jbvc/strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
69
69%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
57%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 identifies a clear niche around manual context compaction timing, which makes it distinctive. However, it lacks an explicit 'Use when...' trigger clause and could benefit from more natural user-facing keywords. The specificity of actions is moderate—it describes one core behavior but doesn't enumerate concrete sub-actions.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the conversation is getting long, when context window limits are approaching, or when transitioning between task phases.'
Include more natural trigger terms users would say, such as 'context window', 'running out of context', 'token limit', 'long conversation', or 'memory management'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (context compaction) and describes a specific action (suggesting manual context compaction at logical intervals), but doesn't list multiple concrete actions or elaborate on what specific capabilities are involved. | 2 / 3 |
Completeness | It describes what it does (suggests manual context compaction at logical intervals) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the phrase 'to preserve context through task phases rather than arbitrary auto-compaction.' | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'context compaction' and 'auto-compaction', but misses common user-facing variations like 'context window', 'running out of context', 'memory management', 'conversation length', or 'token limit' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Context compaction management is a fairly distinct niche that is unlikely to conflict with other skills. The specific focus on manual compaction timing versus auto-compaction creates a clear, narrow scope. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, practical skill that provides genuinely useful guidance for strategic context compaction with concrete configuration and a helpful decision framework. Its main weaknesses are some verbosity in explaining concepts Claude already understands (like why auto-compaction is suboptimal) and the lack of explicit verification steps after compaction to ensure critical context was preserved. The decision guide table is the standout element, providing real value-add that Claude wouldn't know independently.
Suggestions
Add a brief verification step after compaction (e.g., 'After compacting, verify key context by checking TodoWrite status and confirming you can reference the current plan') to improve workflow clarity.
Trim the 'Why Strategic Compaction?' section to 1-2 lines — Claude doesn't need a detailed explanation of why auto-compaction is suboptimal; just state the preference directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary explanation (e.g., 'Why Strategic Compaction?' section explains concepts Claude can infer, and the 'What Survives Compaction' table, while useful, partially restates things Claude already knows about its own architecture). The decision guide table is valuable and earns its tokens, but overall could be tightened. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready JSON configuration for hooks, a specific script path, configurable environment variables, and a clear decision table for when to compact. The best practices section gives specific, actionable guidance including the exact `/compact` command syntax with summary example. | 3 / 3 |
Workflow Clarity | The 'How It Works' section describes the hook mechanism clearly, and the decision guide table provides good phase-transition guidance. However, there's no explicit validation or feedback loop — the skill doesn't describe what happens if compaction goes wrong, how to verify important context was preserved, or what to do if critical context was lost. The 'Write before compacting' best practice hints at this but lacks a concrete verification step. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's somewhat monolithic — the decision guide and survival tables could potentially be in a separate reference file. The 'Related' section references external resources but they're external links rather than well-structured local file references. For a skill of this length (~80 lines of content), the inline approach is borderline acceptable. | 2 / 3 |
Total | 9 / 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