context-optimization

tessl i github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill context-optimization

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

58%

Overall

Validation — 88%

Implementation — 57%

Activation — 37%

SKILL.md

Review

Evals

Validation

88%

Warnings & errors only

Criteria	Description	Result
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning

	Total	14 / 16 Passed

Implementation

57%

This skill provides a comprehensive conceptual overview of context optimization but falls short on actionability. It explains what to do at a high level but lacks the concrete, executable code and specific implementation details that would make it immediately useful. The structure and organization are strong, but the content would benefit from less conceptual explanation and more practical, copy-paste ready examples.

Suggestions

Replace pseudocode examples with complete, executable implementations including actual threshold values, data structures, and error handling

Remove conceptual explanations like 'What is Compaction' and 'Understanding KV-Cache' - Claude knows these concepts; focus on the specific implementation patterns

Add explicit validation steps to the optimization workflow (e.g., 'After compaction, verify quality with: [specific test]')

Include concrete metrics and thresholds (e.g., specific token counts, quality measurement methods) rather than vague percentages like '50-70% reduction'

Dimension	Reasoning	Score
Conciseness	The skill contains some unnecessary explanation of concepts Claude likely knows (e.g., explaining what KV-cache is, what compaction means conceptually). While not egregiously verbose, sections like 'What is Compaction' and 'The Observation Problem' could be tightened significantly.	2 / 3
Actionability	Code examples are minimal and incomplete pseudocode rather than executable implementations. The guidance is largely conceptual ('apply compaction', 'monitor signals') without concrete, copy-paste ready implementations or specific thresholds/configurations.	2 / 3
Workflow Clarity	The 'Optimization Decision Framework' provides some sequencing, but lacks explicit validation checkpoints. For operations that could degrade context quality, there's no feedback loop for verifying optimization effectiveness before proceeding.	2 / 3
Progressive Disclosure	Good structure with clear sections, appropriate references to related skills and external resources, and a single-level reference to detailed technical documentation. Content is well-organized with logical progression from concepts to practical guidance.	3 / 3
	Total	9 / 12 Passed

Activation

37%

This description is fundamentally incomplete - it functions as a trigger list rather than a skill description. While it excels at providing natural keywords users might say, it completely fails to explain what the skill actually does. A user or Claude cannot make an informed decision about using this skill because the capabilities are entirely undefined.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Analyzes conversation context to identify redundant information, implements observation masking strategies, and restructures prompts for optimal KV-cache utilization.'

Restructure to lead with capabilities before trigger conditions: '[What it does]. Use when [trigger conditions].'

Specify the outputs or results users can expect, such as 'Provides recommendations for reducing token usage by X%' or 'Generates optimized context partitioning strategies.'

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions - it only lists trigger phrases without explaining what the skill actually does. There are no verbs describing capabilities like 'extract', 'analyze', or 'generate'.	1 / 3
Completeness	The description only addresses 'when' (trigger conditions) but completely omits 'what' - there is no explanation of what actions or capabilities this skill provides. The 'what' component is entirely missing.	1 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'optimize context', 'reduce token costs', 'improve context efficiency', 'context limits', 'context budgeting'. These are realistic phrases users would naturally use.	3 / 3
Distinctiveness Conflict Risk	The trigger terms are fairly specific to context optimization domain, but without knowing what the skill actually does, it's unclear how it would differentiate from other potential context-related skills. The niche is somewhat defined but incomplete.	2 / 3
	Total	7 / 12 Passed

Reviewed

16 days ago

Table of Contents

Validation Implementation Activation

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.