ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
git clone --depth 1 https://github.com/mxyhi/ok-skills /tmp/ontoly-software-graph && cp -r /tmp/ontoly-software-graph/ontoly-software-graph ~/.claude/skills/ontoly-software-graphSKILL.md
# Ontoly Software Graph Use this skill when a coding agent needs graph-backed understanding of a TypeScript repository. Ontoly is the source of truth; the skill only teaches the workflow. ## When to Use - Explain repository architecture or package/module topology - Trace a route, controller, service, function, or dependency path - Find services, controllers, providers, modules, routes, configuration, or environment variables - Estimate impact before refactoring or deleting code - Audit unresolved imports, circular dependencies, dead code, semantic coverage, or graph quality - Produce onboarding, documentation, or architecture-review notes with deterministic evidence ## Workflow 1. Check whether an Ontoly graph already exists: `.ontoly/`, `SoftwareGraph.json`, `diagnostics.json`, validation reports, graph hash, or MCP setup. 2. If the graph is missing and local analysis is allowed, run: ```bash ontoly build . ``` 3. Inspect graph health before answering: diagnostics, graph hash, semantic coverage, trust or quality score, framework detection, and build timestamp. 4. Prefer Ontoly CLI or MCP capabilities over repository search for graph-answerable questions. 5. Search source files only when Ontoly cannot answer, the graph is stale or incomplete, or the user explicitly asks for file-level verification. 6. Always cite graph evidence: node IDs, edge types, file paths, source locations, diagnostics, framework analyzer output, and confidence. ## Capability Map - Architecture review: `ExplainArchitecture` - Dependency analysis: `FindDependencies` - Impact analysis: `ImpactAnalysis` - Request tracing: `TraceExecution` - Configuration analysis: `FindConfigurationUsage` - Framework analysis: `FrameworkReport` - Dead-code review: `FindDeadCode` ## Response Pattern Return the direct answer first, then evidence: ```text AuthController handles authentication. Evidence: - node: class:src/auth/auth.controller.ts:AuthController - route edges: HANDLES POST /login and POST /logout - dependency edges: USES AuthService and JwtService Confidence: high, because the graph has controller, route, and dependency edges with source locations. ``` ## Fallbacks - If the graph is missing, build it first when allowed. - If validation fails, report the graph issue and verify only the affected area with source search. - If several nodes match, show candidates with package/module context. - If nothing matches, return `NOT_FOUND` with the closest graph evidence instead of inventing an answer.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
Autonomous iteration loop: modify, verify, keep/discard against any metric
Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: `better-icons search <query>` to find icons, `better-icons get <id>` to get SVG. Also available as MCP server for AI agents.
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
>
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.