askill
context-graph

context-graphSafety 95Repository

Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, ChromaDB for cross-platform vector storage, and pattern extraction from history.

6 stars
1.2k downloads
Updated 1/2/2026

Package Files

Loading files...
SKILL.md

Context Graph

Living records of decision traces with semantic search. Find similar past decisions by meaning, not keywords.

Setup

MCP Server (recommended):

The context-graph MCP server provides the same functionality via tools:

  • context_store_trace - Store decisions with embeddings
  • context_query_traces - Semantic search
  • context_get_trace - Get by ID
  • context_update_outcome - Mark success/failure
  • context_list_traces - List with pagination
  • context_list_categories - Category breakdown

Configure in .claude/mcp.json:

{
  "mcpServers": {
    "context-graph": {
      "command": "uv",
      "args": ["--directory", "context-graph-mcp", "run", "python", "server.py"],
      "env": {"VOYAGE_API_KEY": "your_key_here"}
    }
  }
}

CLI Scripts (alternative):

# 1. Install dependencies
pip install voyageai chromadb

# 2. Set Voyage AI key
export VOYAGE_API_KEY="your_key_here"

# 3. Store/query traces
python scripts/store-trace.py "DECISION"
python scripts/query-traces.py "similar situation"

Instructions

  1. Store trace after decisions with category + outcome
  2. Query precedents when facing similar situations
  3. Update outcome to success/failure after validation

Quick Commands (MCP)

context_store_trace(decision="Chose FastAPI for async", category="framework")
context_query_traces(query="web framework choice", limit=5)
context_update_outcome(trace_id="trace_abc...", outcome="success")

Quick Commands (CLI)

# Store a decision trace
python scripts/store-trace.py "Chose FastAPI over Flask for async support" --category framework

# Find similar past decisions
python scripts/query-traces.py "web framework selection"

# Query by category
python scripts/query-traces.py "database choice" --category architecture --limit 3

# Output JSON for parsing
python scripts/query-traces.py "error handling" --json

Trace Schema

FieldDescription
idUnique trace identifier
timestampWhen stored
categoryGrouping (framework, api, error, etc.)
decisionWhat was decided (text)
outcomepending / success / failure
stateState machine state when decided
feature_idRelated feature (if any)
embedding1024-dim vector (Voyage AI)

Categories

  • framework - Tech stack choices
  • architecture - Design patterns, structure
  • api - Endpoint design, contracts
  • error - Failure modes, fixes
  • testing - Test strategies
  • deployment - Infra decisions

When to Use

SituationAction
Made a technical decisionStore trace with category
Facing similar problemQuery traces before deciding
Session completeQuery category → extract patterns
Repeating errorQuery traces for that error

Install

Download ZIP
Requires askill CLI v1.0+

AI Quality Score

83/100Analyzed 3/1/2026

Well-structured skill covering semantic search with Voyage AI and ChromaDB. Provides both MCP server and CLI alternatives with clear setup instructions, usage examples, schema definitions, and a when-to-use matrix. Technical content is accurate and comprehensive. Minor gap: assumes some prerequisites knowledge. Good discoverability through tags."

95
85
70
85
80

Metadata

Licenseunknown
Version-
Updated1/2/2026
Publisheringpoc

Tags

apidatabasellmtesting