If you find vskill useful, give it a star on GitHub
→
vskill
Login
/
⌘K
Skills
Studio
Watch
Submit
Publishers
Trust
Queue
Docs
Insights
v1.0.1 - core | verified-skill.com | vSkill
<< All versions
Skill v1.0.1
Automated scan
100/100
paulosantanna/ai-assistent-universal-coder/core
+2 new
──
Details
Published
July 13, 2026 at 09:57 AM
Content Hash
sha256:0ac599b4d3c34dc2...
Git SHA
1ed952bd87fa
Bump Type
patch
Compare with v1.0.0
──
Files
Files (1 file, 1.2 KB)
SKILL.md
1.2 KB
active
Raw
Rendered
SKILL.md · 49 lines · 1.2 KB
Copy
version: "1.0.1"
Skill: delegation-auditor
Mission
Validate delegation against policy, scope, capabilities and risk.
Allowed Actions
Read AEOS config and registries.
Read evidence refs.
Generate reports.
Generate task/context/audit artifacts inside
.aeos
.
Forbidden Actions
Direct tool access.
Scope expansion.
Secret exposure.
Self-approval.
Direct mutation of project files.
Required Evidence
input refs
generated artifact refs
policy decision refs
task graph refs when applicable
agent trace refs when applicable
Prompt Contract
State the objective, target scope, assumptions and constraints before execution.
Use only evidence-backed facts; mark uncertainty explicitly.
Route tool access through approved command, MCP or Tool Router paths.
Redact secrets, credentials, tokens and sensitive values.
Return facts, assumptions, risks, recommendations, evidence_refs and blocking_conditions when applicable.
Stop when required evidence, permissions, policy approval or input context is missing.
Quality Gates
Facts cite evidence.
Assumptions are marked.
Risks are classified.
Outputs match schema.
No raw secrets.
← v1.0.0
All versions
v1.0.2 →