agent tooling by ellmos-ai
Semantic Persona Routing ellmos-ai/semantic-persona-routing
Builds and uses a provider-neutral semantic routing graph from personas, coordinating roles, experts and live skill endpoints. Use when an LLM should route a request through boss-role to expert to skill, extract a portable persona router from an existing agent system, combine a semantic domain map with a lexical skill registry, or expose missing role-to-skill ports instead of silently falling back. Triggers on semantic persona routing, persona umbrella, role router, boss-agent expert skill routi
Install linked skill Links this skill to your agents and keeps it current with the author's updates.
Fork editable copy Install locally · CLI or SKILL.md 1 · One-time — install the CLI (
docs ↗ )
$ pip install decimalaiCopy
2 · Get the skill — writes .claude/skills/ellmos-ai-semantic-persona-routing/SKILL.md
$ decimalai skills pull ellmos-ai-semantic-persona-routing --out .claude/skills/Copy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/ellmos-ai-semantic-persona-routing/SKILL.md https://app.decimal.ai/s/ellmos-ai-semantic-persona-routing/SKILL.mdCopy
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 2 Ratings 0
Benchmark snapshot Same tasks, with and without this skill.
View full report → Model gemini-3.6-flashMeasured 8/11/2026 v2
Pass-rate lift +57 pp percentage-point change
Pass rate with skill 87% 30% without skill
Tokens +16% vs. without skill
Agent turns 0% vs. without skill Usage All-time distinct users and times used, across every version.
View activity → Read the skill SKILL.md and 3 supporting files · includes scripts
Open contents → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/9/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported ellmos-ai / skills
skills/infrastructure/semantic-persona-routing/SKILL.md
View on GitHub ↗ License MITImported 8/24/2026Version v2Bundled 3 files · scripts