strategic-compact

建议在逻辑间隔处进行手动压缩（Manual Compaction），以在整个任务阶段保持上下文（Context），而非随意的自动压缩。

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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/ja-JP/skills/strategic-compact/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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 provides a concrete hook configuration, but it is held back by a missing referenced script, absent validation checkpoints, and minor verbosity from bilingual parentheticals. Every dimension lands at a middling 2.

Suggestions

Ship the missing `scripts/suggest-compact.sh` (or inline its executable content) so the referenced implementation actually exists and actionability/progressive_disclosure reach 3.

Add an explicit validation/feedback step in the workflow, e.g. after installing the hook, verify with a dry-run tool-call count and confirm the threshold fires before relying on it.

Trim bilingual parentheticals ("钩子（Hook）", "上下文（Context）") and condense the "why" section to assume Claude's existing knowledge of auto-compaction.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight bullet points and a copy-paste JSON block, but the "为什么需要策略性压缩" explainer and repeated bilingual parentheticals ("钩子（Hook）", "上下文（Context）") add explanation Claude does not need, keeping it short of lean.	2 / 3
Actionability	It gives concrete, copy-paste-ready hook config and an env var, but the core logic script `suggest-compact.sh` is referenced yet absent from the bundle (no scripts/ directory), leaving the executable implementation incomplete.	2 / 3
Workflow Clarity	A clear 3-step sequence (track → threshold → periodic reminder) and ordered best practices are present, but there are no explicit validation checkpoints or feedback loops for setup/operation, so it sits at 2 rather than 3.	2 / 3
Progressive Disclosure	The SKILL.md is a well-organized overview with one-level-deep, clearly signaled references (`suggest-compact.sh`, an external guide URL), but the referenced script file does not exist in the bundle, breaking the navigation promise.	2 / 3
	Total	8 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 conveys a clear single purpose (manual compaction at logical boundaries to preserve context) but lacks an explicit "Use when..." trigger clause and broader natural trigger terms. It is competent but middling across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when managing long sessions, approaching the context window limit, or before major task phase transitions."

Expand trigger terms to natural user phrasings: "context window", "long session", "running out of context", "compact before implementing".

List more concrete actions (e.g. "Tracks tool-call count, suggests /compact at configurable thresholds, preserves implementation plans across compaction") to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "建议在逻辑间隔处进行手动压缩" (recommends manual compaction at logical intervals) — but lists only a single action rather than multiple specific concrete actions, so it falls short of a 3 and is well above vague filler like "Helps with documents".	2 / 3
Completeness	It answers "what" (recommend manual compaction to preserve context) but the "when" is only implied ("在逻辑间隔处") with no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces relevant terms ("手动压缩/Manual Compaction", "上下文/Context", "自动压缩") that a user might say, but misses common natural variations such as "context window", "long session", or "running out of context", so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"Strategic/manual compaction at logical intervals" is a recognizable niche, but without explicit distinct triggers it could still overlap with general context-management guidance, so it is not yet a clearly conflict-free 3.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xu-xiang/everything-claude-code-zh
Path: docs/ja-JP/skills/strategic-compact/SKILL.md
Commit: dfbf946

Reviewed: 2 months 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.