strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Install with Tessl CLI
npx tessl i github:ysyecust/everything-claude-code --skill strategic-compact60
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
17%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 identifies a specific technical capability but fails to make it accessible or actionable. It lacks explicit trigger guidance, uses jargon users wouldn't naturally say, and doesn't clearly explain when Claude should apply this skill. The description would benefit significantly from user-friendly language and a clear 'Use when...' clause.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when conversations are getting long, when approaching context limits, or when transitioning between major task phases'
Replace technical jargon with natural user terms: instead of 'context compaction', include terms like 'long conversation', 'memory management', 'context window', 'running out of space'
Specify concrete actions: what does 'suggests manual context compaction' actually involve? Does it summarize, archive, or prompt the user to do something specific?
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (context compaction) and describes the action (suggests manual compaction at logical intervals), but lacks concrete details about what specific actions are performed or what 'logical intervals' means in practice. | 2 / 3 |
Completeness | Describes what it does (suggests manual context compaction) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon like 'context compaction' and 'task phases' that users are unlikely to naturally say. Missing common terms users might use like 'memory', 'conversation length', 'running out of space', or 'context window'. | 1 / 3 |
Distinctiveness Conflict Risk | The concept of 'context compaction' is somewhat specific, but without clear triggers it could overlap with other memory management or conversation optimization skills. The phrase 'task phases' is vague enough to cause confusion. | 2 / 3 |
Total | 6 / 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 skill provides actionable hook configuration and clear best practices for strategic compaction timing. The main weakness is some unnecessary explanation of why auto-compaction is problematic (Claude understands this) and missing verification steps for confirming the hook setup works correctly.
Suggestions
Remove or significantly condense the 'Why Strategic Compaction?' section - Claude understands the tradeoffs of auto vs manual compaction
Add a verification step after hook setup, e.g., 'Test by running 50+ tool calls and confirming the suggestion appears'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some explanatory sections (like 'Why Strategic Compaction?') that explain concepts Claude likely understands. The comparison between auto vs strategic compaction could be more concise. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready JSON configuration for hooks, specific environment variable settings, and clear script behavior description. The setup instructions are immediately executable. | 3 / 3 |
Workflow Clarity | The 'How It Works' section explains the script behavior, and 'Best Practices' provides guidance on when to compact. However, there's no explicit validation step or feedback loop for verifying the hook is working correctly after setup. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~50 lines), the content is well-organized with clear sections. References to external resources (Longform Guide, Memory persistence hooks) are appropriately signaled and one level deep. | 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.
- 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.