home / skills / ken-cavanagh-glean / fieldkit

ken-cavanagh-glean/fieldkit

empower your claude.

15 skills
GitHub

Sponsored

tool-design

ken-cavanagh-glean/fieldkit

3
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.
evaluation

ken-cavanagh-glean/fieldkit

3
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
memory-systems

ken-cavanagh-glean/fieldkit

3
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
advanced-evaluation

ken-cavanagh-glean/fieldkit

3
This skill helps you build robust LLM evaluation systems by applying direct scoring, pairwise comparisons, rubrics, and bias mitigation.
project-development

ken-cavanagh-glean/fieldkit

3
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
multi-agent-patterns

ken-cavanagh-glean/fieldkit

3
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
context-compression

ken-cavanagh-glean/fieldkit

3
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
brief

ken-cavanagh-glean/fieldkit

3
This skill provides a pre-meeting briefing for any account by aggregating local checklists and real-time Glean data for actionable insights.
agent-spec-generator

ken-cavanagh-glean/fieldkit

3
This skill designs and generates complete Glean Agent specifications from discovery to JSON output for Agent Builder.
browser-automation

ken-cavanagh-glean/fieldkit

3
This skill guides effective browser automation with a dev-browser plugin to test local UI changes, debug issues, and automate repetitive tasks.
glean-mcp

ken-cavanagh-glean/fieldkit

3
This skill lets you query Glean to quickly access your company knowledge across apps, with cited sources for accounts, meetings, and documents.
context-degradation

ken-cavanagh-glean/fieldkit

3
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
context-optimization

ken-cavanagh-glean/fieldkit

3
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.