Ready to supercharge your AI agents?

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

Get Started Free →

Web Research — measured AI agent skill | DecimalAI

taracodlabs/web_research

NewSkillScoreMaintained

Deep web research with multi-source verification

researchby taracodlabs

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

Automatic

Research pack

decimalai skills pull taracodlabs-web-research

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/taracodlabs-web-research/SKILL.md

Raw file: /s/taracodlabs-web-research/SKILL.md ↗ · machine-readable summary at /s/taracodlabs-web-research.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 5h ago

—+17% tokens0% turns13% of whole cases pass with skill (3/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-18	✗→✓	▲ Improved	6%	0%
case-02	✓→✗	▼ Worse	-81%	0%
case-07	✓→✗	▼ Worse	-87%	0%
case-14	✓→✗	▼ Worse	-85%	0%
case-19	✓→✓	＝ Same ✓	13%	0%

Showing 5 of 23 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

taracodlabs / aiden

skills/web_research/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

Web Research

When performing web research:

Search broad first, then narrow by entity
Fetch actual page content, not just snippets
Cross-reference at least 2 sources before stating facts
Extract specific data points: names, numbers, dates, comparisons
Never state information you cannot verify from the fetched content
For comparisons: create structured tables with consistent attributes
Always note the source URL for key facts

Want to see if taracodlabs/web_research 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.