菜单
Promote a validated pattern into a reusable Skill in AgentDB's skill library. Use when the same approach has worked 3+ times across episodes, or when the user explicitly says "make this a skill" / "save this as reusable".
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。
基于 SOC 职业分类
Walk the causal graph in AgentDB to explain why two memories are connected, or trace a root cause. Use when the user asks "why did X happen", "what led to Y", or after an incident.
Record a causal relationship between two memories in AgentDB — "X caused Y", "A supersedes B", "patch-foo depends-on patch-bar". Use when the user is documenting cause/effect, dependencies, supersessions, or after-action analysis.
Store memories in tier-aware hierarchical memory — working / short-term / long-term — and recall with tier filters. Use for working-set context that should fade, vs facts that should persist, vs patterns that should be searchable forever.
Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server. Use when the user is starting a new project that needs vector memory, or asks to "set up agentdb" / "init agentdb".
Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb stats", or after long-running sessions to confirm state.
Execute Cypher queries against AgentDB's graph backend. Use when the user wants to write a custom traversal that the standard tools don't cover, or when explaining graph state.
| name | agentdb-skill-create |
| description | Promote a validated pattern into a reusable Skill in AgentDB's skill library. Use when the same approach has worked 3+ times across episodes, or when the user explicitly says "make this a skill" / "save this as reusable". |
Take an approach that's been validated multiple times and elevate it to a first-class Skill — queryable by intent, composable into chains, and tracked separately from one-off patterns.
agentdb_skill_create(
name: <verb-noun-noun> // e.g. "rotate-jwt-refresh-token"
description: <one-liner> // what it does
precondition: <plain English query> // matched by intent embedding
action: <step list> // executable steps
outcome: <success criteria> // what "worked" looks like
tags: [<topic>, <stack>, ...]
metadata: { sourceEpisodeIds: [...], confidence }
)
The precondition is what makes the skill discoverable — it's embedded and matched against future task intents. Write it like a search query: "need to rotate a JWT refresh token without invalidating active sessions", not like a docstring.
Skills can chain via agentdb_skill_compose:
compose(
intent: "set up authenticated API with token rotation",
available: [skill_a, skill_b, skill_c]
) → bandit picks the best chain ordering
The bandit tracks composition rewards over time; bad orderings decay automatically.
action. Use placeholders.