← ClaudeAtlas

speaking-coachlisted

Use when the user wants to practice English exam speaking (IELTS Parts 1-3, TOEFL iBT speaking tasks, B1-C2 interview/long turn/collaborative tasks), wants a speaking prompt or cue card, or wants feedback on a spoken answer provided as a transcript, self-recording description, or audio file. Generates original tasks in the exam's format with real timings and gives criteria-based feedback (fluency, coherence, lexis, grammar, pronunciation) with a range estimate and CEFR level. Logs every scored attempt.
OleksiiDotsenko/english-exam-coach · ★ 8 · AI & Automation · score 73
Install: claude install-skill OleksiiDotsenko/english-exam-coach
# Speaking Coach Terminal-friendly speaking practice: **record or perform → transcribe → evaluate**. Paths are relative to `${CLAUDE_PLUGIN_ROOT}` (if unset, resolve relative to the plugin root — the directory two levels above this file, `.../plugins/english-exam-coach`). ## When to use The user wants a speaking task, mock speaking interview, or feedback on an answer they spoke (pasted as transcript or provided as an audio file). ## Steps 1. **Identify** exam + level + part. Load `data/exam-formats/<exam-id>.md`, `data/cefr/speaking-descriptors.md`, and `data/cefr/speaking-calibration-anchors.md` (leveled transcript samples). Seed shapes: `data/item-bank/seed/speaking-tasks.md` (imitate format, never reuse). 2. **Generate the task** with the exam's real prep/speaking times (e.g. IELTS Part 2: 1 min prep, 1–2 min talk; TOEFL interview answers: 45 s each with no preparation time). **Pitch the prompt's demand to the level** (B1 concrete/personal; B2 opinion on a familiar topic; C1 abstract, asks the speaker to weigh/hypothesise; C2 nuanced) — `speaking-calibration- anchors.md` shows an at-level answer to aim the prompt at. Visual-dependent tasks (Cambridge B1 Part 2 describe-a-photo; B2 First / C1 Advanced Part 2 compare-photographs; C2 Part 2 picture discussion) can't be rendered here; say so and offer a non-visual part instead of faking it. IELTS Speaking uses no visual prompts — its Part 2 is a text cue card and IS fully renderable