diff --git a/README.md b/README.md
index 2cf2886..a65a84b 100644
--- a/README.md
+++ b/README.md
@@ -206,6 +206,7 @@ Agent Skills are portable, [open standard](https://agentskills.io/home), version
 - [Playwright CLI](https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/SKILL.md) - Automate browser interactions, test web pages and work with Playwright tests.
 - [Frontend Design](https://github.com/anthropics/skills/blob/main/skills/frontend-design/SKILL.md) - Create distinctive, production-grade frontend interfaces with high design quality.
 - [Webapp Testing](https://github.com/anthropics/skills/blob/main/skills/webapp-testing/SKILL.md) - Toolkit for interacting with and testing local web applications using Playwright.
+- [Ontoly Software Graph](https://github.com/Code-and-Sorts/awesome-copilot-agents/tree/main/skills/ontoly-software-graph/SKILL.md) - Query deterministic Software Graph evidence for architecture, routes, dependencies, configuration, and impact analysis.
 
 ## MCPs
 
diff --git a/skills/ontoly-software-graph/SKILL.md b/skills/ontoly-software-graph/SKILL.md
new file mode 100644
index 0000000..e6aad9b
--- /dev/null
+++ b/skills/ontoly-software-graph/SKILL.md
@@ -0,0 +1,72 @@
+---
+name: ontoly-software-graph
+description: Use Ontoly's deterministic Software Graph and MCP server for architecture summaries, route tracing, dependency analysis, configuration usage, and impact analysis before broad source search.
+license: MIT
+compatibility: Requires Ontoly installed in the target repository or available through npx. Optional Ontoly MCP server support improves query ergonomics.
+metadata:
+  author: 0xsarwagya
+  version: "1.0"
+---
+
+# Ontoly Software Graph
+
+Use Ontoly as the evidence layer for repository-level software understanding.
+This skill teaches the workflow for using Ontoly; it does not replace Ontoly's
+compiler, graph, query engine, or MCP capabilities.
+
+## When to Use
+
+- Explain repository architecture, package structure, modules, services, or ownership.
+- Trace a route, request lifecycle, dependency path, call chain, or impact radius.
+- Find controllers, services, providers, configuration, environment variables, imports, exports, or graph diagnostics.
+- Compare deterministic graph evidence with source-file verification.
+
+Do not use this skill for ordinary single-file edits unless the user asks for
+repository-level context.
+
+## Workflow
+
+1. Check for an existing graph: `.ontoly/`, `SoftwareGraph.json`, `diagnostics.json`, or Ontoly docs.
+2. If the graph is missing and Ontoly is available, build it from the repository root:
+
+   ```bash
+   ontoly build .
+   ```
+
+   If the command is unavailable, try the documented package runner:
+
+   ```bash
+   npx ontoly build .
+   ```
+
+3. Inspect graph health before answering. Look for graph statistics,
+   diagnostics, semantic coverage, trust, and framework detection.
+4. Query Ontoly before broad source search. Prefer Ontoly MCP capabilities or
+   documented CLI queries for architecture, route tracing, dependency,
+   configuration, and impact questions.
+5. Cite graph evidence: node names, stable identifiers, relationship types,
+   diagnostics, source locations, and commands used.
+6. Search source files only when the graph is missing, stale, ambiguous, low
+   confidence, diagnostically incomplete, or when the user asks for source
+   verification.
+
+## Evidence Rules
+
+- Treat graph output as deterministic evidence, not model inference.
+- Do not invent confidence. Derive it from exact node matches, resolved edges,
+  provenance, diagnostics, validation status, and source locations.
+- Report `NOT_FOUND` when Ontoly has no matching graph concept.
+- Name ambiguity when multiple nodes or relationships may answer the question.
+- Separate measured graph results from source-file verification and assumptions.
+
+## Output Contract
+
+For repository-level answers, include:
+
+- Direct answer.
+- Evidence from Ontoly graph nodes, edges, diagnostics, source locations, or commands.
+- Confidence: high, medium, or low, with the graph-based reason.
+- Gaps: missing graph concepts, unresolved imports, stale graph, or fallback file searches.
+
+Keep the answer focused. Ontoly helps avoid broad file search; do not dump raw
+graph data unless the user asks for it.