メニュー
Analyze sentiment in text using ML models. Use when: analyzing customer reviews; processing NPS feedback; monitoring brand mentions; evaluating campaign responses; categorizing support tickets
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint
Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections.
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Use when analyzing server logs to understand how AI crawlers (GPTBot, ClaudeBot, PerplexityBot) interact with your site. Use when optimizing content placement for LLM retrieval, diagnosing why AI search isn't citing your content, or auditing crawl patterns to find optimization gaps.
Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.
| name | sentiment-analyzer |
| description | Analyze sentiment in text using ML models. Use when: analyzing customer reviews; processing NPS feedback; monitoring brand mentions; evaluating campaign responses; categorizing support tickets |
| license | MIT |
| metadata | {"author":"ClawFu","version":"1.0.0","mcp-server":"@clawfu/mcp-skills"} |
Analyze sentiment in customer feedback using transformer models - understand what your customers really feel at scale.
| Claude Does | You Decide |
|---|---|
| Structures analysis frameworks | Metric definitions |
| Identifies patterns in data | Business interpretation |
| Creates visualization templates | Dashboard design |
| Suggests optimization areas | Action priorities |
| Calculates statistical measures | Decision thresholds |
pip install transformers torch pandas click
# Or for lighter CPU-only version:
pip install textblob vaderSentiment pandas click
python scripts/main.py analyze "This product exceeded my expectations!"
python scripts/main.py analyze "The service was terrible and slow."
python scripts/main.py batch reviews.csv --column text
python scripts/main.py batch feedback.csv --column comment --output results.csv
python scripts/main.py report reviews.csv --column text --output sentiment-report.html
# Process CSV of reviews
python scripts/main.py batch amazon-reviews.csv --column review_text
# Output: amazon-reviews_sentiment.csv
# review_text | sentiment | score | label
# "Absolutely love this!" | positive | 0.95 | Very Positive
# "It's okay, nothing special" | neutral | 0.52 | Neutral
# "Worst purchase ever" | negative | 0.12 | Very Negative
# Analyze NPS survey responses
python scripts/main.py report nps-responses.csv --column feedback
# Output: sentiment-report.html
# Summary:
# - Positive: 62% (mainly: product quality, support)
# - Neutral: 23% (mainly: pricing concerns)
# - Negative: 15% (mainly: shipping delays)
| Score Range | Label | Interpretation |
|---|---|---|
| 0.8 - 1.0 | Very Positive | Enthusiastic, recommend |
| 0.6 - 0.8 | Positive | Satisfied, happy |
| 0.4 - 0.6 | Neutral | Mixed or indifferent |
| 0.2 - 0.4 | Negative | Disappointed, frustrated |
| 0.0 - 0.2 | Very Negative | Angry, will churn |
category: analytics
subcategory: nlp
dependencies: [transformers, torch, pandas]
difficulty: intermediate
time_saved: 6+ hours/week