Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.
77
65%
Does it follow best practices?
Impact
98%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/flags/SKILL.mdQuality
Discovery
57%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 focuses almost entirely on when to use the skill ('Use when...') but neglects to explicitly state what the skill does, making it incomplete. It has decent trigger terms for its niche domain but could benefit from more natural keyword variations and a clearer statement of concrete capabilities.
Suggestions
Add an explicit 'what it does' statement before the 'Use when' clause, e.g., 'Queries feature flag configurations, compares flag states across release channels, and identifies discrepancies in feature rollouts.'
Expand trigger terms to include common variations like 'feature toggle', 'flag configuration', 'rollout', 'canary', 'staging vs production'.
List more specific concrete actions such as 'list active flags', 'diff flag states between channels', 'show flag history' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (feature flags, channels) and some actions (check states, compare channels, debug behavior differences), but the actions are somewhat general and don't list concrete operations like 'list all flags', 'toggle flag', or 'diff flag configurations between environments'. | 2 / 3 |
Completeness | The description provides a 'Use when...' clause addressing when to use the skill, but the 'what does this do' part is only implied through the trigger conditions rather than explicitly stated as capabilities. It lacks a clear statement of what the skill actually does. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'feature flag', 'channels', 'release channels', and 'debug', which users might naturally say. However, it misses common variations like 'feature toggle', 'flag configuration', 'staging vs production', 'rollout', or 'canary'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'feature flag states', 'release channels', and 'compare channels' creates a clear niche that is unlikely to conflict with other skills. This is a fairly specific domain. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured skill that efficiently documents a feature flag inspection tool. Its main weakness is the lack of concrete example output showing what `yarn flags` produces and how to interpret/explain it, which would significantly improve actionability. The workflow is straightforward but the 'explain the output' step is too vague for a debugging-oriented skill.
Suggestions
Add a concrete example showing sample `yarn flags` output and a model explanation/interpretation of that output, so Claude knows exactly what to highlight and how to present findings.
Clarify step 2 ('Explain the output to the user') with specific guidance: e.g., group by enabled/disabled, call out __VARIANT__ flags, note cross-channel discrepancies.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. Every section serves a purpose — options table, channel list, legend, and instructions are all tightly written with no unnecessary explanation of concepts Claude already knows. | 3 / 3 |
Actionability | Provides the concrete command (`yarn flags $ARGUMENTS`) and options, but lacks example output or a concrete end-to-end example showing what the output looks like and how to interpret it. 'Explain the output to the user' is vague guidance. | 2 / 3 |
Workflow Clarity | The 3-step workflow is simple and clear, but step 2 ('Explain the output to the user') is vague and lacks specifics on what to highlight or how to structure the explanation. For a diagnostic/debugging skill, there's no validation or error-handling guidance (e.g., what if the command fails or returns unexpected output). | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clear, logically separated sections (Options, Channels, Legend, Instructions, Common Mistakes) that are easy to scan. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
cafd63b
Table of Contents
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.