correctness-and-error-handling
MUST be used whenever fixing correctness and error handling issues in a Flows app. This skill finds AND fixes bugs, missing error states, unhandled rejections, and edge-case failures — it does not just report them. Triggers: correctness, error handling, bug fix, edge case, crash, unhandled, null, undefined, empty state, loading state, error boundary, try catch, async error, useEffect cleanup, type guard, runtime error, robustness.
68
84%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%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 is a strong skill description that clearly communicates what it does (finds and fixes correctness/error handling issues) and when to use it (comprehensive trigger terms list). The explicit 'Triggers:' section with natural developer terminology is excellent. The main weakness is potential overlap with general debugging skills, though scoping to 'Flows app' helps mitigate this.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: finds and fixes bugs, missing error states, unhandled rejections, and edge-case failures. Also clarifies it doesn't just report them but actively fixes them. | 3 / 3 |
Completeness | Clearly answers both 'what' (finds and fixes bugs, missing error states, unhandled rejections, edge-case failures in Flows apps) and 'when' (explicitly states 'MUST be used whenever fixing correctness and error handling issues' plus a comprehensive triggers list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'bug fix', 'crash', 'null', 'undefined', 'empty state', 'loading state', 'error boundary', 'try catch', 'async error', 'useEffect cleanup', 'type guard', 'runtime error'. These are terms developers naturally use when encountering these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Scoped to 'Flows app' which helps distinguish it, but the broad range of error handling and bug fixing terms could overlap with general debugging or code review skills. Terms like 'bug fix', 'crash', and 'runtime error' are quite general and could trigger for non-Flows contexts. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable, well-structured skill that provides a comprehensive workflow for finding and fixing correctness and error handling issues. Its greatest strength is the concrete, executable guidance at every step — combining grep-based discovery with specific code fix patterns. The main weakness is its length; at 9 detailed steps with full code examples inline, it could benefit from splitting reference patterns into separate files to improve scannability and reduce token cost.
Suggestions
Consider extracting the detailed code fix patterns (Steps 3-7) into a separate reference file like PATTERNS.md, keeping only the grep commands and brief fix descriptions in the main SKILL.md
Remove repeated instructions like 'Read each file, make the edit, and write it back' — state this once at the top as a general principle
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is actionable code examples and grep commands. Some patterns (like the full ErrorBoundary boilerplate and multiple similar fix patterns) could be tightened, and there's mild redundancy across steps (e.g., repeated 'Read each file, make the edit, and write it back' instructions). However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Every step provides concrete, executable bash commands for discovery and complete, copy-paste-ready code fixes. The grep patterns, code templates, and specific fix instructions leave no ambiguity about what to do. The skill consistently shows before/after patterns with real code. | 3 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced from mapping data flows through to a final structured report. Each step has explicit search commands followed by fix instructions, and the final step serves as a validation/reporting checkpoint. The skill includes feedback loops (e.g., Step 1's 'fix or convert to safe fallback' decision tree) and the reporting table in Step 9 provides verification of all changes. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with no references to external files, which is acceptable given no bundle files exist. However, at ~250+ lines with 9 detailed steps, some content (like the full code templates for each fix pattern) could benefit from being split into referenced files. The internal structure with numbered steps and clear headers is good, but the sheer length in a single file works against quick scanning. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- 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.