strategic-compact

建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。

Quality

56%

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 ./.agents/skills/strategic-compact/SKILL.md

Quality

Content

62%

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

The body is well-structured with actionable hook config and a strong decision table, but it loses points for explaining concepts Claude already knows and for referencing a `suggest-compact.js` script that is not actually bundled.

Suggestions

Ship the referenced `suggest-compact.js` in ./scripts/ (or inline its logic) so the hook command is actually executable rather than pointing at a missing file.

Trim the "Why Strategic Compaction?" section to the non-obvious points only; Claude already knows that auto-compaction can fire mid-task.

Move the large settings.json hook block into a referenced setup file (e.g. references/hook-setup.md) to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful tables and a concrete hook snippet, but sections like "Why Strategic Compaction?" explain auto-compaction behavior Claude already knows and could be tightened.	2 / 3
Actionability	Concrete guidance is present (settings.json hook config, env var), but the referenced `suggest-compact.js` script is not bundled in ./scripts/, leaving a key executable piece incomplete.	2 / 3
Workflow Clarity	The single action (run /compact at logical boundaries) is unambiguous and the Compaction Decision Guide table plus Best Practices serve as an explicit checklist with clear yes/no-and-why criteria.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill exceeds 50 lines and references a script file (`suggest-compact.js`) that should live in ./scripts/ yet is missing from the bundle, a structural gap rather than clean one-level-deep references.	2 / 3
	Total	9 / 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 communicates a clear single-purpose niche (manual compaction at logical boundaries) but stays at the mid-band: it names one action without multiple concrete actions, leans on technical jargon, and lacks an explicit "Use when" trigger clause.

Suggestions

Add an explicit "Use when..." trigger clause naming natural user phrasings, e.g. "Use when running long multi-phase sessions, switching unrelated tasks, or when context pressure slows responses."

List concrete actions beyond a single verb, e.g. "Tracks tool-call counts, detects logical task boundaries, and suggests /compact at milestone transitions."

Replace jargon like "arbitrary auto-compaction" with user-natural terms ("random auto-compaction mid-task") to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	It names one concrete action ("Suggests manual context compaction") and the domain, but does not list multiple specific concrete actions as the top anchor requires.	2 / 3
Completeness	It states what the skill does, but the "when" is only implied ("at logical intervals", "through task phases") with no explicit "Use when..." trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms like "context compaction" and "task phases" appear, but phrasing such as "arbitrary auto-compaction" is technical jargon and common natural variations (e.g. "/compact", "running low on context") are missing.	2 / 3
Distinctiveness Conflict Risk	"Manual context compaction" is a fairly distinct niche, but the wording could still overlap with general context-management skills and lacks crisp distinguishing triggers.	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: xu-xiang/everything-claude-code-zh
Path: .agents/skills/strategic-compact/SKILL.md
Commit: dfbf946

Reviewed: about 2 hours 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.