analyzing-text-with-nlp

Execute this skill enables AI assistant to perform natural language processing and text analysis using the nlp-text-analyzer plugin. it should be used when the user requests analysis of text, including sentiment analysis, keyword extraction, topic modeling, or ... Use when analyzing code or data. Trigger with phrases like 'analyze', 'review', or 'examine'.

Quality

21%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/ai-ml/nlp-text-analyzer/skills/analyzing-text-with-nlp/SKILL.md

Quality

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 attempts to list specific NLP capabilities but undermines itself with vague filler language, a trailing ellipsis, contradictory scope (text analysis vs. code/data analysis), and overly generic trigger terms. It also uses a problematic voice ('enables AI assistant') rather than third-person active voice describing what the skill does. The conflation of text analysis with code analysis creates significant conflict risk with other skills.

Suggestions

Remove the contradictory 'analyzing code or data' from the 'Use when' clause and replace with text-specific triggers like 'Use when the user asks about sentiment, keywords, topics, or text summarization'.

Replace the trailing '...' with a complete list of supported capabilities, and remove filler phrases like 'enables AI assistant to perform natural language processing'.

Make trigger terms more distinctive and natural—e.g., 'sentiment analysis', 'extract keywords', 'topic modeling', 'text analysis', 'NLP'—and remove overly generic terms like 'analyze', 'review', 'examine' that would match many other skills.

Dimension	Reasoning	Score
Specificity	Names some specific actions like 'sentiment analysis, keyword extraction, topic modeling' but the description is padded with vague language ('natural language processing and text analysis'), trails off with '...', and conflates text analysis with code/data analysis, reducing clarity.	2 / 3
Completeness	It attempts both 'what' (NLP tasks like sentiment analysis, keyword extraction) and 'when' ('Use when analyzing code or data'), but the 'when' clause is contradictory—it says 'analyzing code or data' for a text analysis tool—and the trailing '...' leaves the 'what' incomplete. The 'Use when' clause exists but is poorly targeted.	2 / 3
Trigger Term Quality	Includes some trigger terms like 'analyze', 'review', 'examine', 'sentiment analysis', 'keyword extraction', but these are overly generic and would match many unrelated skills. Missing natural user phrases like 'summarize text', 'find keywords', 'what is the sentiment', or file-type triggers.	2 / 3
Distinctiveness Conflict Risk	The trigger terms 'analyze', 'review', 'examine' and the scope 'code or data' are extremely generic and would conflict with virtually any analysis-related skill. The description mixes text analysis with code analysis, making it unclear what its true niche is.	1 / 3
	Total	7 / 12 Passed

Implementation

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill content is almost entirely generic boilerplate with no actionable, concrete guidance. It never specifies how to actually invoke the nlp-text-analyzer plugin, what API or commands to use, what the output format looks like, or how to handle specific error cases. The content could apply to virtually any skill with minimal changes, which means it provides essentially zero value to Claude.

Suggestions

Replace the abstract 'How It Works' and 'Instructions' sections with concrete, executable code or commands showing exactly how to invoke the nlp-text-analyzer plugin (e.g., specific function calls, parameters, and expected output formats).

Add real input/output examples with actual data — show the exact plugin invocation and the structured JSON or text output Claude should expect and return to the user.

Remove all generic sections that Claude already knows (Best Practices about 'clarity' and 'context', the vague 'Integration' section, the empty 'Resources' section) to dramatically reduce token waste.

Add concrete error handling with specific error codes/messages from the plugin and exact remediation steps, rather than generic placeholders like 'Invalid input: Prompts for correction'.

Dimension	Reasoning	Score
Conciseness	The content is extremely verbose and padded with information Claude already knows. Sections like 'Overview', 'How It Works', 'When to Use This Skill', 'Best Practices', 'Integration', and 'Resources' are all filler that explain obvious concepts without adding actionable value. The 'Instructions' section is entirely generic and could apply to any skill.	1 / 3
Actionability	There is no concrete, executable code, no specific commands, no API calls, no configuration details, and no actual instructions on how to invoke or use the nlp-text-analyzer plugin. The examples describe what the skill 'will do' in abstract terms rather than showing how to actually do it. The 'Instructions' section is completely generic ('Invoke this skill when the trigger conditions are met').	1 / 3
Workflow Clarity	The workflow steps ('Request Analysis', 'Text Processing', 'Insight Extraction') are abstract descriptions of what happens conceptually, not actionable steps Claude can follow. There are no validation checkpoints, no error recovery loops, and no concrete sequencing. The 'Instructions' section is four generic bullet points with no specificity.	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. Multiple sections contain redundant or near-empty content (e.g., 'Resources' just says 'Project documentation' and 'Related skills and commands' with no links). The structure creates an illusion of organization but every section is shallow and repetitive.	1 / 3
	Total	4 / 12 Passed

Validation

81%

Warnings & errors only

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

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 69c73e9

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.