Graphify

Graphify

Graphify is a CLI. The primary path for every request in this skill is a real graphify … command, not a slash command and not an improvised Python script.

Use this skill when the main question is "which graphify command answers this, over what scope, and what should we read next?"

The job is to:

1. classify the request into one graph packet,
2. choose one CLI mode,
3. scope the corpus before runtime or token cost explodes,
4. report artifacts and any degraded output truthfully,
5. route search-only, wiki-only, or project-memory work to the right neighboring skill.

Read references/cli-command-map.md for the full command surface with real flags. Read references/install-matrix.md before installing anything — especially for jeo / jeopi / gjc / opencode. Read references/mode-packets-and-route-outs.md for an unfamiliar request, and references/build-and-fallback-recipes.md when native extraction is weak.

CLI quickstart

pip install graphifyy                       # PyPI package is graphifyy; the binary is graphify
graphify --version

graphify scope                              # what would actually be graphed?
graphify update .                           # build -> .graphify/graph.json + .graphify/GRAPH_REPORT.md
graphify summary                            # hubs, communities, representative nodes
graphify query "where is auth enforced?" --budget 1500
graphify explain <node>                     # one node, plain language
graphify path <source> <target>             # shortest path between two nodes
graphify tree <node> --depth 2              # local neighbourhood
graphify export html                        # -> .graphify/graph.html

Three facts that keep answers truthful:

• `graphify build` does not exist. The build command is graphify update. graphify build --help silently falls through to the root help.
• State lives in `.graphify/`, not graphify-out/. graphify-out/ is the legacy layout; graphify migrate-state moves it. Every --graph <path> flag defaults to <cwd>/.graphify/graph.json.
• `graph.html` is not produced by `graphify update`. It comes from graphify export html.

When to use this skill

• The user explicitly wants GRAPH_REPORT.md, graph.json, graph.html, a codebase graph, or a persistent knowledge graph
• The request is about repo/corpus structure, relationship tracing, path queries, or architecture discovery that should survive the current session
• The corpus mixes code, docs, PDFs, notes, or screenshots and the user wants one durable structure layer
• The user wants to refresh, query, or explain an existing graph instead of re-reading raw files
• The user wants change-aware review context, affected execution flows, or risk scoring for a diff or PR
• The user wants Graphify installed into jeo, jeopi, gjc, opencode, Claude, Codex, Gemini, or another supported agent

When not to use this skill

• Only needs to find a symbol, file owner, config location, or reference chain → codebase-search
• Wants a persistent markdown knowledge base or filed research notes → llm-wiki
• Wants project/repo memory, manifests, or cross-agent handoff packets → opencontext
• Needs dependency-only JS/TS analysis or a quick repo tree diagram, not a durable graph
• Generic GraphRAG / text-KG architecture talk with no concrete Graphify ask

Install for jeo / jeopi / gjc / opencode

graphify install [platform] accepts exactly these ids: claude, codex, gemini, opencode, aider, copilot, claw, droid, trae, trae-cn, hermes, kimi, kiro, antigravity, antigravity-windows, vscode-copilot-chat, windows, vscode.

`jeo`, `jeopi` and `gjc` are not platform ids — graphify install jeo will fail the same way graphify install agents does (error: unknown platform). Per this repo's setup-all-skills-prompt.md, those three discover the shared ~/.agents/skills root natively, which the unconditional universal id populates. So:

# CLI for everyone
pip install graphifyy && graphify --version

# skill into the shared root that jeo, jeopi, gjc and sst/opencode all read
npx skills add https://github.com/akillness/jeo-skills --skill graphify -a universal
ls "${SKILLS_ROOT:-$HOME/.agents/skills}/graphify/SKILL.md"

# optional: opencode plugin + tool.execute.before hook (sst/opencode only)
graphify install opencode            # or: graphify install opencode --project

graphify install opencode --project writes .opencode/skills/graphify/SKILL.md, .opencode/plugins/graphify.js, .opencode/opencode.json, and an AGENTS.md section. graphify install claude --project writes .claude/skills/graphify/SKILL.md, .claude/settings.json PreToolUse hooks, and a CLAUDE.md section.

The archived Go opencode-ai/opencode TUI has no skill loader — graphify install opencode will not surface the skill there; bridge it as a command file or just use the CLI. Full detail: references/install-matrix.md.

Instructions

Step 1: Normalize the request into one packet

• repo-structure-packet — map a codebase or subsystem before editing
• relationship-trace-packet — answer a path/query/explain question from an existing graph
• mixed-corpus-memory-packet — build durable structure across code + docs + assets
• review-diff-packet — produce review context or affected flows for changed files
• install-packet — get Graphify into an agent for always-on use
• refresh-or-fallback-packet — update an existing graph, recover from weak output, or fall back

Start from the packet the user already has. Do not force every request through a feature tour.

Step 2: Pick one CLI mode

Name one primary mode. Mention at most one fallback.

Step 3: Scope before spending

Run graphify scope first on anything unfamiliar. Good defaults:

• repo root only when repo-wide architecture is genuinely the ask
• src/, app/, packages/<pkg>/, or one service directory for implementation work
• raw/, docs/, or a mixed research folder for corpus graphing
• an existing .graphify/ when the job is query/refresh rather than rebuild

Use --scope auto|committed|tracked|all and .graphifyignore instead of hoping runtime behaves. If the request is really locate/reference, route to codebase-search.

Step 4: Run the narrowest command set

Keep it to the commands the mode needs. Do not chain a build, an export, a wiki, and a watch loop when the user asked one question.

Step 5: Report degraded output honestly

Verified behavior: with no LLM API key configured, graphify update . still writes graph.json and GRAPH_REPORT.md, but prints:

[graphify label] warning: community labeling failed (...); using Community N placeholders.
[graphify describe] description generation failed (...); continuing without descriptions.

When that happens, say the graph is structurally complete but unlabeled/undescribed, and offer graphify update --fill-missing once a backend is configured. Never present placeholder