strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete config, executable hooks, and a clear decision table, giving strong actionability and workflow clarity. It is somewhat over-long with general token-management content that could be split out, and it uses no external references for progressive disclosure.

Suggestions

Move the 'Token Optimization Patterns' section into a separate reference file (e.g., references/token-optimization.md) and link to it from the body to improve progressive disclosure and reduce inline bulk.

Trim explanatory prose such as the 'Tool count alone is a weak proxy' paragraph to the essential rationale, since the numbered mechanism already conveys the point.

Tighten or remove the general 'Context Composition Awareness' and 'Duplicate Instruction Detection' subsections, which overlap with knowledge Claude already has about context management.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete config and thresholds, but includes explanatory prose ('Tool count alone is a weak proxy...') and a 'Token Optimization Patterns' section that drifts into general token-management advice beyond the skill's core mechanism.	2 / 3
Actionability	Provides executable hook JSON, named script (suggest-compact.js), concrete env vars with defaults, and specific thresholds (160k/250k/60k) — copy-paste ready.	3 / 3
Workflow Clarity	A clear 'Compaction Decision Guide' table with phase transitions and yes/no/maybe rationale plus sequenced 'Best Practices' gives explicit decision checkpoints, and the two-signal mechanism is well sequenced.	3 / 3
Progressive Disclosure	No bundle files exist and the body is a single monolithic file with all content inline, including a 'Token Optimization Patterns' section that could be split into a separate reference.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 is third-person and states a clear purpose, but it relies on technical jargon rather than natural trigger terms and omits any explicit 'when to use' guidance. It is distinguishable but not strongly differentiated from related context-management skills.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when running long sessions, hitting context limits, or switching between task phases').

Replace jargon like 'context compaction' and 'logical intervals' with phrasings a user would naturally invoke, such as 'compact context' or 'free up context window'.

List a couple of concrete triggering situations directly in the description to sharpen distinctiveness from generic context-management skills.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Suggests manual context compaction at logical intervals') and the mechanism ('preserve context through task phases'), but does not enumerate multiple specific concrete actions like the score-3 anchor.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only implied — capping completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Terms like 'context compaction', 'logical intervals', and 'task phases' are technical jargon a user would not naturally say when needing this skill, and no natural trigger keywords are present.	1 / 3
Distinctiveness Conflict Risk	The manual-vs-auto compaction niche is somewhat specific but lacks distinct triggers and could overlap with other context-management skills.	2 / 3
	Total	7 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: ysyecust/everything-claude-code
Commit: a9cbecb

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.