菜单
Convert query text to an embedding and run a cosine-distance search over the PGVector entities table to find related nodes in the Human Story Graph. Use when the Knowledge Graph agent must retrieve semantically related entities/facts to feed a writing or research agent.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Query the keyless academic and public-domain registries (OpenAlex, Crossref, Semantic Scholar, Project Gutenberg, Internet Archive, Stack Exchange) for a topic and get back normalized, copyright-safe reference metadata (title, link, provenance). Use when gather-citations or verify-claims needs primary-literature grounding instead of the LLM's training memory.
Query Wikipedia, Wikidata, Stack Exchange, public Discourse forums, academic APIs, and public-domain archives to synthesize facts, human struggles, and philosophical debates to build the narrative arc for a topic. Store only facts/events/dates/relationships, dialogic tension points, and reference metadata — never full articles (copyright-safe pipeline, spec §2.5).
Query Metacritic, GameSpot, and TVGuide (resolved and read via Bright Data) for a personality's existing game/film/TV adaptation, extracting critic/user scores, narrative themes critics highlighted, and reception debates. Use when generate-psych-profile or backlog-ranking want a critical-reception signal on top of gather-citations' facts and fandom-lore's fan interpretation.
Compose the per-beat music score plan (Lyria cues, deliberate silence segments, optional sound-effect cues) for a content run by calling Hermes's music-director judgment agent. Use when the Content Factory agent must produce the music_director_output that Hermes's content-run pipeline needs for music generation, beat-synced editing, and the SFX layer.
Decide the whole-video visual grade, typography, and per-shot treatments (transitions, camera moves, grade deviations, light leaks) for a content run by calling Hermes's visual-director judgment agent. Use when the Content Factory agent must produce the visual_director_output that Hermes's content-run pipeline needs for shot styling in Video Assembly.
Trigger Hermes's deterministic 11-agent video-production pipeline for an editorially-approved run, and poll it to completion. Use when submit-editorial-review records a human PASS and the approved asset bundle is ready to actually produce.
基于 SOC 职业分类
| name | query-semantic-nodes |
| description | Convert query text to an embedding and run a cosine-distance search over the PGVector entities table to find related nodes in the Human Story Graph. Use when the Knowledge Graph agent must retrieve semantically related entities/facts to feed a writing or research agent. |
| metadata | {"agent":"knowledge-graph","source":"Project Atlas Agent Skills Manifest §3","layer":"memory"} |
Semantic recall over the entity graph via vector similarity.
SELECT name, type, summary, (embedding <=> $1) AS distance
FROM entities ORDER BY distance LIMIT $2;
def query_semantic_nodes(query_text: str, limit: int = 5) -> list:
"""Embed query_text (1536-dim) and cosine-search PGVector for related nodes."""
query_text, limit.{name, type, summary, distance}.Call the temporal-bridge MCP tool start_workflow("querySemanticNodesWorkflow", "knowledge-graph", [{"query_text": query_text, "limit": limit}]), then poll get_workflow_result(workflow_id). Runs the SQL above for real against the live Railway Postgres entities table (server/src/modules/graph/graph.service.ts's querySemanticNodes), embedding query_text via LlmService.generateEmbeddings() (Modal-hosted embeddinggemma-300m, 300-dim — note this is not Jina; the embedding column is sized to match whatever model actually writes to it).
entities table on Railway is live (pgvector extension verified in production), but
only the two original seed rows (Sachin/McGrath) exist until gather-citations/autolink-entities or
another caller starts calling upsertEntity to actually populate it. Results will be sparse until then.No generative LLM for this skill itself — embedding + DB only.