jbvc/strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
52
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
32%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 communicates a reasonably specific concept—manual context compaction at logical intervals—but lacks an explicit 'Use when...' clause, which is critical for skill selection. It also misses common user-facing trigger terms that would help Claude match this skill to natural user requests about running out of context or managing long conversations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the conversation is getting long, context is running low, or the user mentions context limits, memory, or compaction.'
Include more natural trigger terms users would say, such as 'context window', 'running out of context', 'long conversation', 'context limit', 'memory management'.
List more specific concrete actions, e.g., 'Identifies logical breakpoints in tasks, recommends when to compact context, preserves key information across compaction boundaries.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (context compaction) and describes the core action (suggests manual context compaction at logical intervals), but doesn't list multiple concrete actions or elaborate on what specific steps are involved. | 2 / 3 |
Completeness | Describes what it does (suggests manual context compaction at logical intervals) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'when' is entirely missing, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'context compaction', 'auto-compaction', and 'task phases', but misses common user-facing variations like 'context window', 'running out of context', 'memory management', 'long conversation', or 'context limit'. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of 'context compaction' is fairly niche, but the description could overlap with other context management or conversation management skills. The mention of 'manual' vs 'auto-compaction' adds some distinction but isn't strongly differentiated. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with strong actionability and workflow clarity. The decision guide table and compaction survival table are particularly valuable, providing concrete guidance for when and how to compact. Minor weaknesses include some verbosity in the motivational sections and all content being inline rather than leveraging supporting files.
Suggestions
Trim the 'Why Strategic Compaction?' section to 2-3 bullet points — Claude doesn't need to be convinced, just instructed.
Consider extracting the decision guide and survival tables into a separate reference file to keep the main SKILL.md as a concise overview with hook setup.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., 'Why Strategic Compaction?' section explains auto-compaction behavior that could be trimmed). The tables and decision guide add value but the overall content could be tightened by ~20%. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready JSON configuration for hooks, a specific script path, environment variable configuration, and actionable decision tables. The `/compact` command with summary example is directly executable. | 3 / 3 |
Workflow Clarity | The decision guide table clearly sequences when to compact across phase transitions with explicit yes/no guidance. The 'What Survives Compaction' table serves as a validation checkpoint, and best practices include clear ordering (write before compacting, don't compact mid-implementation). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but everything is inline in a single file. The 'Related' section references external resources but no bundle files exist to support progressive disclosure. The decision guide and survival tables could potentially be separate reference files for a cleaner overview. | 2 / 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