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.
65
57%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-compression/SKILL.mdQuality
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 provides excellent trigger term coverage but completely omits what the skill actually does. It reads as a 'Use when...' clause without the preceding capability description, making it impossible for Claude to understand what actions this skill enables.
Suggestions
Add a capability statement at the beginning describing concrete actions (e.g., 'Compresses conversation history into structured summaries, extracts key decisions and context, and reduces token usage while preserving essential information.')
Restructure to follow the pattern: '[What it does]. Use when [triggers]' - currently only the second half exists.
Include specific outputs or artifacts the skill produces (e.g., 'generates compacted context documents', 'creates hierarchical summaries')
| 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 'compresses', 'summarizes', or 'reduces'. | 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 outputs. | 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 'summarize conversation history' could overlap with general summarization skills. The lack of capability description makes it harder to distinguish from related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, actionable skill with excellent workflow clarity and concrete guidance. The structured summary templates, decision tables, and probe-based evaluation framework provide immediately usable tools. The main weakness is length—the skill tries to be comprehensive in a single file rather than using progressive disclosure to split detailed method descriptions and examples into reference files.
Suggestions
Split detailed method descriptions (anchored iterative, opaque, regenerative) into a separate METHODS.md reference file, keeping only selection criteria in the main skill
Move the evaluation dimensions table and probe examples to the referenced evaluation-framework.md file to reduce main skill length
Tighten the 'Core Concepts' section by removing explanatory prose and using a comparison table instead
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary elaboration. Phrases like 'The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is...' could be tightened. Some sections explain concepts at length that could be more direct, though it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific markdown templates for structured summaries, clear decision tables for method selection, step-by-step implementation instructions for anchored iterative summarization, and detailed examples showing before/after compression with actual content. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The three-phase compression workflow has clear stages, the anchored iterative summarization has numbered steps, and the skill includes explicit guidance on when to trigger compression and how to evaluate quality with probes. | 3 / 3 |
Progressive Disclosure | The skill is quite long (~250 lines of substantive content) and could benefit from splitting detailed topics into separate reference files. While it has clear section headers and references external materials, the core content is monolithic. The evaluation framework reference is appropriately externalized, but method details and examples could be split out. | 2 / 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.
- Commit
3ab8c94
- 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.