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。
45
32%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/zh-CN/skills/strategic-compact/SKILL.mdQuality
Discovery
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 is a vague, abstract recommendation written in Chinese rather than a proper skill description. It fails to specify concrete actions, lacks trigger terms, provides no 'when to use' guidance, and is indistinguishable from general advice about context management.
Suggestions
Rewrite the description to list specific concrete actions the skill performs, e.g., 'Summarizes and compresses conversation context at logical breakpoints during multi-step tasks to preserve key information.'
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 switching between task phases.'
Make the description distinctive by specifying the exact scenarios and file types or task types it applies to, differentiating it from general summarization or memory management skills.
| Dimension | Reasoning | Score |
|---|---|---|
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 recommendation than a skill description. | 1 / 3 |
Completeness | The description only vaguely hints at 'what' (manual context compression) and completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent explicit trigger. | 1 / 3 |
Trigger Term Quality | The description is in Chinese and uses abstract terms like '压缩上下文' (compress context) and '逻辑间隔' (logical intervals). These are not natural keywords a user would say when seeking help with a task. There are no recognizable trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'context compression' could apply to virtually any long-running conversation or task. It provides no clear niche or distinct triggers to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable guidance on strategic compaction with excellent decision tables and concrete hook configuration. However, it suffers from scope creep — the 'Token Optimization Patterns' section is essentially a separate skill that inflates the document. The absence of the referenced `suggest-compact.js` bundle file and lack of validation/feedback loops after compaction are notable gaps.
Suggestions
Split the 'Token Optimization Patterns' section into a separate reference file (e.g., TOKEN-OPTIMIZATION.md) and link to it, keeping SKILL.md focused on strategic compaction.
Add a verification step after compaction — e.g., 'After compacting, verify key context survived by checking TodoWrite items and confirming your current task understanding.'
Include the referenced `suggest-compact.js` script as a bundle file so the skill is self-contained and the hook configuration is verifiable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is more verbose than necessary. The 'Why Strategic Compact?' section explains concepts Claude can infer, and sections like 'What Survives Compaction' and 'Token Optimization Patterns' add significant length. The token optimization patterns section feels like a separate skill bolted on, diluting focus. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready JSON configuration for hooks setup, a clear decision table for when to compact, specific environment variable configuration, and actionable best practices with concrete examples like `/compact Focus on implementing auth middleware next`. | 3 / 3 |
Workflow Clarity | The decision table for when to compact is excellent, and the hook mechanism is clearly explained. However, there's no explicit validation or feedback loop — no way to verify compaction was effective, no guidance on what to do if important context was lost, and the hook script's behavior (threshold detection, reminders) lacks a clear error recovery path. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's monolithic — the token optimization patterns section, context composition awareness, and deduplication detection could be split into separate reference files. External links are provided but the bundle has no supporting files despite referencing `suggest-compact.js`. | 2 / 3 |
Total | 9 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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
- Commit
841beea
- 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.