Ready to supercharge your AI agents?

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

Get Started Free →

Hermes Skill — dictionarysearch (E3) — measured AI agent skill | DecimalAI

keith-leung/hermes-skill-dictionary-search-e3

SkillScore91Maintained

Bridge material for Layer-2 Hermes packaging.

by keith-leung

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

Automatic

Knowledge Management pack

decimalai skills pull keith-leung-hermes-skill-dictionary-search-e3

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/keith-leung-hermes-skill-dictionary-search-e3/SKILL.md

Raw file: /s/keith-leung-hermes-skill-dictionary-search-e3/SKILL.md ↗ · machine-readable summary at /s/keith-leung-hermes-skill-dictionary-search-e3.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 — +55% lift-20% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-42%	0%
case-03	✗→✓	▲ Improved	15%	0%
case-04	✗→✓	▲ Improved	3%	0%
case-06	✗→✓	▲ Improved	-11%	0%
case-07	✗→✓	▲ Improved	-27%	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

keith-leung / mcp-capability-plane

src/mcp_capability_plane/adapters/hermes_skill/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 1 file · scripts

Skill contents

scripts/

SKILL.md

Hermes Skill — dictionary_search (E3)

Bridge material for Layer-2 Hermes packaging. This skill shells out to an MCP client that talks to E's FastMCP server.

When to use

Use this skill when the agent needs to search a knowledge base via the capability-plane's dictionary-then-search MCP tool. The agent never calls HTTP directly; it invokes this skill, which calls the MCP client.

Prereqs

E's MCP server is running (stdio or streamable-http).
The MCP client library is available in the Hermes environment.

Invocation

bash
python scripts/call_mcp_tool.py \
  --server-cmd "python -m mcp_capability_plane.server.serve" \
  --tool dictionary_search \
  --params '{"query":"cozy cafe near downtown","domain":"dining","limit":5}'

Parameters

query: natural language search intent
domain: abstract domain hint (dining / travel / mobility / general)
limit: max results (1–50)

Output

JSON with data.items, data.total, data.domain, data.query.

Notes

This skill is framework-neutral: it calls MCP, not framework-specific tool code.
Layer-2 wires this into a Hermes install; E ships it as an adapter artifact.

Want to see if keith-leung/hermes-skill-dictionary-search-e3 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.