context-engineering
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques, compression strategies, memory architectures, multi-agent patterns, evaluation, tool design, and project development.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that follows best practices. It uses third person voice, provides specific concrete actions, includes an explicit 'Use when...' clause with multiple trigger scenarios, and covers a distinct specialized domain. The description effectively communicates both capabilities and usage triggers while maintaining clear differentiation from other potential skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'designing agent architectures', 'debugging context failures', 'optimizing token usage', 'implementing memory systems', 'building multi-agent coordination', 'evaluating agent performance', 'developing LLM-powered pipelines'. Also enumerates specific topics covered. | 3 / 3 |
Completeness | Clearly answers both what ('Master context engineering for AI agent systems') and when ('Use when designing agent architectures, debugging context failures...') with explicit 'Use when' clause containing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'agent', 'context', 'token usage', 'memory systems', 'multi-agent', 'LLM', 'pipelines', 'optimization', 'compression'. Good coverage of terms someone working on AI agents would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on 'context engineering for AI agent systems' - a specialized domain. The combination of agent-specific terminology (context failures, token usage, multi-agent coordination) creates distinct triggers unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly concise skill that effectively serves as an overview document with clear pointers to detailed references. Its main weakness is the lack of concrete, executable examples - the guidance is specific in terms of metrics and principles but doesn't provide copy-paste ready implementations or explicit validation workflows for the complex operations it describes.
Suggestions
Add a concrete code example demonstrating at least one technique (e.g., a token counting snippet or a simple compaction trigger implementation)
Include an explicit workflow with validation checkpoints for a common task like 'debugging context degradation' or 'implementing compaction triggers'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every section uses bullet points and terse phrasing. No unnecessary explanations of concepts Claude already knows. Metrics are specific numbers, not verbose descriptions. | 3 / 3 |
Actionability | Provides concrete guidelines and specific metrics (70% threshold, 50-70% reduction targets), but lacks executable code examples or copy-paste ready commands. The guidance is specific but abstract rather than demonstrable. | 2 / 3 |
Workflow Clarity | The Four-Bucket Strategy provides a clear conceptual sequence, and guidelines are numbered, but there are no explicit validation checkpoints or feedback loops for the multi-step processes involved in context engineering. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and well-signaled one-level-deep references to 8 detailed reference files. Clear navigation with descriptive labels for each reference file. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- siviter-xyz/dot-agent
- Commit
3376255
- Reviewed
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.