菜单
Use when writing Python code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ax-llm/ax --skill ax-python-agent-memory-skills命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when writing C++ code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.
Use when writing C++ code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
Use when writing C++ code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
正在显示 SKILL.md
| name | ax-python-agent-memory-skills |
| description | Use when writing Python code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking. |
| version | 23.0.15 |
This skill helps an agent write Python code with the generated Ax package axllm. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.
axllm.API.md and axir-api.json.axir-capabilities.json.examples/.javascript-quickjs, python-pyodide.from axllm import agent
helper = agent("question:string -> answer:string")
out = helper.forward(llm, {"question": "How should I proceed?"})
skills seed the loaded-skill prompt without firing load observers.skills override constructor entries by normalized ID and remain loaded for later calls. IDs and names are trimmed, malformed entries are skipped, valid empty content is preserved, and rendered entries are ID-sorted.memories seeds the first actor turn. Recalled entries merge by ID for that run, then memory state resets before the next forward.onSkillsSearch / onMemoriesSearch take precedence over static catalogs. Without a host callback, skillsCatalog / memoriesCatalog use the built-in deterministic lexical ranker.onLoadedMemories / onLoadedSkills observe runtime recall and discovery, not constructor presets. onUsedMemories / onUsedSkills emit one consolidated notification per forward. Forward observers override constructor observers, and observer errors are ignored.relevanceRanking produces advisory skill and memory hints using the same tokenization, weighting, tie suppression, limits, snippets, and already-loaded exclusion as TypeScript.get_state() and set_state(...) preserve the legacy bare-runtime snapshot shape. Use export_runtime_state() and restore_runtime_state(...) for the complete portable agent snapshot, including loaded skills and constructor-preset reapplication. Do not interchange the two shapes.src/examples/python/long-agents/skills-and-memory-assistant.py.smart-defaults-agent example under src/examples/python/long-agents/.agent, AxAgentProcessCodeRuntime, RuntimeCapabilities, RuntimeEnvelope, javascript-quickjs, python-pyodideprovider-api examples only when the user explicitly has provider credentials available.no-key examples for deterministic local checks and provider request mapping.tools/*/skills/ into user packages.