Ready to supercharge your AI agents?

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

AGENTS-BRIDGE (Deutsch) — measured AI agent skill | DecimalAI

ellmos-ai/agents-bridge

SkillScore91Maintained

Provider- and user-neutral bridge for agent, CLI, and IDE boot rules. It discovers known bootstrap surfaces, requires the user to select one or more ordered truth sources, and renders small loaders without duplicating rules.

by ellmos-ai

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

Automatic

AI Engineer pack

decimalai skills pull ellmos-ai-agents-bridge

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ellmos-ai-agents-bridge/SKILL.md

Raw file: /s/ellmos-ai-agents-bridge/SKILL.md ↗ · machine-readable summary at /s/ellmos-ai-agents-bridge.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 46h ago

Yes — +73% lift-55% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-21	✗→✓	▲ Improved	-67%	0%
case-03	✗→✓	▲ Improved	-78%	0%
case-04	✗→✓	▲ Improved	-59%	0%
case-05	✗→✓	▲ Improved	-34%	0%
case-06	✗→✓	▲ Improved	-55%	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 — 8/2/2026

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

ellmos-ai / skills

skills/infrastructure/agents-bridge/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 9 files · scripts

Skill contents

scripts/

references/

assets/

SKILL.md

> Deutsch — Offizielle Deutsch-Version / Documento Oficial en Deutsch.

AGENTS-BRIDGE (Deutsch)

Use this skill to connect an agent or IDE to explicitly selected rule files. No provider, filename, host, or cloud directory is implicitly canonical.

Workflow & Vorgehen

Read all local instructions that govern the source and target paths.
Run python scripts/bridge.py discover and optionally pass --project.
Ask the user to select the ordered truth sources and the target. An empty

selection authorizes no write.

Prefer a redirect or ordered loader. Use a generated copy only when the

target cannot load references, and record provenance plus drift checks.

Preview with:

text python scripts/bridge.py render --truth <path> --target-kind generic

Create or change the target only after reviewing the preview.
Prove that the target agent actually read every selected source.

See references/agent-conventions.md, references/truth-topologies.md, and references/inventory-contract.md.

agent-config-sync manages broader configuration topologies. agents-bridge is limited to boot and rule access. Runtime partner bridges and schedulers are separate components.

Want to see if ellmos-ai/agents-bridge 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.