strategic-compact

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is structured and genuinely useful with concrete hook config and decision tables, but it is monolithic, references a script not present in the bundle, and lacks validation checkpoints for the lossy compaction workflow.

Suggestions

Provide the referenced `suggest-compact.js` in a scripts/ bundle (or remove the hook-setup section) so the setup is fully executable.

Add an explicit validation checkpoint before compacting, e.g. 'Confirm the plan is saved in TodoWrite/memory before running /compact.'

Move the tangential '令牌优化模式' section into a separate reference file or trim it to keep the core compaction guidance lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly well-organized with useful tables, but sections like '为何采用战略精简？' and the tangential '令牌优化模式' explain concepts Claude largely knows and could be tightened or removed.	2 / 3
Actionability	It provides copy-paste-ready hook JSON and concrete env vars/examples, but the referenced `suggest-compact.js` script is not present in the bundle, so the setup is not fully executable end-to-end.	2 / 3
Workflow Clarity	The decision-guide table and numbered best practices give a clear sequence, but there are no explicit validation checkpoints (e.g., verify TodoWrite/memory persisted before compacting) for this lossy operation.	2 / 3
Progressive Disclosure	The file is well-organized into clear sections, but at ~140 lines it is monolithic with no one-level-deep references to detail files, and the token-optimization section that could be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 in clear third person and conveys a specific niche (strategic manual context compaction), but it lacks an explicit 'Use when...' trigger clause and multiple concrete action verbs, leaving every dimension at the mid level.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g. 'Use when running long sessions, switching between task phases, or approaching the context limit.'

List multiple concrete actions (e.g., 'Compacts context at phase boundaries, preserves plans in TodoWrite, clears debug context') to raise specificity.

Include common natural trigger terms users would say ('long session', 'context full', 'switching tasks') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (context compaction) and a concrete action ('手动压缩上下文...在逻辑间隔处'), but describes a single recommendation rather than listing multiple specific actions, so it is not comprehensive.	2 / 3
Completeness	It clearly states what the skill does (recommend manual compaction at logical intervals), but the 'when to use it' trigger is only implied and there is no explicit 'Use when...' clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant keywords ('压缩上下文', '上下文', '自动压缩') a user might say, but offers no 'Use when...' clause and is missing common natural variations, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The strategic-compaction niche is fairly specific and unlikely to conflict broadly, but without explicit distinct triggers it could still overlap with general context-management skills.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/everything-claude-code
Commit: 81af407

Reviewed: 4 days 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.