CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-structured into a clear nine-step sequence with concrete commands and code throughout. Its main gaps are mild per-step boilerplate repetition and the absence of a verification checkpoint after applying batch fixes.

Suggestions

Add a verification step (e.g., run `pnpm typecheck` and the test suite) after the fix steps to confirm edits compile and tests pass before reporting, which would lift workflow_clarity.

Reduce the repeated "Read each file, make the edit, and write it back" instruction by stating this once up front and referencing it, tightening conciseness.

Consider condensing the Step 9 worked-example table or moving the full report schema to a brief template to trim token overhead.

DimensionReasoningScore

Conciseness

The body is largely action-dense with no concept re-explanation, but the repeated boilerplate "Read each file, apply the fix, and write it back" across nearly every step and the lengthy worked example table add padding that could be tightened.

2 / 3

Actionability

Every step supplies executable grep commands and copy-paste-ready code (try/catch wrapping, ErrorBoundary setup, Zod safeParse, optional chaining, AbortController cleanup), giving fully concrete guidance.

3 / 3

Workflow Clarity

The nine steps are clearly sequenced and Step 9 provides a status report, but for a batch file-mutating operation there is no verification checkpoint (e.g., run typecheck/tests) to confirm fixes compile and pass, capping this dimension.

2 / 3

Progressive Disclosure

Content is organized into clearly headed one-level sections with no nested external references and easy navigation, which is appropriate for a single-file skill with no bundle.

3 / 3

Total

10

/

12

Passed

Description

100%

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 is specific, complete, and well-scoped, naming concrete actions and an explicit trigger list in third-person voice. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

"finds AND fixes bugs, missing error states, unhandled rejections, and edge-case failures" lists multiple concrete actions rather than vague language.

3 / 3

Completeness

Clearly states what it does ("finds AND fixes...") and when to use it ("MUST be used whenever fixing correctness and error handling issues in a Flows app") with explicit triggers, answering both what and when.

3 / 3

Trigger Term Quality

An explicit Triggers list gives broad natural coverage ("bug fix", "crash", "null", "undefined", "edge case", "try catch", "async error", "runtime error") a developer would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to Flows apps with a clear niche and the differentiator "it does not just report them", making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
cognitedata/builder-skills
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.