jbvc/strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
55
69%
Does it follow best practices?
Impact
—
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 and distinguishes itself from auto-compaction approaches. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users would actually say. The specificity of actions is moderate—it describes the general approach but not the concrete steps involved.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions running out of context, context window limits, long conversations, or managing conversation memory.'
Include more natural trigger terms users would say, such as 'context window', 'token limit', 'long conversation', 'running out of memory', or 'conversation too long'.
List additional concrete actions beyond 'suggests manual compaction', such as 'identifies logical breakpoints in tasks, recommends when to compact, preserves key context across phases'.
| 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 steps are involved. | 2 / 3 |
Completeness | It describes what the skill does (suggests manual context compaction at logical intervals) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the contrast with auto-compaction, not explicitly stated. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'context compaction' and 'auto-compaction', but misses common user-facing variations such as 'context window', 'running out of context', 'memory management', 'conversation length', or 'token limit'. Users may not naturally say 'compaction'. | 2 / 3 |
Distinctiveness Conflict Risk | Context compaction is a fairly niche topic, and the description clearly distinguishes itself by focusing on manual compaction at logical intervals versus arbitrary auto-compaction. This is unlikely to conflict with other skills. | 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 skill provides solid actionable guidance with good configuration examples and a useful decision guide table for compaction timing. Its main weaknesses are moderate verbosity (explaining concepts Claude already understands like what survives compaction) and lack of validation/feedback mechanisms to confirm compaction was beneficial. The referenced script 'suggest-compact.js' is not included in the bundle, which undermines the skill's completeness.
Suggestions
Remove or significantly trim the 'What Survives Compaction' and 'Why Strategic Compaction?' sections — Claude already understands these concepts and they consume tokens without adding actionable value.
Add a brief validation step after compaction, such as checking that TodoWrite tasks or key files are still accessible, to create a feedback loop.
Include the referenced 'suggest-compact.js' script in the bundle or inline a minimal version so the skill is self-contained and verifiable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like 'Why Strategic Compaction?' which explains concepts Claude can infer, and the 'What Survives Compaction' table which is general Claude knowledge. The 'When to Activate' section also restates things Claude would understand from context. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready JSON configuration for hooks, a specific script path, environment variable configuration, and a clear decision guide table for when to compact. The `/compact` command with summary example is directly executable. | 3 / 3 |
Workflow Clarity | The decision guide table provides good sequencing for when to compact, and the 'How It Works' section explains the hook mechanism. However, there are no explicit validation steps — no way to verify compaction was effective, no feedback loop for checking if important context was lost, and the 'Best Practices' are guidelines rather than a clear workflow sequence. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's somewhat monolithic — the decision guide, survival table, and best practices could potentially be separate references. The 'Related' section references external links and other skills but the bundle has no supporting files despite referencing 'suggest-compact.js', making it impossible to verify the referenced script exists. | 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