extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
58
41%
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.
This description only provides trigger conditions ('Use when...') without explaining what the skill actually does, making it impossible for Claude to understand the skill's capabilities. While the trigger terms are somewhat specific to a React error message workflow, the complete absence of capability description severely limits its usefulness for skill selection.
Suggestions
Add a 'what' clause before the 'Use when' that describes concrete actions, e.g., 'Registers new error codes in React's error message registry, updates error code mappings, and resolves unknown error code warnings.'
Include additional trigger terms like 'error codes', 'error registry', 'codes.json', or other React-specific error infrastructure terms users might reference.
Specify the scope more precisely — is this for React core development, a specific React error boundary pattern, or a custom error code system?
| 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., generates error codes, updates error message files, registers error entries). | 1 / 3 |
Completeness | The description answers 'when' (adding error messages, seeing unknown error code warnings) but completely fails to answer 'what' — there is no explanation of what the skill actually does or what actions it performs. | 1 / 3 |
Trigger Term Quality | Includes some natural trigger terms like 'error messages', 'React', and 'unknown error code warnings' that a user might encounter, but misses variations like 'error codes', 'error registry', 'error handling', or specific file references. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of React error messages and 'unknown error code' warnings is somewhat specific to a particular workflow, but without describing what the skill does, it could overlap with general React development or error handling skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
60%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is admirably concise and provides a concrete starting command, but steps 2 and 3 are too vague to be actionable — Claude wouldn't know how to interpret the output, where error codes are stored, or how to assign new ones. The skill needs more specific guidance on what success and failure look like and what concrete actions to take.
Suggestions
Add specifics on how to interpret the output of `yarn extract-errors` — what does it look like when new errors need codes, and where are codes assigned (e.g., which file to edit)?
Include an example of expected output and the concrete steps to assign a new error code (e.g., editing a specific codes map file).
Add a validation step: after assigning codes, re-run `yarn extract-errors` to confirm no warnings remain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanation. Every line serves a purpose and assumes Claude knows what error codes and yarn commands are. | 3 / 3 |
Actionability | Provides a concrete command (`yarn extract-errors`) but lacks detail on what to do after running it — how to interpret output, how to assign new error codes, or what 'up to date' means in practice. | 2 / 3 |
Workflow Clarity | Steps are listed but extremely vague. 'Report if any new errors need codes assigned' and 'Check if error codes are up to date' lack any specifics on what to look for, what output to expect, or what actions to take based on results. No validation or feedback loop is present. | 1 / 3 |
Progressive Disclosure | This is a very simple, short skill (under 50 lines, single task) with no need for external references or deeper file structure. The organization is appropriate for its scope. | 3 / 3 |
Total | 9 / 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.