip install semantica
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.1%+0.1%
14k → 14k stars · 2 个快照14k → 14k stars · 2 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
HN_STORY · 12 points · 0 comments
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ Python 用户的完整版安装，包含命令行工具。The full install for Python users, including the command-line tool.
$ Python 用户的完整版安装，包含命令行工具。The full install for Python users, including the command-line tool.
两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.这不等于安全that does not mean it is safe，只能说明文档里没写。 — only that the docs do not mention it.
这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …anthropics.png?size=120\" alt=\"Claude Desktop\" width=\"48\" height=\"48\" /></a…"
},
{
"agent": "claude-ai",
"evidence": "readme: …dth=\"12.5%\"> <a href=\"https://claude.ai/download\"><img src=\"https://g…"
},
{
"agent": "codex",
"evidence": "readme: …> <a href=\"https://github.com/openai/codex\"><img src=\"https://github.com…"
},
{
"agent": "windsurf",
"evidence": "readme: …r Claude Code, Cursor, Codex, Windsurf, Cline, Continue, VS Code, Op…"
},
{
"agent": "cline",
"evidence": "readme: …ode, Cursor, Codex, Windsurf, Cline, Continue, VS Code, OpenClaw,…"
},
{
"agent": "vscode",
"evidence": "readme: …x, Windsurf, Cline, Continue, VS Code, OpenClaw, and pi; a full-fea…"
},
{
"agent": "copilot",
"evidence": "readme: …com/github.png?size=120\" alt=\"GitHub Copilot\" width=\"48\" height=\"48\" /></a…"
}
],
"apiKey": "environment variables (e.g., `DATABRICKS_TOKEN`, `SNOWFLAKE_PASSWORD`) or a secrets ma",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 12,
"dev-tools": 3,
"indie-web": 0,
"skill-agent": 0,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "multi-agent"
},
"localRuntime": "Azure OpenAI · AWS Bedrock · Ollama · DeepSeek · Perplexity · Together AI ·",
"skillMdTotal": 18,
"skillMdErrors": [
{
"path": "plugins/skills/embed/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": "plugins/skills/reason/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": "plugins/skills/temporal/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": "plugins/skills/validate/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": "plugins/skills/visualize/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 5,
"agent": 0,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "13 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 1 markdown files",
"weight": 0.75
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/semantica/SKILL.md",
"plugins/skills/causal/SKILL.md",
"plugins/skills/change/SKILL.md",
"plugins/skills/decision/SKILL.md",
"plugins/skills/deduplicate/SKILL.md",
"plugins/skills/embed/SKILL.md",
"plugins/skills/explain/SKILL.md",
"plugins/skills/export/SKILL.md",
"plugins/skills/extract/SKILL.md",
"plugins/skills/ingest/SKILL.md",
"plugins/skills/ontology/SKILL.md",
"plugins/skills/policy/SKILL.md",
"plugins/skills/provenance/SKILL.md",
"plugins/skills/query/SKILL.md",
"plugins/skills/reason/SKILL.md",
"plugins/skills/temporal/SKILL.md",
"plugins/skills/validate/SKILL.md",
"plugins/skills/visualize/SKILL.md"
],
"skillMdFetched": 18
}