CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

31

Quality

25%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

50%

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

This skill provides a useful conceptual framework for strategic compaction with good decision tables and clear best practices. However, it falls short on actionability because the core script (suggest-compact.js) is never provided, and the token optimization section adds bulk without being directly tied to the compaction workflow. The content would benefit from being more focused and including the actual implementation.

Suggestions

Include the actual `suggest-compact.js` script content or provide it as a bundle file, since the skill is unusable without it.

Move the 'Token Optimization Patterns' section to a separate reference file — it's tangential to the core compaction skill and adds significant length.

Remove or significantly trim the 'What's Retained vs Lost' table, as Claude already understands compaction behavior from its own system knowledge.

Add a verification step after compaction (e.g., 'After compacting, confirm key context is preserved by checking TodoWrite items and memory files').

DimensionReasoningScore

Conciseness

The skill contains useful information but is more verbose than necessary. The 'Why Strategic Compaction?' section explains concepts Claude can infer, and some tables (like 'What's Retained vs Lost') restate knowledge Claude already has about how compaction works. The token optimization patterns section at the end feels tangential to the core skill.

2 / 3

Actionability

The hook setup JSON is concrete and copy-paste ready, and the decision table provides useful guidance. However, the core script `suggest-compact.js` is referenced but never provided, making the skill incomplete — the user cannot actually implement this without writing the script themselves. The token optimization tools mentioned (token-optimizer MCP, context-mode) are referenced without concrete setup instructions.

2 / 3

Workflow Clarity

The decision table for when to compact is well-structured and the best practices list provides clear sequencing guidance. However, there's no explicit validation step — no way to verify compaction was successful or that critical context was preserved. The 'How It Works' section describes the script's behavior but doesn't provide a complete workflow for setup, verification, and troubleshooting.

2 / 3

Progressive Disclosure

The content is organized into logical sections with headers, which aids navigation. However, the skill is quite long (~100+ lines of substantive content) and could benefit from splitting the token optimization patterns into a separate reference file. The external links at the bottom (Twitter link, references to other skills) are present but the referenced bundle files (suggest-compact.js script) are not provided, making the skill incomplete as a standalone unit.

2 / 3

Total

8

/

12

Passed

Description

0%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads as a vague procedural suggestion rather than a proper skill description. It lacks concrete actions, natural trigger terms, explicit 'use when' guidance, and any distinguishing details that would help Claude select it appropriately from a pool of skills.

Suggestions

Rewrite the description to list specific concrete actions the skill performs, e.g., 'Summarizes and compresses conversation context at logical breakpoints such as task completions or topic changes.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the conversation is getting long, when context window limits are approaching, or when the user mentions summarizing or compressing chat history.'

Make the description distinctive by specifying what differentiates manual context compression from automatic compression or general summarization skills.

DimensionReasoningScore

Specificity

The description is vague and abstract. It mentions 'compressing context at logical intervals' but does not list concrete actions or specific capabilities. It reads more like a general suggestion than a skill description.

1 / 3

Completeness

The description partially addresses 'what' (manual context compression at logical intervals) but is very weak on specifics, and there is no 'when should Claude use it' clause or explicit trigger guidance whatsoever.

1 / 3

Trigger Term Quality

The description is in Chinese and contains no natural trigger terms a user would use when seeking this skill. Terms like '压缩上下文' (compress context) and '任务阶段' (task stages) are abstract and not phrases users would naturally say.

1 / 3

Distinctiveness Conflict Risk

The description is extremely generic—'context compression' and 'preserving context across task stages' could overlap with many workflow or memory management skills. There is nothing distinctive to carve out a clear niche.

1 / 3

Total

4

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
affaan-m/everything-claude-code
Reviewed

Table of Contents

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.