analyzing-text-sentiment
Execute this skill enables AI assistant to analyze the sentiment of text data. it identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral. use this skill when a user requests sentiment analysis, opinion mining, or emoti... Use when analyzing code or data. Trigger with phrases like 'analyze', 'review', or 'examine'.
28
21%
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 ./plugins/ai-ml/sentiment-analysis-tool/skills/analyzing-text-sentiment/SKILL.mdQuality
Discovery
42%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description starts with a reasonable explanation of sentiment analysis capabilities but is severely undermined by contradictory trigger guidance ('Use when analyzing code or data'), truncated content ('emoti...'), and overly generic trigger terms that would cause frequent false matches. The use of first/second person ('it identifies', 'a user requests') and the imperative 'Execute this skill' add unnecessary noise without improving selection accuracy.
Suggestions
Remove the contradictory 'Use when analyzing code or data' clause and replace with sentiment-specific triggers like 'Use when the user asks about sentiment, emotional tone, opinion polarity, or text mood analysis'.
Fix the truncated text and complete the description with specific trigger terms such as 'sentiment', 'opinion mining', 'emotional tone', 'positive/negative', 'text classification'.
Remove the overly generic trigger phrases ('analyze', 'review', 'examine') that would conflict with many other skills, and focus on domain-specific keywords unique to sentiment analysis.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (sentiment analysis) and some actions (analyze sentiment, classify as positive/negative/neutral), but the description is muddled with contradictory information about code/data analysis, reducing clarity of the concrete actions. | 2 / 3 |
Completeness | It attempts to answer both 'what' (sentiment analysis of text) and 'when' (trigger phrases provided), but the 'when' clause is contradictory—it says 'Use when analyzing code or data' which conflicts with the sentiment analysis purpose, and the description is truncated, undermining completeness. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'sentiment analysis', 'opinion mining', and generic triggers like 'analyze', 'review', 'examine', but the generic triggers are too broad and would match many unrelated skills. The truncated 'emoti...' suggests incomplete coverage. | 2 / 3 |
Distinctiveness Conflict Risk | The trigger terms 'analyze', 'review', 'examine' and the clause 'Use when analyzing code or data' are extremely generic and would conflict with virtually any analysis-related skill. The sentiment-specific niche is undermined by these overly broad triggers. | 1 / 3 |
Total | 7 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely generic boilerplate with no actionable content. It describes sentiment analysis at a conceptual level that Claude already understands, provides no executable code or concrete output format, and includes multiple sections of filler ('Prerequisites', 'Instructions', 'Output', 'Error Handling', 'Resources') that contain no specific information. The skill would need to be completely rewritten to provide actual value.
Suggestions
Replace the entire body with a concrete implementation: specify an output JSON schema (e.g., {"text": "...", "sentiment": "positive|negative|neutral", "confidence": 0.95}) and provide executable Python code or a clear algorithmic approach Claude should follow.
Remove all sections that explain what sentiment analysis is, when to use it, and how it works conceptually—Claude already knows these things. Focus only on the specific format, constraints, and edge cases unique to this skill.
Add concrete examples with actual input and expected output, showing the exact JSON or structured format Claude should produce rather than describing what 'the skill will do'.
Replace the generic 'Error Handling', 'Prerequisites', 'Instructions', and 'Resources' sections with specific, actionable content or remove them entirely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows. The 'Overview', 'How It Works', 'When to Use This Skill', 'Best Practices', and 'Integration' sections are all padding that explain obvious concepts. The 'Instructions' section is entirely generic boilerplate ('Invoke this skill when the trigger conditions are met'). Nearly every section could be eliminated or drastically reduced. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific output format defined. The examples describe what the skill 'will do' in vague terms rather than showing actual code or output. The 'Instructions' section is completely generic ('Provide necessary context and parameters'). There is no actual sentiment analysis implementation—no model, no library, no API call, no output schema. | 1 / 3 |
Workflow Clarity | The workflow steps are entirely abstract ('Process the text using a pre-trained sentiment analysis model'). No specific model is named, no validation steps exist, no error recovery is defined. The 'Error Handling' section is generic boilerplate with no actionable guidance. The 'Instructions' section is four vague bullet points that could apply to literally any skill. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no bundle files to support it. All sections are inline despite being mostly filler. The 'Resources' section mentions 'Project documentation' and 'Related skills and commands' without any actual links or file references. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
6e9558f
- 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.