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

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./docs/zh-CN/skills/strategic-compact/SKILL.md

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 content is well-structured and offers genuinely actionable hook configuration, config, and best-practice examples, but it is padded with a tangential token-optimization section and ships as a monolithic file with no bundle files for its referenced script. Every dimension sits at the midpoint between efficient/complete and verbose/incomplete.

Suggestions

Remove or move the '令牌优化模式' section (trigger-table lazy loading, context-composition awareness, MCP tool claims) out of SKILL.md — it is general advice unrelated to the core manual-compaction skill and dilutes conciseness.

Bundle the referenced suggest-compact.js (and install.sh / hooks.json) under scripts/ and assets/, or split the detailed decision/retention tables into a reference file linked from a concise overview, to establish real progressive disclosure.

Add an explicit validation checkpoint to the workflow, e.g. 'After compacting, verify the retained items (TodoWrite tasks, CLAUDE.md, memory files) are still present before proceeding.'

Dimension	Reasoning	Score
Conciseness	The core sections (when to activate, hook setup, config, decision/retention tables, best practices) are efficient, but the appended '令牌优化模式' section is tangential general token-optimization advice with over-claims ('95%以上的自动令牌减少', '315KB 减少到 5.4KB') that could be cut.	2 / 3
Actionability	It provides copy-paste-ready hook JSON, a concrete COMPACT_THRESHOLD env var, and specific best-practice examples ('/compact Focus on implementing auth middleware next'), but '工作原理' is descriptive and the central suggest-compact.js script is not bundled, leaving it incomplete standalone.	2 / 3
Workflow Clarity	The '压缩决策指南' table gives a clear, sequenced decision framework (phase transition → compress? → reason) and best practices form a checklist, but there are no explicit validation/checkpoint steps for the decision process.	2 / 3
Progressive Disclosure	The body is a single monolithic file with good section headers and tables, but there is no reference-file split and the referenced suggest-compact.js, install.sh, and hooks/hooks.json are not present in any bundle directory.	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 clearly states a single concrete action and purpose with a distinctive manual-vs-automatic framing, but it lacks an explicit 'Use when...' trigger clause and natural trigger-term coverage. All dimensions land at the midpoint, chiefly because the 'when' is implied rather than stated.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running long sessions near the context limit, between multi-stage task phases, or after completing a milestone.'

Broaden trigger terms to natural user phrasing such as '上下文快满了 / context limit / 长会话 / tokens' so the skill surfaces when users actually describe the problem.

List a couple of concrete compaction actions (e.g. '/compact with a focus summary, compact after research before implementation') to lift specificity toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	It names a concrete action ('手动压缩上下文' / manually compact context) and its purpose ('在任务阶段中保留上下文'), but lists a single action rather than the multiple specific actions required for a 3.	2 / 3
Completeness	The 'what' is explicit ('建议...手动压缩上下文') and a 'when' is only implied ('在逻辑间隔处'), but there is no explicit 'Use when...' trigger clause, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	The keyword '压缩上下文' (compact context) is relevant, but common variations a user would actually say (e.g. '上下文满了', 'context limit', '长会话', 'tokens') are missing.	2 / 3
Distinctiveness Conflict Risk	The contrast '而非任意的自动压缩' carves a clear niche (manual strategic compaction vs automatic), but the generic 'context' trigger terms 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
Path: docs/zh-CN/skills/strategic-compact/SKILL.md
Commit: 754b8dd

Reviewed: 5 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.