bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Local Deep Research Skill
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install eplt/local-deep-researchInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
This skill interfaces with a locally-hosted LDR (Local Deep Research) service to perform multi-cycle, iterative research with full citations and source tracking.
LDR_BASE_URL (default http://127.0.0.1:5000). Only point it at an LDR instance you control. Do not set it to an unknown or untrusted remote host.curl and jq are installed on the host where the skill runs.LDR_SERVICE_USER and LDR_SERVICE_PASSWORD (or LDR_USERNAME/LDR_PASSWORD) via environment variables or a local .env file only. Use a dedicated, low-privilege LDR account (e.g. openclaw_service). Do not store secrets in committed config or in the skill directory.~/.config/local_deep_research/config/.env if that file exists. That file may expose any variables it contains to the script. Verify the contents of that path before use; do not place unrelated secrets there.scripts/ldr-research.sh before use. For higher assurance, run it in an isolated environment (e.g. container or VM) with network restricted to your LDR host.LDR uses session-cookie auth with CSRF protection (not HTTP Basic Auth). The skill script performs a proper login flow: GET login page → obtain session cookie and CSRF token → POST credentials + CSRF → reuse session cookie (and CSRF for POSTs) for all API calls. Username and password are used only to create a session with your local LDR instance; they are never sent to ClawHub, GitHub, or any other server.
Do not put credenti...
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
Multi-cycle deep research using a locally-hosted Local Deep Research (LDR) service for OpenClaw / ClawHub. Use this skill when you need comprehensive research with citations, literature reviews, competitive intelligence, or exhaustive web search with iterative question generation.
Triggers: "deep research", "research this topic", "comprehensive analysis with sources", "literature review", "investigate [topic]", or when local LDR is preferred over cloud research.
curl and jq must be installed. The skill declares these in its manifest (requires.bins).LDR_BASE_URL (default http://127.0.0.1:5000) and, if your LDR uses auth, LDR_SERVICE_USER and LDR_SERVICE_PASSWORD (or LDR_USERNAME/LDR_PASSWORD). These are declared in the skill manifest (requires.env / primaryEnv). Set them via your environment or a local .env file only; do not commit secrets.LDR_BASE_URL at an LDR instance you control (e.g. localhost). The script sources ~/.config/local_deep_research/config/.env if present—verify that file’s contents and do not put unrelated secrets there.scripts/ldr-research.sh; for higher assurance, run the skill in an isolated environment with network restricted to your LDR host.http://127.0.0.1:5000)curl and jq on the hostexport LDR_BASE_URL="http://127.0.0.1:5000"
.env file onl...# Local Deep Research Skill This skill interfaces with a locally-hosted LDR (Local Deep Research) service to perform multi-cycle, iterative research with full citations and source tracking. ## What to consider before installing - **LDR service**: The script talks only to the URL in `LDR_BASE_URL` (default `http://127.0.0.1:5000`). Only point it at an LDR instance you control. Do not set it to an unknown or untrusted remote host. - **Required binaries**: Ensure `curl` and `jq` are installed on the host where the skill runs. - **Credentials**: If your LDR instance requires login, set `LDR_SERVICE_USER` and `LDR_SERVICE_PASSWORD` (or `LDR_USERNAME`/`LDR_PASSWORD`) via environment variables or a local `.env` file only. Use a dedicated, low-privilege LDR account (e.g. `openclaw_service`). Do not store secrets in committed config or in the skill directory. - **Sourced .env**: The script optionally sources `~/.config/local_deep_research/config/.env` if that file exists. That file may expose any variables it contains to the script. Verify the contents of that path before use; do not place unrelated secrets there. - **Review the script**: The script performs form-based session+CSRF login and uses an ephemeral cookie jar. It does not send data to any endpoint other than the configured LDR service. You can review `scripts/ldr-research.sh` before use. For higher assurance, run it in an isolated environment (e.g. container or VM) with network restricted to your LDR host. ## Configuration ### Credentials (local-only, never transmitted) LDR uses **session-cookie auth with CSRF protection** (not HTTP Basic Auth). The skill script performs a proper login flow: GET login page → obtain session cookie and CSRF token → POST credentials + CSRF → reuse session cookie (and CSRF for POSTs) for all API calls. Username and password are used **only** to create a session with your **local** LDR instance; they are never sent to ClawHub, GitHub, or any other server. **Do not** put credenti...
# Local Deep Research (LDR) — OpenClaw Skill > Multi-cycle deep research using a **locally-hosted** Local Deep Research (LDR) service for OpenClaw / ClawHub. Use this skill when you need comprehensive research with citations, literature reviews, competitive intelligence, or exhaustive web search with iterative question generation. **Triggers:** "deep research", "research this topic", "comprehensive analysis with sources", "literature review", "investigate [topic]", or when local LDR is preferred over cloud research. --- ## Before installing - **Required**: `curl` and `jq` must be installed. The skill declares these in its manifest (`requires.bins`). - **Environment / credentials**: The skill expects `LDR_BASE_URL` (default `http://127.0.0.1:5000`) and, if your LDR uses auth, `LDR_SERVICE_USER` and `LDR_SERVICE_PASSWORD` (or `LDR_USERNAME`/`LDR_PASSWORD`). These are declared in the skill manifest (`requires.env` / `primaryEnv`). Set them via your environment or a local `.env` file only; do not commit secrets. - **Trust**: Only point `LDR_BASE_URL` at an LDR instance you control (e.g. localhost). The script sources `~/.config/local_deep_research/config/.env` if present—verify that file’s contents and do not put unrelated secrets there. - **Optional**: Review `scripts/ldr-research.sh`; for higher assurance, run the skill in an isolated environment with network restricted to your LDR host. --- ## Requirements - A running **LDR** instance (e.g. `http://127.0.0.1:5000`) - OpenClaw with network and shell permissions - `curl` and `jq` on the host - (If LDR has auth enabled) LDR account credentials — **stored only locally**, see below --- ## Quick start 1. **Install the skill** (e.g. via ClawHub or copy into your OpenClaw skills directory). 2. **Set LDR URL** (optional if using default): ```bash export LDR_BASE_URL="http://127.0.0.1:5000" ``` 3. **If your LDR instance requires login**, set credentials via **environment variables or a local `.env` file onl...
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, o...
飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化...