context-optimizer
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
76
Quality
70%
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-optimizer/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a reasonable 'Use when' clause with some practical triggers, but fails to specify what concrete actions the skill actually performs. The vague 'optimize' and 'management' language doesn't help Claude understand the skill's capabilities, and the trigger terms lean toward technical jargon rather than natural user language.
Suggestions
Replace vague terms with specific actions: e.g., 'Summarizes conversation history, prunes redundant context, compresses long exchanges to reduce token consumption.'
Add more natural trigger terms users would say: 'conversation too long', 'running out of space', 'memory full', 'hitting limits'
Clarify what 'context is degraded' means in practical terms to help distinguish this skill from general performance or debugging skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'optimize token usage' and 'context management' without listing concrete actions. It doesn't specify what actions are actually performed (e.g., summarize conversations, prune history, compress context). | 1 / 3 |
Completeness | Has a 'Use when...' clause which addresses the 'when' question with triggers like 'sessions feel slow' and 'running out of budget'. However, the 'what' is weak - it doesn't explain what concrete actions the skill performs to optimize tokens. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'slow', 'context', and 'budget' that users might mention, but 'token usage' and 'context management' are more technical jargon. Missing natural phrases like 'running out of space', 'conversation too long', 'memory issues'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on token/context optimization is somewhat specific, but terms like 'slow' and 'budget' could overlap with performance monitoring or cost management skills. The niche is identifiable but not sharply defined. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill file that maximizes information density while maintaining clarity. It provides concrete commands, specific thresholds, and actionable tables throughout. The workflow from diagnosis through optimization strategies to troubleshooting is logical and includes explicit checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables for quick scanning, no unnecessary explanations of what context windows or tokens are. Every section delivers actionable information without padding. | 3 / 3 |
Actionability | Provides specific commands (/context, /compact, /mcp, /resume), exact configuration JSON, concrete thresholds (70%, 90%), and clear examples of good vs bad prompts. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear diagnostic sequence (check → threshold → action), explicit phase-based budget planning with actions for each threshold, and a troubleshooting flow for degraded context with escalating fixes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from quick diagnosis to strategies to troubleshooting. Content is appropriately contained in a single file given the scope, with logical groupings and scannable tables. | 3 / 3 |
Total | 12 / 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
- rohitg00/pro-workflow
- Commit
57b813b
- 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.