agentleFS
Dianel555Dianel555/DSkills/skills/ontoly/SKILL.md

ontoly

Skill65 starsChanged 2 months agoMITView on GitHub

Deterministic Software Graph analysis via Ontoly CLI and MCP. Use when: (1) Codebase architecture, dependency, route, service, module, configuration, or impact questions need graph evidence, (2) A repository should be analyzed before source search, (3) You need a persistent SoftwareGraph.json for validation, MCP, or agent workflows. Triggers: "build software graph", "trace route", "impact analysis", "architecture summary", "dependency graph", "what uses this", "Ontoly".

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the project already has Ontoly installed, prefer the repository-local package manager command, such as pnpm ontoly, npm exec ontoly, or …

    line 18
  2. Very specific:

    Check for an existing Ontoly graph, usually .ontoly/SoftwareGraph.json.

    line 59
  3. Distinctive:

    If missing or stale, run:

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ontoly - Software Graph Analysis

Build and query deterministic Software Graphs for TypeScript repositories. Ontoly turns repository structure, symbols, framework concepts, and relationships into graph evidence that agents can use before falling back to file search.

Prerequisites

# Recommended: run through npx so the current published CLI is used
npx ontoly --help

If the project already has Ontoly installed, prefer the repository-local package manager command, such as pnpm ontoly, npm exec ontoly, or npx ontoly.

Quick Start

# From the repository root
npx ontoly build .

# Start MCP for agent integrations
npx ontoly mcp

# Inspect available commands
npx ontoly --help

Expected outputs may include .ontoly/SoftwareGraph.json, diagnostics, graph statistics, indexes, and metadata depending on the Ontoly version and repository configuration.

Tool Routing Policy

Prefer Ontoly Before File Search

TaskAvoidUse Ontoly
Architecture summaryReading every README/source folderBuild graph, inspect graph statistics and architecture report
Impact analysisGrep for identifier textQuery dependencies, callers, callees, and related nodes
Request flowManually follow controller/service filesTrace route/controller/service relationships
Configuration auditSearch .env names onlyQuery configuration and environment-variable nodes
Dead code reviewGuess from unused exportsUse graph diagnostics and unreachable/dead-code evidence

When to Use Built-in Tools

  • Ontoly is not installed and cannot be run in the environment
  • The graph reports low coverage or missing framework support
  • The question depends on source comments, prose documentation, generated artifacts, or runtime data not represented in the graph
  • You need to verify a suspected graph gap

Workflow

Phase 1: Graph Readiness

  1. Locate the repository root.
  2. Check for an existing Ontoly graph, usually .ontoly/SoftwareGraph.json.
  3. If missing or stale, run:
npx ontoly build .
  1. Review diagnostics, graph hash, node count, edge count, framework detection, and coverage/trust signals before answering.

Phase 2: Query

Choose the narrowest query or capability for the question:

Question TypeQuery Direction
"What owns auth?"Services, controllers, modules, packages
"What handles POST /login?"Routes, handlers, request lifecycle
"What breaks if I remove X?"Impact analysis, consumers, dependency traversal
"Where is DATABASE_URL used?"Configuration and environment-variable usage
"Which modules depend on this package?"Package/module dependency traversal
"Why is this service reachable?"Containment, registration, route, and dependency edges

Phase 3: Answer with Evidence

Always include:

  • direct answer
  • relevant node IDs and node kinds
  • relationship names and directions
  • source locations when present
  • diagnostics or graph-quality warnings
  • confidence derived from graph evidence

Output Format

## Answer
{Concise answer.}

## Graph Evidence
| Type | Evidence |
|------|----------|
| Node | `{nodeId}` ({kind}) |
| Edge | `{source} --RELATIONSHIP--> {target}` |
| Location | `{file}:{line}` |
| Diagnostic | `{code}: {message}` |

## Confidence
{High/Medium/Low} because {specific graph evidence, coverage, diagnostics}.

## Fallbacks
{Any source search used, or graph gaps that prevented a full answer.}

Common Commands

# Build a graph for the current repository
npx ontoly build .

# Build a graph for a specific repository
npx ontoly build /path/to/repo

# Start the MCP server
npx ontoly mcp

# Validate skills if using Ontoly Agent Skills
npx ontoly skills validate

Error Handling

ErrorRecovery
ontoly command not foundUse npx ontoly --help or install Ontoly as a dev dependency
Build failsReport command, exit code, diagnostics, and smallest blocker
No graph outputConfirm repository root, package manager, permissions, and Ontoly config
Ambiguous nodeList candidate node IDs/kinds/locations before answering
Low graph coverageAnswer only evidenced parts and label missing coverage

Anti-Patterns

ProhibitedCorrect
Search files first for architecture questionsBuild/query Ontoly graph first
Claim certainty without graph evidenceInclude nodes, edges, diagnostics, and confidence
Hide graph gaps with manual inferenceState missing node/edge/framework coverage
Compare raw node names across toolsCompare semantic concepts and relationship evidence

Limitations

  • Requires the Ontoly CLI package or repository-local installation
  • Graph completeness depends on the language and framework analyzers available in the installed Ontoly version
  • Runtime-only behavior may require additional source or runtime evidence

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.