strategic-compact
tessl i github:ysyecust/everything-claude-code --skill strategic-compactSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Validation
75%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 12 / 16 Passed | |
Implementation
57%This skill provides useful guidance on strategic compaction with a clear hook configuration, but falls short on actionability by not including the actual shell script code. The explanatory content about why strategic compaction matters could be trimmed since Claude understands context management concepts. The workflow could benefit from validation steps to confirm the hook is functioning.
Suggestions
Include the actual suggest-compact.sh script content or at minimum show its core logic, so the skill is fully executable without external dependencies
Trim the 'Why Strategic Compaction?' section to 2-3 bullet points - Claude understands context window limitations
Add a verification step: how to confirm the hook is working (e.g., expected output format, test command)
| 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 JSON configuration and mentions a shell script, but the actual script content is not shown. The hook setup is copy-paste ready, but the core functionality (suggest-compact.sh) is referenced without executable code. | 2 / 3 |
Workflow Clarity | The 'How It Works' section lists steps but lacks validation checkpoints. Best practices provide guidance on when to compact, but there's no explicit workflow for error handling or verification that the hook is working correctly. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the structure is appropriate with clear sections. References to external resources (Longform Guide, memory persistence hooks) are one level deep and clearly signaled. | 3 / 3 |
Total | 9 / 12 Passed |
Activation
17%This description identifies a specific technical capability but fails to make it accessible or actionable. It lacks natural trigger terms users would actually say, provides no explicit 'Use when' guidance, and uses insider jargon that won't help Claude match user requests to this skill.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the conversation is getting long, when approaching context limits, or when the user mentions memory, context, or conversation history'
Replace technical jargon with natural user language - instead of 'context compaction' and 'task phases', use terms like 'summarize conversation', 'free up memory', 'long conversation', or 'context window'
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', 'context window', or 'running out of space'. | 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 'logical intervals' is too vague to create clear boundaries. | 2 / 3 |
Total | 6 / 12 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.