Jobo16/ielts-buddy / skills/ielts-mock-review
ielts-mock-review
Verified依据一次模考的科目完成状态、可信成绩与作答证据进行复盘,识别高影响问题并提出下一步;需要时按明确结构检索或组成模考试卷。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.4 KB |
| agents/openai.yaml | config | 251 B |
| manifest.json | config | 211 B |
| references/api-access.md | markdown | 1.1 KB |
| references/browser-routes.md | markdown | 587 B |
| references/learning-data.md | markdown | 965 B |
| references/mock-test-review/WORKFLOW.md | markdown | 1.6 KB |
| references/review-records.md | markdown | 1.1 KB |
| references/skill-taxonomy.json | config | 1.5 KB |
references/mock-test-review/WORKFLOW.md
View on GitHub# Mock Test Review
> 当当前学习任务需要本方法时按需读取。脚本命令中的 `scripts/` 相对于本 Skill 根目录;执行时解析为安装目录中的绝对路径。
Use this workflow after a completed IELTS mock test. The browser owns timing, media playback, answer entry, and submission; the local Agent owns evidence review and remediation.
## Inputs
Use owned session data or learner-provided results:
- test type and date;
- section scores and timing;
- question-level answers for objective sections;
- Writing answers and Speaking transcript or audio evidence;
- interruptions or invalid sections that affect interpretation.
## Workflow
1. Verify which sections are complete and comparable.
2. Calculate or read section and overall band data without inventing missing components.
3. For Reading and Listening, group misses by canonical skill code and question type.
4. For Writing and Speaking, use local rubric evidence and state confidence; assess pronunciation only from audio evidence.
5. Separate knowledge gaps, strategy errors, and time-management errors.
6. Choose one high-impact repair task per affected subject, capped at three tasks total.
7. Record evidence, then hand off to `$ielts-study-plan` for weekly review or the next daily study action.
## Output
```text
模考结论:<one sentence>
有效分数:<section scores with missing/invalid labels>
主要失分模式:<canonical skills with evidence>
下一轮修复:<up to three tasks>
建议复测:<date or completion condition>
```
Do not treat one mock as a stable level. Compare trends only after comparable attempts exist.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |