agentleFS
iPythoningiPythoning/b2b-sdr-agent-template/skills/graphify/SKILL.md

graphify

Skill191 starsChanged 5 months agoMITView on GitHub

Knowledge graph engine for B2B sales intelligence. Builds queryable graphs from product catalogs, customer conversations, and market research. Powered by graphify.

  • Installs packages

125 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use remotion-maps, remotion-saas and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    remotion-maps

    Remotion Map animation knowledge

    Also in 4 projects that use this

  • OpenAISkill

    remotion-saas

    Build an app with Remotion

    Also in 4 projects that use this

  • royaluniondesign-sysSkill

    deployment-patterns

    Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

    Also in 4 projects that use this

  • mstuder-slalomSkill

    django-verification

    Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

    Also in 3 projects that use this

  • ttmouseSkill

    prompt-master

    提示词主控 - 智能选择合适的领域skill并生成提示词,支持自动领域分类和调度

    Also in 4 projects that use this

  • seikaikyoSkill

    doubt-driven-development

    對非平凡決策啟動新鮮 context 對抗審查(找碴不背書),在修正還便宜的時候抓出錯誤方向。適用:高風險改動(production、資安敏感邏輯、不可逆操作)、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 123 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When to use: Before quotation, during BANT qualification, when customer asks about related products.

    line 32
  2. Distinctive:

    After building a graph, query it for specific sales intelligence:

    line 108

“Common” is measured: kept by at least 6 in 10 of the 123 edited versions of this file we could read. “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

Graphify — Sales Intelligence Knowledge Graph

Build knowledge graphs from your product catalog, customer conversations, and market research to surface hidden connections, cross-sell opportunities, and competitive insights.

Based on graphify — adapted for B2B SDR context.

Triggers

  • Manual: "Build a knowledge graph of our products"
  • Manual: "Map customer relationships"
  • Manual: "Analyze competitive landscape"
  • Cron (optional): Weekly rebuild after lead-discovery updates

Prerequisites

# Ensure graphify is installed
python3 -c "import graphify" 2>/dev/null || pip install graphifyy -q --break-system-packages 2>&1 | tail -3

Use Cases

1. Product Catalog Graph

Build a graph from product-kb/ to understand product relationships, shared certifications, overlapping target markets, and cross-sell paths.

When to use: Before quotation, during BANT qualification, when customer asks about related products.

python3 -c "
import json
from graphify.extract import collect_files, extract
from graphify.build import build
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
from pathlib import Path

# Extract from product catalog
files = collect_files(Path('product-kb'))
ast_result = extract(files)

# Build and analyze
G = build([ast_result])
communities, labels = cluster(G)
cohesion = score_all(G, communities)

gods = god_nodes(G, top_n=5)
surprises = surprising_connections(G, communities, top_n=5)

print('=== Core Products (God Nodes) ===')
for g in gods:
    print(f'  {g[\"label\"]} — {g[\"edges\"]} connections')

print('=== Surprising Connections ===')
for s in surprises:
    print(f'  {s[\"source\"]} ↔ {s[\"target\"]} [{s[\"confidence\"]}]')
"

Sales actions from graph insights:

  • God nodes = your anchor products → lead with these in cold outreach
  • Surprising connections = non-obvious cross-sell paths → "customers who buy X often need Y"
  • Communities = product families → bundle pricing opportunities

2. Customer Intelligence Graph

Build a graph from conversation histories and CRM data to map customer relationships, identify buying patterns, and find warm introduction paths.

Input sources:

  • ChromaDB conversation history (chroma:recall)
  • CRM records (Google Sheets)
  • Supermemory research notes (memory:search)

What to extract (semantic, not AST):

  • Companies → employees (decision makers, influencers)
  • Companies → products they bought or inquired about
  • Companies → companies (same industry, same region, competitors)
  • People → people (referrals, shared contacts)
  • Deals → products, timelines, objections

Sales actions from graph insights:

  • Cluster customers by behavior → tailor nurture campaigns per cluster
  • Find bridge nodes (customers who connect segments) → referral candidates
  • Detect isolated nodes (customers with no follow-up) → stalled lead recovery

3. Market Research Graph

Build a graph from lead-discovery research, competitor intel, and market signals stored in Supermemory.

What to extract:

  • Competitors → products, pricing, markets
  • Markets → trends, regulations, trade shows
  • Customers → competitors they also buy from
  • Regions → seasonal demand patterns

Sales actions from graph insights:

  • Surprising connections between markets → expansion opportunities
  • Competitor clusters → differentiation strategy
  • Market god nodes → priority regions for lead-discovery rotation

Graph Query (runtime)

After building a graph, query it for specific sales intelligence:

# BFS — broad context around a topic
python3 -m graphify query "hydraulic excavator certification" --budget 1500

# DFS — trace a specific relationship chain
python3 -m graphify query "Dubai customer fleet" --dfs --budget 1000

Use before:

  • Responding to product questions → query product graph for specs and relationships
  • Preparing quotations → find cross-sell opportunities in graph
  • Cold outreach → understand prospect's market context from research graph

Graph Export

python3 -c "
from graphify.export import to_json, to_html
from graphify.build import build_from_json
from pathlib import Path
import json

data = json.loads(Path('graphify-out/graph.json').read_text())
G = build_from_json(data)

# Interactive HTML for owner dashboard
to_html(G, Path('graphify-out/graph.html'))

# JSON for programmatic access
to_json(G, Path('graphify-out/graph.json'))
"
  • HTML: Interactive vis.js graph — share with owner for pipeline visibility
  • JSON: Machine-readable — feed into reporting or CRM enrichment
  • Report: graphify-out/GRAPH_REPORT.md — god nodes, communities, knowledge gaps

Output Format (report to owner)

Product Knowledge Graph:
- X nodes · Y edges · Z communities
- Core products: [god nodes list]
- Cross-sell opportunities: [surprising connections]
- Knowledge gaps: [isolated products with missing specs]

Recommendation: Update product-kb for [gap products] to improve graph coverage.

Integration with Other Skills

SkillHow Graphify Helps
lead-discoveryQuery market graph before searching → better targeting
quotation-generatorQuery product graph → include related products in quote
chroma-memoryFeed conversation data → build customer intelligence graph
supermemoryFeed research notes → build market research graph
sdr-humanizerGraph context → more relevant, personalized conversations

Rebuild Strategy

  • Product graph: Rebuild when product-kb/ changes (new products, updated specs)
  • Customer graph: Rebuild weekly from ChromaDB + CRM snapshots
  • Market graph: Rebuild after lead-discovery runs (daily 10:00 output)

Store graphs in graphify-out/ — survives across sessions, queryable anytime.

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.