essential-tools — Claude Code skill: pentesting tools and methodology
essential-tools — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that loads pentesting methodology, Burp Suite, Playwright, Nuclei, and reporting standards into the agent context.
MIT 202 installs ★ 632 updated 2026-07-29
npx skills add transilienceai/communitytools --skill essential-tools -a claude-codeWhat essential-tools does
The skill injects a set of reference files into the agent: Burp Suite techniques from reference/essential-skills*.md, Playwright MCP browser automation from reference/playwright-automation.md, a binary analysis quickstart from reference/binary-analysis-quickstart.md, and web attack methodology from reference/web-application-attacks.md.
For web and API engagements, the skill tells the agent to run command -v subfinder nuclei sslscan httpx and probe crt.sh before marking recon done. If a whole tool class is missing, the agent records it as an explicit limitation — the methodology prohibits substituting hand-rolled urllib.
A separate reporting component, formats/transilience-report-style/pentest-report.md, covers finding quality standards, compliance mapping, and a pre-delivery checklist. Without the actual tools in PATH, the skill's recon checks will consistently report gaps.
What it helps with
- check TLS posture of a target with sslscan from inside the agent
- run Nuclei templates against discovered subdomains
- capture screenshots and DOM snapshots of SPAs with Playwright as evidence
- produce a pentest report from the bundled template with compliance mapping
- run static analysis on a binary and extract strings
Example prompts for the agent
- Check whether subfinder, nuclei, sslscan, and httpx are available before starting recon on
${DOMAIN} - Use
reference/playwright-automation.mdto capture screenshots of all forms on the target - Build the final report from
pentest-report.mdand run through the pre-delivery checklist
How to install essential-tools
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill essential-tools -a claude-code2Manually: put the files in place
~/.claude/skills/essential-tools/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/essential-tools/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill essential-tools -a codex2Manually: put the files in place
.agents/skills/essential-tools/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill essential-tools -a cursor2Manually: put the files in place
.cursor/skills/essential-tools/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install transilienceai/communitytools skills/essential-tools2Manually: put the files in place
.github/skills/essential-tools/SKILL.md1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill essential-tools -a gemini-cli2Platform CLI
gemini skills install https://github.com/transilienceai/communitytools --path skills/essential-toolsManually: put the files in place
.devin/skills/essential-tools/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill essential-tools -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about essential-tools
How do I install essential-tools in Claude Code?
Run npx skills add transilienceai/communitytools --skill essential-tools -a claude-code. The skill will then be available at ~/.claude/skills/essential-tools/SKILL.md.
What does the essential-tools skill do?
It loads pentesting methodology into the agent: references for Burp Suite, Playwright, Nuclei, sslscan, binary analysis, and web attacks, plus a professional report template with a pre-delivery checklist and compliance mapping.
What happens if nuclei or sslscan are not installed?
The agent must record the missing tool class as an explicit limitation and cannot declare recon complete. The skill's methodology explicitly forbids substituting absent tools with hand-rolled HTTP code.
Source text
SKILL.md · MIT
---
name: essential-tools
description: Core pentesting tools and methodology - Burp Suite usage, Playwright automation, binary analysis, testing methodology, and professional reporting standards.
---
# Essential Tools
Core tools, methodology, and reporting standards for penetration testing.
## Components
| Component | Purpose |
|-----------|---------|
| **Burp Suite** | Proxy, scanner, intruder, repeater, sequencer |
| **Playwright** | Browser automation, evidence capture, SPA testing |
| **Binary Analysis** | Static analysis, reverse engineering, string extraction |
| **Nuclei** | Templated exposure & misconfiguration scanning |
| **sslscan** | TLS posture (protocols, ciphers, cert) |
| **Methodology** | PTES, OWASP WSTG, attack prioritization |
| **Reporting** | Professional report templates, PDF generation |
## Reference
- `reference/essential-skills*.md` - Burp Suite techniques and web security testing methodology
- `reference/playwright-automation.md` - Playwright MCP usage for pentesting
- `reference/binary-analysis-quickstart.md` - Static analysis for executable files and reverse engineering
- `reference/web-application-attacks.md` - Web application attack methodology
- `formats/transilience-report-style/pentest-report.md` - Finding quality standards, compliance mapping, and pre-delivery checklist
## Required-at-start tooling (web/API engagements)
Run an availability check before declaring recon complete:
`command -v subfinder nuclei sslscan httpx; curl -s "https://crt.sh/?q=%25.${DOMAIN}&output=json" | head -c1`
- Subdomain/CT enum: subfinder, certspotter, crt.sh
- TLS posture: sslscan
- Templated exposure: nuclei
If a tool-class is unavailable, record it as an explicit limitation — NEVER declare recon COMPLETE having skipped a whole class. Hand-rolled urllib is not a substitute (see skills/coordination/reference/principles.md 'Real tools before hand-rolled HTTP').
© transilienceai · MIT · transilienceai/communitytools