extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
56
37%
Does it follow best practices?
Impact
81%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/extract-errors/SKILL.mdQuality
Discovery
22%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 but fails to explain what the skill actually does, making it incomplete. It lacks concrete actions and specific capabilities. The trigger terms are somewhat relevant but could be broader to capture more user query variations.
Suggestions
Add a clear 'what' clause describing the concrete actions the skill performs, e.g., 'Registers new error codes in React's error map, updates error message definitions, and resolves unknown error code warnings.'
Expand trigger terms to include variations like 'error codes', 'React error registry', 'error code mapping', 'React warnings'.
Restructure to lead with capabilities before the 'Use when...' clause, following the pattern: '[What it does]. Use when [triggers].'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions. It mentions 'adding new error messages to React' and 'unknown error code warnings' but doesn't describe what the skill actually does (e.g., registers error codes, updates error maps, generates error documentation). | 1 / 3 |
Completeness | The description answers 'when' (adding error messages, seeing unknown error code warnings) but completely omits 'what' — there is no explanation of what the skill actually does or what actions it performs. | 1 / 3 |
Trigger Term Quality | It includes some natural trigger terms like 'error messages', 'React', and 'unknown error code warnings' that a user might encounter, but it's missing variations and broader terms (e.g., 'error codes', 'error registry', 'error handling', 'React error codes'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of React error messages and 'unknown error code' warnings provides some specificity, but 'error messages' is broad enough to potentially overlap with general error handling or debugging skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is admirably concise but too sparse to be truly useful. It names the right command but fails to provide actionable guidance on interpreting output, assigning new error codes, or validating the result. The workflow lacks any feedback loop or verification step, which is critical for a task that modifies source artifacts.
Suggestions
Add concrete guidance on what the output of `yarn extract-errors` looks like and how to interpret it (e.g., example output showing an unassigned error).
Include a validation/verification step: after assigning codes, re-run the command and confirm no warnings remain.
Specify the file where error codes are maintained (e.g., `scripts/error-codes/codes.json`) and show an example of adding a new entry.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely lean—just three short steps with no unnecessary explanation. Every token earns its place and it assumes Claude knows what error codes and yarn commands are. | 3 / 3 |
Actionability | It provides a concrete command (`yarn extract-errors`) but lacks detail on what to do after reporting new errors, how codes are assigned, where the error codes file lives, or what 'up to date' means in practice. | 2 / 3 |
Workflow Clarity | The steps are listed but there's no validation checkpoint, no guidance on what to do if errors are found, no feedback loop for fixing issues, and no clarity on what 'report' or 'check' concretely entail. For a task involving code changes (adding error codes), missing validation caps this low. | 1 / 3 |
Progressive Disclosure | The content is short and well-organized for its size, but it provides no references to where error codes are defined, no link to React's error code conventions, and no bundle files to support deeper exploration. | 2 / 3 |
Total | 8 / 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.