jbvc/strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
54
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
40%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 (manual context compaction) and is distinctive, but it lacks explicit trigger guidance ('Use when...') and misses natural user-facing keywords. It reads more like a feature rationale than a skill selection description.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the conversation is getting long, when context window limits are approaching, or when the user mentions running out of context or memory.'
Include more natural trigger terms users would say, such as 'context window', 'running out of context', 'long conversation', 'memory management', or 'conversation history'.
List additional concrete actions beyond suggesting compaction, such as 'identifies logical breakpoints in tasks, recommends when to compact, preserves key context across phases'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (context compaction) and describes the core action (suggesting manual context compaction at logical intervals), but it doesn't list multiple concrete actions—it's essentially one action with a rationale. | 2 / 3 |
Completeness | The description explains what the skill does (suggests manual context compaction at logical intervals) but lacks any explicit 'Use when...' clause or 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 | It 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', or 'conversation length'. Users may not naturally say 'compaction'. | 2 / 3 |
Distinctiveness Conflict Risk | Context compaction is a fairly niche topic, and the description's focus on manual compaction vs. auto-compaction at logical intervals makes it clearly distinguishable from other skills with minimal conflict risk. | 3 / 3 |
Total | 8 / 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-structured skill with strong actionability — the hook configuration, decision tables, and best practices give Claude concrete guidance on when and how to suggest compaction. The workflow clarity is excellent with the phase transition table serving as an effective decision framework. Minor weaknesses include some unnecessary explanatory content about why auto-compaction is suboptimal and the missing bundle file (suggest-compact.js) that the skill references.
Suggestions
Trim the 'Why Strategic Compaction?' section to 1-2 lines — Claude doesn't need a detailed explanation of auto-compaction's shortcomings.
Include the `suggest-compact.js` script in the bundle or inline its key logic, since the skill references it as the core mechanism but it's not provided.
| 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 Claude would already understand). The tables and decision guide add value but the introductory framing could be tighter. | 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/maybe guidance. The 'What Survives Compaction' table and best practices provide clear checkpoints (e.g., 'write before compacting'). The numbered hook mechanism steps are clear. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and tables, but everything is inline in a single file. The referenced script `suggest-compact.js` is not provided in the bundle, and the 'Related' links point to external URLs and other skills without clear navigation. For a skill of this length (~90 lines of content), some separation or bundle support would improve organization. | 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