Ready to supercharge your AI agents?

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

Deep Search Enabler — measured AI agent skill | DecimalAI

stijnman/deep-search-enabler

SkillScore36Maintained

Enables thorough multi-source research beyond quick answers. Use for complex research or user says deep search, comprehensive research. Use when the use r needs this capability. Triggers: deep search, comprehensive research, rese arch thoroughly.

by stijnman

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

Automatic

Research pack

decimalai skills pull stijnman-deep-search-enabler

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-deep-search-enabler/SKILL.md

Raw file: /s/stijnman-deep-search-enabler/SKILL.md ↗ · machine-readable summary at /s/stijnman-deep-search-enabler.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 — +18% lift-13% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-40%	0%
case-06	✗→✓	▲ Improved	-6%	0%
case-10	✗→✓	▲ Improved	-27%	0%
case-14	✗→✓	▲ Improved	-14%	0%
case-12	✓→✓	＝ Same ✓	52%	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/deep-search-enabler/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Deep Search Enabler

When to Use

User says deep search or task matches this capability
User says comprehensive research or task matches this capability
User says research thoroughly or task matches this capability

Workflow

Decompose question into sub-queries.
Search web, docs, and workspace in parallel.
Synthesize with citations; flag conflicting sources.
Score confidence via agentic-uncertainty-quantifier.

Integrations

internet-enabler
web-scraper
insight-synthesizer
agentic-uncertainty-quantifier

Error Handling

| Failure | Response | |---------|----------| | No sources found | Broaden query; suggest alternate terms. |

Gotchas

Cite URLs for factual claims.

Example

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

Want to see if stijnman/deep-search-enabler 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.