From agentdb-memory
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".
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentdb-memory:agentdb-skill-createThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.npx claudepluginhub ruvnet/agentdb --plugin agentdb-memoryCreates and improves agent skills following the Agent Skills specification using workflows for synthesis, iteration, authoring, evaluation, and optimization. Use for skill creation, updates, or refinement requests.
Guides creation of Agent Skills with progressive disclosure, best practices, structure, and categories. Use when building new skills or understanding skill format.
Creates new agent skills with proper structure and progressive disclosure. Use when user wants to create, write, or build a new skill.