← 返回 Skills 市场
150
总下载
2
收藏
0
当前安装
11
版本数
在 OpenClaw 中安装
/install reflexio
功能描述
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or...
安全使用建议
This plugin appears to do what it says: it extracts and stores local user facts and playbooks under .reflexio/ and uses Openclaw's memory/LLM capabilities to dedupe and consolidate. Before installing: (1) review the code and prompt templates if you don't trust their behavior, especially the LLM prompts that produce JSON used to write/delete files; (2) run it in a safe/test workspace first (backup or isolate any existing .reflexio/); (3) decline the automated config changes if you don't want the plugin to alter global active-memory or memorySearch.extraPaths (you can perform the steps manually after review); (4) do not paste secrets into conversations — the skill instructs redaction but relies on agent behavior to obey that rule; (5) if you require stricter controls, disable exec/automatic config changes and perform setup steps manually. Overall the package is internally coherent, but it has privileges to change Openclaw config and to write/delete local files — grant those only when you trust the plugin and have reviewed the prompts and code.
功能分析
Type: OpenClaw Skill
Name: reflexio
Version: 1.0.10
The reflexio-embedded skill bundle is a comprehensive local memory management system designed to capture user preferences and procedural corrections into a `.reflexio/` directory. It utilizes OpenClaw's native memory engine, lifecycle hooks, and sub-agents to perform extraction, deduplication, and periodic consolidation of facts. The code and instructions (SKILL.md, prompts) include explicit safeguards and instructions to redact secrets, credentials, and PII, and the setup process for modifying system configuration requires explicit user approval. While the plugin performs high-privilege operations such as modifying the workspace `HEARTBEAT.md` and executing `openclaw` CLI commands for indexing, these actions are clearly aligned with its stated purpose of providing persistent, cross-session learning without external dependencies.
能力标签
能力评估
Purpose & Capability
Name/description (capture profiles/playbooks into .reflexio/) align with the code and prompts: tools for extracting, deduping, writing, consolidating, and searching memories are present. The plugin asks to register .reflexio/ as a memory path and to enable active-memory for better retrieval — these are expected for the stated purpose.
Instruction Scope
SKILL.md instructs the agent (with user approval) to run `openclaw config set` commands and to create a `.reflexio/.setup_complete_<agentId>` marker; it also instructs LLM-driven extraction and to call local tools (reflexio_search/write_*) and run `openclaw memory search` via an injected runner. These actions are within scope but have side effects on agent config and local files; the skill explicitly warns to never write secrets but this is a policy requirement (not fully enforced by code).
Install Mechanism
No external install/download URLs are used. The plugin ships as source files (TypeScript) intended to be installed via Openclaw CLI; there is no bake-in network fetch or archive extraction from an untrusted host in the manifest.
Credentials
The skill declares no required env vars or credentials. It optionally suggests configuring an embedding provider for improved retrieval quality (user-supplied API key); that is reasonable and optional. The code reads WORKSPACE if present (standard) and relies on platform-provided inferFn/runner rather than requiring extra secrets.
Persistence & Privilege
always:false. The skill may propose changing global Openclaw plugin/config settings (active-memory agents list and agents.defaults.memorySearch.extraPaths) — it asks for explicit approval before making changes. Allowing those changes will affect how memory is injected globally for agents; this is expected but significant, so approve only if you accept those side effects.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install reflexio - 安装完成后，直接呼叫该 Skill 的名称或使用
/reflexio触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.10
**Reflexio v1.0.10 — Major re-architecture: now runs fully local, storing all memory in .reflexio/ using only OpenClaw primitives.**
- Replaced previous server-based design and network-dependent hooks with a native, file-backed skill under the new reflexio-embedded name.
- Adds agent-initialization logic: probes and, if approved, auto-configures active-memory and .reflexio/ path registration per agent.
- Introduces `reflexio_write_profile`, `reflexio_write_playbook`, and `reflexio_search` tools for profile/playbook management and retrieval.
- Documents strict signals and capture requirements (triggers, confirmation/patterns, safety, TTL handling).
- Removes network hops, external LLM/service dependencies, and credential prompts: all operation is now fully local and transparent.
- Expanded documentation for first-use setup, data safety, and degraded mode operation if configuration steps are declined.
v1.0.9
**Major update: Reflexio skill now uses a local server backend for LLM-based session extraction, ships with new slash commands, and simplifies config.**
- Switched from embedded agent/consolidator model to a hook approach: all capture, extraction, and aggregation routed through a local Reflexio server at 127.0.0.1:8081.
- Added new slash commands: `/reflexio-extract` (publish session learnings) and `/reflexio-aggregate` (merge learnings across agents/sessions).
- Removed 27 files related to previous OpenClaw embedded integration (manual agent scripts, prompts, and install scripts).
- Added concise setup instructions: requires only a local Reflexio backend and CLI, with any LLM provider supported for extraction.
- Privacy & credential handling clarified: skill never reads API keys directly; local server performs LLM calls and may forward excerpts to external model providers.
- All configuration moved to `~/.reflexio/`; no more OpenClaw-wide install scripts or privileged changes required.
v1.0.8
reflexio 1.0.8
- Added SECURITY.md file outlining security policies for the project.
- No functional or runtime changes to the skill itself.
v1.0.7
**Reflexio Embedded 1.0.7 — First release of the serverless Reflexio skill for Openclaw**
- Captures user facts (profiles) and agent corrections (playbooks) into workspace-local `.reflexio/` directories for seamless, cross-session learning.
- Runs entirely within Openclaw; no separate Reflexio server, database, or plugin-owned API keys required.
- Uses existing Openclaw LLM and embedding provider (if configured) for all extraction and retrieval — supports offline mode with local models.
- Auto-enables the `active-memory` plugin, registers a daily consolidation cron job, and restarts the Openclaw gateway during install.
- All data is stored locally; the plugin reads/saves only within known Openclaw workspace folders and `.reflexio/`.
- Enhanced privacy: no outbound sync, and no new network traffic beyond your existing Openclaw LLM/embedding provider configuration.
v1.0.6
Reflexio 1.0.6 Changelog
- Added explicit documentation that enabling this skill requires providing an LLM provider API key during setup, even though no credential is referenced in the skill metadata.
- Clarified separation between the hook (stateless, no credential or config reads) and the backend server (which requires and uses the LLM provider key for extraction).
- Updated First-Use Setup instructions to highlight the interactive prompt for LLM provider selection and credential entry.
- Provided detailed explanation of why the skill metadata omits environment variable requirements, with emphasis on backend/server-level dependencies.
- Improved privacy and data collection documentation, ensuring the role of the API key and backend responsibilities are clearly stated.
v1.0.5
**Summary:** This update clarifies privacy implications and updates the Reflexio hook to use a JavaScript handler. Localhost-only capture is explicitly limited to the hook; the local Reflexio server may forward excerpts to LLM providers depending on configuration.
- Updated the core hook from TypeScript (`handler.ts`) to JavaScript (`handler.js`).
- Documentation now explains two network hops: local-only for capture, potentially external for LLM-based extraction.
- Privacy section clarifies that the local Reflexio server may send conversation excerpts to third-party LLM APIs depending on `~/.reflexio/.env` settings.
- Users are advised to configure a local LLM for fully offline operation if needed.
- Setup and opt-out instructions updated to reference the new handler file and make privacy boundaries unambiguous.
v1.0.4
reflexio 1.0.4
- Clarifies first-use setup: local Reflexio server must be started manually; hook only communicates with `http://127.0.0.1:8081`
- Updates setup steps to check server health and launch server if needed
- Explicitly documents server start-up in the instructions and outlines user notification requirements
- Refines error-handling: skills degrade gracefully if local server is unreachable
- Improves language for transparency, privacy, and opt-out instructions
v1.0.3
Version 1.0.3
- Changed to localhost-only: all data is now hard-pinned to your machine, stored under ~/.reflexio/, and never sent off-host.
- The hook prepends --server-url http://127.0.0.1:8081 to every reflexio CLI call, overriding all environment variables and user configs.
- No environment variables or remote servers are supported; configuration is locked down to prevent data from ever leaving your computer.
- Privacy documentation updated to clarify that nothing is ever sent externally, and to improve instructions for opt-out and local data wiping.
v1.0.2
Use localhost only
v1.0.1
reflexio 1.0.1 Changelog
- Major update: adds extensive privacy and data collection disclosure, clarifying exactly what is captured, where it is sent, and how to disable features.
- SKILL.md rewritten to prioritize user transparency and consent, including a new "Privacy & Data Collection" section at the top.
- Now instructs agents to announce Reflexio’s activity and destination on session start, and when background servers are launched.
- Detailed instructions for per-session and permanent opt-outs, as well as search-only configurations.
- The description clarifies cross-instance learning and how Reflexio aggregates corrections for all OpenClaw agents.
- Enhanced warnings: explicitly instructs users to audit the Reflexio server destination before enabling the skill.
v1.0.0
Initial release of reflexio skill for OpenClaw:
- Enables agents to search Reflexio for task-specific playbooks and user preferences before starting any task.
- Publishes corrections, user preferences, and key learnings to Reflexio when users correct, intervene, or a milestone is completed.
- Installs CLI tools and hooks for seamless integration with OpenClaw, including auto-injection of behavioral rules.
- Gracefully degrades if Reflexio cannot be installed or reached—never blocks user tasks.
- Step-by-step instructions for setup, searching, and publishing, including handling of multi-agent and multi-user cases.
元数据
常见问题
Reflexio 是什么？
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 150 次。
如何安装 Reflexio？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install reflexio」即可一键安装，无需额外配置。
Reflexio 是免费的吗？
是的，Reflexio 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Reflexio 支持哪些平台？
Reflexio 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Reflexio？
由 Yi Lu（@yyiilluu）开发并维护，当前版本 v1.0.10。
推荐 Skills