ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

ralph-quick

Fast security spot-check with 10 iterations (~5-10 min). Use when user says 'quick security check', 'pre-deploy audit', 'ralph quick', 'fast security scan', 'spot check before deploy', or 'daily security check'. Covers secrets, OWASP basics, auth, rate limiting, and containers.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/dorukardahan/ralph-quick
Or

Ralph Quick — 10 Iterations (~5-10 min)

Fast security spot-check for pre-deployment or daily security hygiene.

References

  • Severity definitions

Instructions

Execution Engine

YOU MUST follow this loop for EVERY iteration:

  1. STATE: Read current iteration (start: 1)
  2. ACTION: Perform ONE check from current phase
  3. VERIFY: Before reporting FAIL — read actual code, check if a library handles it, check DB constraints, check if dev-only
  4. REPORT: Output iteration result in the format below
  5. INCREMENT: iteration = iteration + 1
  6. CONTINUE: IF iteration <= 10 GOTO Step 1
  7. FINAL: Generate summary report saved to .ralph-report.md

Critical rules:

  • ONE check per iteration (not all at once)
  • ALWAYS show iteration counter [QUICK-X/10]
  • NEVER skip iterations
  • If VERIFY is inconclusive: mark NEEDS_REVIEW, not FAIL

Per-Iteration Output

[QUICK-{N}/10] {check_name}
Target: {file or system component}
Result: {PASS|FAIL|WARN|N/A}
Confidence: {VERIFIED|LIKELY|PATTERN_MATCH|NEEDS_REVIEW}
Finding: {description or "Clean"}
───────────────────────────────

Persona

Senior security engineer — evidence-based, critical focus, maximum efficiency.

Phase Structure

IterCheck
1Auto-detect stack, infra, git sync
2.env in .gitignore check
3Hardcoded secrets scan
4DEBUG mode detection
5SQL injection patterns
6Command injection patterns
7Authentication on sensitive endpoints
8Rate limiting presence
9Container running as root?
10Summary & recommendations

Auto-Detect (Iteration 1)

Deterministic order:

  1. git rev-parse --show-toplevel
  2. Stack: package.json, pyproject.toml, requirements.txt, go.mod
  3. Infra: Dockerfile, docker-compose.yml, k8s manifests
  4. CI/CD: .github/workflows, .gitlab-ci.yml
  5. Skip non-applicable checks, mark N/A

Confidence Levels

LevelMeaning
VERIFIEDConfirmed with code reading or PoC
LIKELYStrong evidence, no PoC
PATTERN_MATCHKeyword match only — flag for human review
NEEDS_REVIEWInconclusive

Severity

LevelCVSSResponse
CRITICAL9.0-10.0Stop and fix immediately
HIGH7.0-8.9Fix before deployment
MEDIUM4.0-6.9Schedule fix
LOW0.1-3.9Note for later

Report File

On start: if .ralph-report.md exists, rename to .ralph-report-{YYYY-MM-DD-HHmm}.md. Save final report at end.

Parameters

ParamDefaultOptions
--iterations101-20
--focusallsecrets, owasp, infra, all

Note: Parameters are AI-interpreted instructions, not parsed CLI args.

When to Use

  • Pre-deployment quick check
  • Daily security spot-check
  • Verifying a specific fix

Metadata

Stars2387
Views0
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-dorukardahan-ralph-quick": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

research-reprompter

Transform rough research questions into executable USACF research prompts. Use when user says "research", "research this", "investigate", "deep dive", "researcher", or pastes a research topic. Generates complete multi-agent swarm configuration with algorithm selection, claude-flow commands, and adversarial review.

dorukardahan 2387

ralph-security

Comprehensive security audit with 100 iterations (~30-60 min). Use when user says 'security audit', 'ralph security', 'weekly security check', 'audit this project', 'new project security review', or 'check for vulnerabilities'. Covers OWASP Top 10, auth, secrets, infrastructure, and code quality.

dorukardahan 2387

skeall

Agent Skills (SKILL.md) builder, auditor, and improver for cross-platform LLM agents. Use for "skeall", "build a skill", "create skill", "improve skill", "audit skill", "skill review", or any SKILL.md question. Follows agentskills.io standard.

dorukardahan 2387

humanizer-enhanced

Advanced AI text humanizer for blog content. Detects and removes 34 AI writing patterns, adds personality/soul, and handles crypto/Web3 specific tells. Use when user says /humanizer, "humanize this", "remove AI patterns", "make it sound human", or asks to clean up blog posts, articles, or drafts. Features: 28 base patterns from Wikipedia's "Signs of AI writing", 6 crypto/Web3 specific patterns, severity scoring (HIGH/MEDIUM/LOW), stat attribution fixer, soul/personality injection, batch mode.

dorukardahan 2387

traktor

Extract all assets and content from websites including images, SVGs, fonts, videos, and page structure. Parallel agents with thorough scraping coverage. Triggers: "extract assets", "scrape website", "download site assets", "get all images from", or "/traktor url". Supports multiple URLs.

dorukardahan 2387