flags
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 provides a clear 'Use when' clause with a reasonably specific niche around feature flags and release channels, making it distinctive. However, it lacks an explicit 'what does this do' component — it tells Claude when to use the skill but not what concrete actions or outputs the skill provides. The trigger terms are adequate but could be broader to capture more natural user phrasings.
Suggestions
Add a 'what' clause before the 'Use when' that lists concrete capabilities, e.g., 'Queries feature flag configurations, diffs flag states across release channels, and identifies flag mismatches causing behavioral differences.'
Expand trigger terms to include common variations like 'feature toggle', 'flag config', 'staging vs production flags', 'canary', 'beta channel', or specific flag system terminology users might reference.
| 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 for a channel', 'diff flag values between channels', or 'toggle flags'. | 2 / 3 |
Completeness | The description focuses almost entirely on 'when' (Use when...) but barely addresses 'what' — it doesn't explain what the skill actually does or what concrete outputs/capabilities it provides. The 'what' is only implied through the trigger conditions. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'feature flag', 'channels', 'release channels', and 'debug', but misses common variations users might say such as 'feature toggle', 'flag configuration', 'canary', 'beta channel', 'staging vs production', or specific flag system names. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'feature flags', 'release channels', and cross-channel comparison/debugging creates a clear, specific niche that is unlikely to conflict with other skills. | 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 reference skill for feature flag inspection. Its main weakness is that the instructions section is somewhat vague — particularly around interpreting and presenting output. The reference tables (options, channels, legend) are excellent and token-efficient.
Suggestions
Add a brief example of actual command output and how to interpret/present it to make steps 2 and 3 more actionable (e.g., show sample `--diff` output and what a good explanation looks like).
Clarify what constitutes 'meaningful differences' in step 3 — e.g., flags that differ between production and experimental channels, or `__VARIANT__` flags that may cause behavioral divergence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. Every section earns its place — no unnecessary explanations of what feature flags are or how yarn works. The legend, options table, and channel list are all compact reference material. | 3 / 3 |
Actionability | Provides the concrete command (`yarn flags $ARGUMENTS`) and clear options, but step 2 ('Explain the output to the user') and step 3 ('highlight meaningful differences') are vague directives rather than concrete guidance on how to interpret or present the output. | 2 / 3 |
Workflow Clarity | The 3-step workflow is listed but is quite thin — steps 2 and 3 lack specificity. For a non-destructive read-only operation validation isn't critical, but the instructions could better clarify what 'meaningful differences' means or how to structure the explanation. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Options table, Channels, Legend, Instructions, Common Mistakes). No need for external references and no monolithic walls of text. | 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.
- Repository
- facebook/react
- Commit
705268d
- 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.