How do I install the Rtlsdr Hardware Capture skill?

Run npx skillmds@latest add nitrojacob/rtlsdr-hardware-capture in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Rtlsdr Hardware Capture safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Rtlsdr Hardware Capture?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Rtlsdr Hardware Capture free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Rtlsdr Hardware Capture?

nitrojacob (@nitrojacob) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Rtlsdr Hardware Capture by nitrojacob

Name: Rtlsdr Hardware Capture
Author: nitrojacob

Rtlsdr Hardware Capture

Capture live RF signals from RTL-SDR hardware dongles with tunable center frequency, sample rate, duration, tuner/RF/IF gain, offset frequency, and DDC channelization, exporting directly to SigMF (.sigmf-meta and .sigmf-data).

nitrojacob 726b6e8 3 files · 17.2 KB Updated Sep 17, 2026

File contents

RTL-SDR Hardware Capture & Interactive Channel Selection Skill 📡

Use this skill when the user requests to capture live RF spectrum signals using an RTL-SDR hardware USB dongle, analyze potential channels in wideband spectrum, select a target channel interactively, and perform DDC channelization.

Triggering Context

Activate this skill whenever the user asks to:

"capture from RTL-SDR"
"capture pure wideband signal at "
"list potential channels from wideband capture"
"localize channel offset and do DDC"

Interactive 4-Step Wideband Workflow

Step 1: Pure Wideband Capture (Raw Hardware Acquisition)

Capture the full $2.4\text{ MSps}$ wideband RF spectrum without DDC filtering during hardware acquisition:

PYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/capture_rtlsdr.py \
  --freq <center_freq_mhz> \
  --duration <seconds> \
  --gain <tuner_rf_gain_db> \
  --if_gain <if_gain_db> \
  --wideband \
  --output /tmp/wideband_raw_capture.sigmf-data

Step 2: Spectral Power-Based Scan & Potential Channels Listing

Scan the wideband spectrum capture using PSD spectral power analysis to discover and list all potential candidate signal channels:

PYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/localize_and_extract.py \
  --input /tmp/wideband_raw_capture.sigmf-data \
  --scan_only

Step 3: User Channel Selection

Present the table of potential channels (showing Rank, Frequency Offset, Absolute RF Frequency, Peak Power, and Bandwidth) to the user and ask the user to select which candidate channel they wish to localize and process.

Step 4: Targeted DDC Extraction & Full DSP Pipeline Execution

Based on the user's selection, run DDC channelization on the chosen channel index (--channel_index N) or explicit offset (--manual_offset OFFSET_HZ):

PYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/localize_and_extract.py \
  --input /tmp/wideband_raw_capture.sigmf-data \
  --channel_index <user_selected_rank> \
  --decimation 10 \
  --output /tmp/extracted_channel_localized.sigmf-data

Followed by downstream processing: signal-analysis $\rightarrow$ signal-cleanup $\rightarrow$ modulation-recognition $\rightarrow$ signal-demodulation.

---name: rtlsdr-hardware-capturedescription: Capture live RF signals from RTL-SDR hardware dongles with tunable center frequency, sample rate, duration, tuner/RF/IF gain, offset frequency, and DDC channelization, exporting directly to SigMF (.sigmf-meta and .sigmf-data).---# RTL-SDR Hardware Capture & Interactive Channel Selection Skill 📡Use this skill when the user requests to capture live RF spectrum signals using an RTL-SDR hardware USB dongle, analyze potential channels in wideband spectrum, select a target channel interactively, and perform DDC channelization.## Triggering ContextActivate this skill whenever the user asks to:- "capture from RTL-SDR"- "capture pure wideband signal at <freq>"- "list potential channels from wideband capture"- "localize channel offset and do DDC"---## Interactive 4-Step Wideband Workflow### Step 1: Pure Wideband Capture (Raw Hardware Acquisition)Capture the full $2.4\text{ MSps}$ wideband RF spectrum without DDC filtering during hardware acquisition:```bashPYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/capture_rtlsdr.py \ --freq <center_freq_mhz> \ --duration <seconds> \ --gain <tuner_rf_gain_db> \ --if_gain <if_gain_db> \ --wideband \ --output /tmp/wideband_raw_capture.sigmf-data```### Step 2: Spectral Power-Based Scan & Potential Channels ListingScan the wideband spectrum capture using PSD spectral power analysis to discover and list all potential candidate signal channels:```bashPYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/localize_and_extract.py \ --input /tmp/wideband_raw_capture.sigmf-data \ --scan_only```### Step 3: User Channel SelectionPresent the table of potential channels (showing Rank, Frequency Offset, Absolute RF Frequency, Peak Power, and Bandwidth) to the user and ask the user to select which candidate channel they wish to localize and process.### Step 4: Targeted DDC Extraction & Full DSP Pipeline ExecutionBased on the user's selection, run DDC channelization on the chosen channel index (`--channel_index N`) or explicit offset (`--manual_offset OFFSET_HZ`):```bashPYTHONPATH=/usr/lib/python3/dist-packages:./ .agents/skills/rtlsdr-hardware-capture/scripts/localize_and_extract.py \ --input /tmp/wideband_raw_capture.sigmf-data \ --channel_index <user_selected_rank> \ --decimation 10 \ --output /tmp/extracted_channel_localized.sigmf-data```Followed by downstream processing:`signal-analysis` $\rightarrow$ `signal-cleanup` $\rightarrow$ `modulation-recognition` $\rightarrow$ `signal-demodulation`.

Frequently asked questions