CtrlK
BlogDocsLog inGet started
Tessl Logo

context-manager

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

37

1.00x
Quality

3%

Does it follow best practices?

Impact

99%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/context-manager/SKILL.md

The canonical home for this skill is context-manager in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Evaluation results

98%

-1%

Coordinating Context Across a Multi-Agent Insurance Claims Pipeline

Multi-agent context handoff

Criteria
Without this skill
With this skill

Handoff protocol

100%

100%

Conflict resolution mechanism

100%

100%

Multi-tenant isolation

100%

100%

Staleness detection

100%

100%

Handoff schema artifact

100%

100%

Schema has agent metadata

100%

100%

Schema has version/timestamp

100%

100%

Schema has tenant scoping

100%

100%

Actionable design steps

100%

100%

Agent routing addressed

87%

75%

100%

Enterprise Contract Intelligence: Document Search System

RAG vector search design

Criteria
Without this skill
With this skill

Named vector DB

100%

100%

Hybrid search

100%

100%

Chunking with overlap

100%

100%

Multi-modal embeddings

100%

100%

Relevance scoring

100%

100%

Freshness/staleness detection

100%

100%

Cost optimization

100%

100%

Response approach steps

100%

100%

Actionable plan steps

100%

100%

Vector DB rationale

100%

100%

100%

Persistent Memory for a Long-Running AI Customer Support Agent

Hierarchical memory architecture

Criteria
Without this skill
With this skill

Episodic memory layer

100%

100%

Semantic memory layer

100%

100%

Working memory layer

100%

100%

Memory consolidation strategy

100%

100%

Forgetting strategy

100%

100%

Context compression

100%

100%

Token budget management

100%

100%

Memory versioning

100%

100%

Retrieval pseudocode layers

100%

100%

Actionable retrieval steps

100%

100%

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.