sentiment-monitoring

When the user wants to monitor reviews, mentions, and community sentiment about their own product. Also use when the user mentions "track our reviews", "what are people saying about us", "brand monitoring", "reputation management", or "review alerts".

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/sentiment-monitoring/SKILL.md

Quality

Content

62%

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

This is a well-structured skill with a clear workflow and excellent output format template. Its main weaknesses are verbosity (explaining general knowledge like review response etiquette) and lack of truly executable/concrete automation guidance — it describes what to do conceptually but doesn't provide specific tools, scripts, or API calls for actually monitoring platforms. The content would benefit from being trimmed and having detailed reference material moved to separate files.

Suggestions

Add concrete, executable examples for platform monitoring — specific RSS feed URLs, API endpoints, or tool configurations (e.g., Google Alerts setup, specific G2 API calls) instead of vague 'RSS, manual, API, or alert tool'.

Move the 'Frameworks & Best Practices' section (response principles, platform-specific notes, common mistakes) to a separate BEST_PRACTICES.md file and reference it from the main skill to improve progressive disclosure.

Trim general knowledge that Claude already knows — response etiquette principles like 'acknowledge don't argue' and 'take it offline' are standard communication advice that doesn't need detailed explanation.

Dimension	Reasoning	Score
Conciseness	The skill is fairly comprehensive but includes some content that Claude already knows — response principles like 'acknowledge, don't argue' and 'take it offline' are general knowledge. The 'when negative reviews are actually gifts' section and 'common mistakes' add moderate value but could be tightened. The platform-specific notes table is useful but some entries state obvious things.	2 / 3
Actionability	The workflow provides clear steps and the output format is concrete and copy-paste ready. However, there's no executable code, no specific API calls, no actual commands for checking platforms, and no automation scripts. The 'how to check for new reviews (RSS, manual, API, or alert tool)' is vague — it names categories without giving concrete implementations. The guidance is structured but largely descriptive rather than executable.	2 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced with explicit severity scales, response timeframes, and escalation thresholds (3+ reviews = product issue). The pattern detection in step 6 serves as a validation checkpoint, and the severity scale provides clear decision criteria for prioritization. The workflow moves logically from setup through scanning, analysis, response drafting, and reporting.	3 / 3
Progressive Disclosure	The skill references related skills at the bottom which is good navigation, but the content itself is monolithic — the frameworks/best practices section, platform-specific notes, common mistakes, and examples could be split into separate reference files. At ~150 lines, the inline detail is heavy for a SKILL.md overview.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 has excellent trigger terms and completeness with a clear 'Use when' clause containing natural user phrases. However, it is weak on specificity—it describes the domain (brand monitoring) without listing concrete actions the skill performs. Adding specific capabilities would significantly strengthen it.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Aggregates reviews from multiple platforms, generates sentiment trend reports, sends alerts on negative mentions, and summarizes community feedback.'

Rewrite to lead with concrete capabilities before the trigger clause, e.g., 'Tracks and aggregates product reviews, analyzes community sentiment trends, and surfaces negative mentions across platforms.'

Dimension	Reasoning	Score
Specificity	The description lacks concrete actions. It says 'monitor reviews, mentions, and community sentiment' but doesn't specify what actions the skill performs (e.g., aggregate reviews, generate sentiment reports, set up alerts, track trends). The 'what it does' is vague and abstract.	1 / 3
Completeness	The description answers both 'what' (monitor reviews, mentions, and community sentiment about their product) and 'when' (explicit 'Also use when...' clause with specific trigger phrases). Both components are present and explicit.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'track our reviews', 'what are people saying about us', 'brand monitoring', 'reputation management', 'review alerts'. These are phrases users would naturally say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The focus on 'own product' monitoring and reputation management creates a somewhat distinct niche, but 'sentiment' and 'reviews' could overlap with general sentiment analysis or review analysis skills. The self-referential framing ('about us') helps but the boundaries aren't fully clear.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: shawnpang/startup-founder-skills
Commit: 4ad31b4

Reviewed: 3 months 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.