context-compression
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Install with Tessl CLI
npx tessl i github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill context-compressionOverall
score
61%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
37%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 description is heavily imbalanced - it excels at trigger terms but completely lacks any explanation of what the skill actually does. It reads as a 'Use when...' clause without the preceding capability description. Without knowing the concrete actions (e.g., 'Creates structured summaries of conversation history, extracts key decisions and context'), Claude cannot make informed decisions about whether this skill is appropriate for a given task.
Suggestions
Add concrete capability statements before the trigger clause, e.g., 'Creates structured summaries of conversation history, preserves key decisions and context while reducing token count.'
Specify the outputs or results the skill produces, e.g., 'Generates compacted context documents that maintain essential information for long-running sessions.'
Restructure to follow the pattern: [What it does] + [Use when...] rather than only listing triggers.
| 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 specific capabilities like 'summarizes conversations', 'extracts key points', or 'reduces context by X%'. | 1 / 3 |
Completeness | The description only answers 'when' (extensively) but completely fails to answer 'what does this do'. There is no explanation of the skill's actual capabilities or actions - it's entirely trigger-focused with no substance about functionality. | 1 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'compress context', 'summarize conversation history', 'reduce token usage', 'context compression', 'long-running agent sessions'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The trigger terms are fairly specific to context/token management, but without knowing what the skill actually does, there's potential overlap with general summarization skills. Terms like 'summarize conversation history' could conflict with other summarization tools. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid conceptual coverage of context compression strategies with good workflow clarity and decision frameworks. However, it lacks executable code examples (only markdown templates) and is verbose for a skill document, explaining concepts at length rather than providing lean, actionable guidance. The content would benefit from being split into a concise overview with detailed references.
Suggestions
Add executable Python/pseudocode for implementing compression triggers and summary merging logic rather than just conceptual steps
Move detailed sections (evaluation dimensions, probe types, compression ratio tables) to separate reference files and link from a leaner main skill
Trim explanatory passages that describe 'why' at length - Claude understands trade-offs; focus on 'what to do'
Add a concrete code example showing how to detect context utilization and trigger compression programmatically
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some explanatory content Claude likely knows (e.g., explaining what compression trades off, basic concepts). The tables and structured sections are efficient, but the overall length (~400 lines) could be tightened without losing actionable value. | 2 / 3 |
Actionability | Provides conceptual guidance and structured examples but lacks executable code. The markdown summary templates are useful but the 'Implementing Anchored Iterative Summarization' section gives steps without concrete implementation code. No copy-paste ready compression functions or scripts. | 2 / 3 |
Workflow Clarity | Clear multi-step workflows are present: the three-phase compression workflow, the anchored iterative summarization steps, and trigger strategies with explicit decision points. The 'When to Use Each Approach' section provides clear decision criteria. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is monolithic with extensive inline content that could be split. References to other skills and external resources exist, but detailed topics like evaluation dimensions and probe types could be in separate reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- 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.