Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Frontend Tech-Stack Identification — measured AI agent skill | DecimalAI

transilienceai/techstack-frontend

NewSkillScoreMaintained

Frontend tech-stack identification — JavaScript frameworks, meta-frameworks, CSS frameworks, UI libraries, build tools, and CMS via DOM, JS globals, HTML, and bundle patterns.

researchby transilienceai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Security & AppSec pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/transilienceai-techstack-frontend/SKILL.md

decimalai skills pull transilienceai-techstack-frontend --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/transilienceai-techstack-frontend/SKILL.md https://app.decimal.ai/s/transilienceai-techstack-frontend/SKILL.md

Raw file: /s/transilienceai-techstack-frontend/SKILL.md ↗ · machine-readable summary at /s/transilienceai-techstack-frontend.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9h ago

Yes — +5% lift · at higher cost+72% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	73%	0%
case-02	✓→✓	＝ Same ✓	33%	0%
case-03	✓→✓	＝ Same ✓	29%	0%
case-04	✓→✓	＝ Same ✓	117%	0%
case-05	✓→✓	＝ Same ✓	147%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

transilienceai / communitytools

skills/techstack-identification/frontend/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Frontend Tech-Stack Identification

Scope

Identify client-side technologies: JavaScript frameworks (React, Vue, Angular, Svelte), meta-frameworks (Next.js, Nuxt, Gatsby, Remix), CSS frameworks (Tailwind, Bootstrap, Material UI), state management, build tools, CMS generators, and analytics SDKs from rendered HTML/JS.

Signals (input)

HTTP response bodies (HTML)
JavaScript global variables (window.*)
DOM attributes (data-*, ng-*, _ngcontent-*)
Script src URL patterns (/_next/, /wp-content/, etc.)
<meta name="generator"> tags
HTML comments
CSS class patterns
JSON-LD / structured data
Source map exposure

Inferences (output)

JS framework + version (e.g. React 18.2)
Meta-framework (implies host framework — Next.js → React)
CMS / static site generator (WordPress, Drupal, Hugo, Ghost)
CSS framework + UI library
Build tool (Webpack, Vite, Parcel)
Analytics / tracking SDKs (GA, Mixpanel, Hotjar, FullStory)
Source map exposure (security finding)

Techniques

See reference/patterns.md.

When to use

Phase 2/3 of a tech-stack OSINT engagement
Mapping client-side attack surface for XSS / DOM-based testing
Validating CMS/version for CVE matching
Identifying SaaS dependencies via third-party scripts

Want to see if transilienceai/techstack-frontend would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.