Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

rl-soc-install

Sterne0

Forks0

Aktualisiert16. Juli 2026 um 17:59

Installs the rl-spectra-intel CLI from the bundled wheel included with this plugin. Trigger when the user wants to set up rl-spectra-intel, when rl-spectra-intel is not found on PATH, or when rl-soc reports that the CLI is missing.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

reversinglabs

reversinglabs/rl-spectra-ai-soc

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

InformationssicherheitsanalystenInformatik- und Mathematikberufe·SOC 15-1212

SKILL.md

readonly

name	rl-soc-install
description	Installs the rl-spectra-intel CLI from the bundled wheel included with this plugin. Trigger when the user wants to set up rl-spectra-intel, when rl-spectra-intel is not found on PATH, or when rl-soc reports that the CLI is missing.

rl-soc-install

Installs the rl-spectra-intel CLI into a dedicated Python virtual environment at ~/.rl-spectra-intel-venv. The wrapper script and credential injection are handled by rl-soc-connect after installation.

Step 1 — Check if already installed; upgrade if so

~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version

If exit code 0: already installed. Search for a bundled wheel in the plugin cache:
```
find ~/.claude/plugins/cache/rl-spectra-ai-soc ~/.claude/plugins/marketplaces/rl-spectra-ai-soc/plugins -name "rl_spectra_intel-*.whl" 2>/dev/null | head -1
```
- If a wheel is found, upgrade from it:
```
~/.rl-spectra-intel-venv/bin/pip install --upgrade <wheel_path>
```
- If no wheel is found: tell the user the bundled wheel could not be located in the plugin cache and stop. Then verify and report the resulting version:
```
~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version
```
Tell the user whether the package was upgraded or already at the latest version, and stop.
If exit code non-zero or command not found: proceed to installation.

Step 2 — Verify Python version

python3 --version

Parse the version from the output (e.g. Python 3.10.2). The CLI requires Python 3.10 or later.

If the version is 3.10 or higher: proceed.
If the version is lower than 3.10, or python3 is not found: stop and tell the user:

rl-spectra-intel requires Python 3.10 or later. Found: <version or "not found">. Please upgrade Python before continuing.

Steps 3 and 4 — Create venv and install

These two steps MUST be executed in order using the EXACT commands below. Do NOT use pip, pip3, pipx, --user, or --break-system-packages. Do NOT skip Step 3. Do NOT ask the user which approach to use.

Step 3 — create the venv:

python3 -m venv ~/.rl-spectra-intel-venv

If exit code is non-zero: report the error and stop.

Step 4 — locate the bundled wheel and install:

Search for the bundled wheel in the plugin cache:

find ~/.claude/plugins/cache/rl-spectra-ai-soc ~/.claude/plugins/marketplaces/rl-spectra-ai-soc/plugins -name "rl_spectra_intel-*.whl" 2>/dev/null | head -1

If a wheel is found, install from it:

~/.rl-spectra-intel-venv/bin/pip install <wheel_path>

If no wheel is found: tell the user the bundled wheel could not be located in the plugin cache and stop. Do not attempt any other installation method.

If exit code is non-zero: show the full output to the user. The wheel file may be missing or corrupt — the user should reinstall the plugin.

Step 5 — Verify venv installation

~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version

If exit code 0: report the installed version. Proceed to Step 6.
If exit code non-zero: report the failure — the package may not have installed correctly.

Step 6 — Report outcome

Tell the user:

The installed version of rl-spectra-intel
That it is installed in ~/.rl-spectra-intel-venv
That they must close Claude Code, open a new terminal, and relaunch Claude Code before configuring credentials
That once they are in a new session, they can configure credentials by asking: "Set up my ReversingLabs credentials" (this will invoke the rl-soc-connect skill)

Mehr aus diesem Repository

gleiches Repository

rl-soc-connect

reversinglabs/rl-spectra-ai-soc

Configures the rl-spectra-intel CLI with ReversingLabs credentials. Trigger only when the analyst explicitly asks to set up or update credentials, provide an API username and password, or configure a custom host. Never invoke this skill automatically in response to CLI errors — authentication failures in analysis agents must be reported to the analyst, not silently fixed.

2026-07-160

rl-adjudicate

reversinglabs/rl-spectra-ai-soc

SOC adjudication phase. Reads FP validation findings and investigation findings, spawns the rl-adjudicate agent to weigh all evidence and produce a final CONFIRMED TP / CONFIRMED FP / UNCERTAIN verdict with confidence and a full per-signal audit trail. Gates transition to remediation. Writes rl-adjudication-verdict.md. Trigger after investigation is complete, or as part of the rl-soc pipeline.

2026-07-160

rl-fp-validate

reversinglabs/rl-spectra-ai-soc

False positive validation phase. Reads rl-triage-handoff.md and evaluates multiple FP signals to determine whether the detection is likely a false positive. A CONCLUSIVE FP recommendation short-circuits the pipeline, skipping investigation and remediation. Writes rl-fp-validate-findings.md. Trigger when triage is complete and FP validation is needed, or as part of the full rl-soc pipeline.

2026-07-160

rl-investigate

reversinglabs/rl-spectra-ai-soc

SOC investigation phase. Reads rl-triage-handoff.md and performs deep enrichment by spawning three parallel sub-agents: IOC enrichment, sample pivots, and YARA hunting with sandbox polling. Writes rl-investigate-findings.md. Trigger when triage and FP validation are complete and a full investigation is needed, or as part of the rl-soc pipeline.

2026-07-160

rl-remediate

reversinglabs/rl-spectra-ai-soc

SOC remediation phase. Reads triage, investigation, and adjudication findings and produces a prioritized containment and eradication playbook. Writes rl-remediate-playbook.md. Only runs when adjudication verdict is CONFIRMED TP or UNCERTAIN. Trigger after adjudication, or as part of the rl-soc pipeline.

2026-07-160

rl-report

reversinglabs/rl-spectra-ai-soc

SOC reporting phase. Reads all prior phase handoff files and synthesizes them into a narrative Markdown incident report and a machine-readable JSON IOC file. Trigger after all analysis phases are complete, or as part of the rl-soc pipeline.

2026-07-160

name	rl-soc-install
description	Installs the rl-spectra-intel CLI from the bundled wheel included with this plugin. Trigger when the user wants to set up rl-spectra-intel, when rl-spectra-intel is not found on PATH, or when rl-soc reports that the CLI is missing.

rl-soc-install

Step 1 — Check if already installed; upgrade if so

~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version

If exit code 0: already installed. Search for a bundled wheel in the plugin cache:
```
find ~/.claude/plugins/cache/rl-spectra-ai-soc ~/.claude/plugins/marketplaces/rl-spectra-ai-soc/plugins -name "rl_spectra_intel-*.whl" 2>/dev/null | head -1
```
- If a wheel is found, upgrade from it:
```
~/.rl-spectra-intel-venv/bin/pip install --upgrade <wheel_path>
```
- If no wheel is found: tell the user the bundled wheel could not be located in the plugin cache and stop. Then verify and report the resulting version:
```
~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version
```
Tell the user whether the package was upgraded or already at the latest version, and stop.
If exit code non-zero or command not found: proceed to installation.

Step 2 — Verify Python version

python3 --version

Parse the version from the output (e.g. Python 3.10.2). The CLI requires Python 3.10 or later.

If the version is 3.10 or higher: proceed.
If the version is lower than 3.10, or python3 is not found: stop and tell the user:

rl-spectra-intel requires Python 3.10 or later. Found: <version or "not found">. Please upgrade Python before continuing.

Steps 3 and 4 — Create venv and install

Step 3 — create the venv:

python3 -m venv ~/.rl-spectra-intel-venv

If exit code is non-zero: report the error and stop.

Step 4 — locate the bundled wheel and install:

Search for the bundled wheel in the plugin cache:

find ~/.claude/plugins/cache/rl-spectra-ai-soc ~/.claude/plugins/marketplaces/rl-spectra-ai-soc/plugins -name "rl_spectra_intel-*.whl" 2>/dev/null | head -1

If a wheel is found, install from it:

~/.rl-spectra-intel-venv/bin/pip install <wheel_path>

If no wheel is found: tell the user the bundled wheel could not be located in the plugin cache and stop. Do not attempt any other installation method.

If exit code is non-zero: show the full output to the user. The wheel file may be missing or corrupt — the user should reinstall the plugin.

Step 5 — Verify venv installation

~/.rl-spectra-intel-venv/bin/rl-spectra-intel --version

If exit code 0: report the installed version. Proceed to Step 6.
If exit code non-zero: report the failure — the package may not have installed correctly.

Step 6 — Report outcome

Tell the user:

The installed version of rl-spectra-intel
That it is installed in ~/.rl-spectra-intel-venv
That they must close Claude Code, open a new terminal, and relaunch Claude Code before configuring credentials
That once they are in a new session, they can configure credentials by asking: "Set up my ReversingLabs credentials" (this will invoke the rl-soc-connect skill)