Ready to supercharge your AI agents?

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

Humanization Stealth Browsing — measured AI agent skill | DecimalAI

stijnman/humanization-stealth-browsing

SkillScore86Maintained

Browses web with human-like patterns to reduce bot detection. Use for scrapi ngfragile sites or user says stealth browse, human-like browsing. Use when t heuser needs this capability. Triggers: stealth browse, human-like browsing, avoid bot detection.

by stijnman

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

Automatic

Data Engineer pack

decimalai skills pull stijnman-humanization-stealth-browsing

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-humanization-stealth-browsing/SKILL.md

Raw file: /s/stijnman-humanization-stealth-browsing/SKILL.md ↗ · machine-readable summary at /s/stijnman-humanization-stealth-browsing.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 7d ago

Yes — +32% lift-26% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	115%	0%
case-03	✗→✓	▲ Improved	-26%	0%
case-07	✗→✓	▲ Improved	-27%	0%
case-13	✗→✓	▲ Improved	-47%	0%
case-15	✗→✓	▲ Improved	-42%	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 — 8/1/2026

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

stijnman / grok-custom-skills

.grok/skills/humanization-stealth-browsing/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Humanization Stealth Browsing

When to Use

User says stealth browse or task matches this capability
User says human-like browsing or task matches this capability
User says avoid bot detection or task matches this capability

Workflow

Set realistic delays and headers.
Navigate incrementally; avoid burst requests.
Rotate user-agent only when site blocks.
Respect robots.txt; stop on CAPTCHA and ask user.

Integrations

web-scraper
sandbox-internet-handler
humanization-stealth-browsing

Error Handling

| Failure | Response | |---------|----------| | CAPTCHA encountered | Stop; ask user to solve manually. |

Gotchas

Never bypass paywalls or auth without permission.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/humanization-stealth-browsing 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.