analyze-feedback
Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise. Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports.
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./analytics-skills/skills/analyze-feedback/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that hits all the key criteria. It uses third person voice, lists specific concrete actions and output types, includes natural trigger terms users would actually say, and has an explicit 'Use when' clause with multiple clear trigger scenarios. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: synthesizing feedback into themes, and enumerates specific theme types (feature requests, bugs, pain points, praise). These are concrete, actionable outputs. | 3 / 3 |
Completeness | Clearly answers both what ('Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise') and when ('Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'customer feedback', 'feature requests', 'bugs', 'pain points', 'product roadmap', 'user sentiment', 'voice-of-customer reports'. These cover a wide range of natural user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around customer feedback synthesis and voice-of-customer analysis. The specific domain (customer feedback themes, roadmap planning, sentiment) is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable workflow for customer feedback analysis with clear steps and a well-defined output format. Its main weaknesses are the lack of concrete examples (sample tool calls, expected outputs, formatted theme examples) and missing validation/error-handling checkpoints in the workflow. The Best Practices section adds useful formatting guidance but could be more concise.
Suggestions
Add a concrete example of a tool invocation with parameters and expected response shape, e.g., show an actual `Amplitude:get_feedback_insights` call with filters and a sample JSON response.
Include a brief example of the final formatted output (even a partial one) so the presentation format in Step 5 is unambiguous and copy-paste ready.
Add validation checkpoints: e.g., 'If fewer than X mentions are returned, expand the date range or broaden filters before proceeding to Step 5.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, particularly in the Best Practices section which repeats formatting guidance that could be tightened. The step-by-step instructions are reasonably lean, though some bullet points could be more concise. | 2 / 3 |
Actionability | The skill provides specific tool names and filter parameters (e.g., `Amplitude:get_feedback_sources`, filter types like `request`, `complaint`), which is good. However, there are no concrete examples of actual tool invocations with parameters, expected outputs, or sample formatted results — it describes what to do rather than showing executable examples. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logical, but there are no validation checkpoints or feedback loops. There's no guidance on what to do if a step fails (e.g., no feedback sources found, no mentions for a theme), and no verification that the analysis is complete or accurate before presenting findings. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines) with no bundle files and a single workflow, the content is well-organized with clear sections (Instructions with numbered steps, Best Practices). The structure is appropriate for the complexity level and doesn't need external references. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
- amplitude/builder-skills
- Commit
221ffaa
- 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.