feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
86
80%
Does it follow best practices?
Impact
98%
1.66xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/feature-flags/SKILL.mdQuality
Discovery
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 excels at trigger term coverage and distinctiveness, making it easy for Claude to know *when* to select this skill. However, it lacks an explicit statement of what the skill actually does—it reads entirely as a 'Use when...' clause without a preceding capability summary. Adding a brief 'what it does' statement would significantly improve it.
Suggestions
Add a capability statement before the 'Use when' clause, e.g., 'Guides debugging and configuration of React feature flags and @gate pragmas. Use when...'
Include specific concrete actions the skill teaches, such as 'diagnoses flag-related test failures, explains @gate pragma syntax, walks through adding new feature flags to React's flag system'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (feature flags in React) and mentions several actions like updating flags, debugging test failures, and adding new flags, but these are framed more as trigger scenarios than concrete actions the skill performs. It doesn't clearly state what the skill *does* (e.g., 'Diagnoses feature flag test failures', 'Generates @gate pragma configurations'). | 2 / 3 |
Completeness | The description has a 'Use when...' clause that clearly addresses *when* to use the skill, but the *what* (what the skill actually does) is only implied through the trigger scenarios. There's no explicit statement of the skill's capabilities or actions it performs. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: 'feature flag', 'tests fail', '@gate pragmas', 'channel-specific test failures', 'adding new flags', and 'React'. These cover multiple variations of how a developer would describe problems in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'feature flags', '@gate pragmas', 'channel-specific test failures', and 'React' creates a very specific niche that is unlikely to conflict with other skills. This is clearly about React's internal feature flag system. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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-crafted skill that efficiently covers React feature flags with concrete examples, clear structure, and good cross-referencing. Its main weakness is the lack of explicit validation steps in the 'Adding a New Flag' workflow — after adding flags to all fork files, there should be a verification step to confirm correctness. The common mistakes section is a strong addition that preempts frequent errors.
Suggestions
Add a validation step to 'Adding a New Flag' workflow, e.g., step 5: 'Run `/test www <pattern>` and `/test www variant false <pattern>` to verify both variants pass'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and informative. No unnecessary explanations of what feature flags are or how React works generally. The table format for flag files is efficient, and code examples are minimal but sufficient. | 3 / 3 |
Actionability | Provides concrete, executable code examples for @gate pragma and gate() inline usage, specific bash commands for testing variants, and a clear step-by-step process for adding new flags. The common mistakes section adds practical, specific guidance. | 3 / 3 |
Workflow Clarity | The 'Adding a New Flag' section has clear steps but lacks validation checkpoints — there's no step to verify the flag works across channels or to run tests after adding. The 'Debugging Channel-Specific Failures' section is well-sequenced but also lacks explicit feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Content is well-organized into logical sections with clear headers. References to the `/flags` skill are appropriately signaled. For a skill of this size (~70 lines) with no bundle files, the structure is clean and navigable without needing external files. | 3 / 3 |
Total | 11 / 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.
- Repository
- facebook/react
- Commit
cafd63b
- 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.