CtrlK
BlogDocsLog inGet started
Tessl Logo

error-handling

Guides Claude in reviewing and writing robust error-handling code. Covers distinguishing recoverable from unrecoverable errors, implementing retry-with-backoff patterns, structured error logging with correlation IDs, and crafting helpful user-facing error messages. Use when the user asks about error handling, exception management, try-catch patterns, error logging, retry logic, or debugging runtime failures in any codebase.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A tight, well-structured body with concrete code examples and a clear decision tree for error-handling patterns. The main gaps are undefined helper functions in examples and minor redundant prose, rather than structural or verbosity problems.

Suggestions

Define or stub the helper functions used in examples (isTransient, sleep, logger, ctx) so the withRetry and logging snippets are fully copy-paste executable.

Remove or shorten the redundant opening line that restates the frontmatter description, since the body's sections already establish scope.

Add a brief note on what to do when retries are exhausted (e.g., log final failure with attempt count and surface a user-facing error) to give the retry workflow an explicit feedback loop.

DimensionReasoningScore

Conciseness

Lean and mostly efficient with focused Bad/Good code pairs that earn their place, but the opening line 'Use this skill when reviewing or writing code that needs to handle unexpected failures' duplicates the frontmatter and a few explanatory sentences could be trimmed, so just below anchor 5.

4 / 5

Actionability

Provides copy-paste-ready guidance (the withRetry function, structured logger.error calls, a concrete user-facing JSON response), but relies on undefined helpers like isTransient(), sleep(), and ctx without defining them, leaving minor gaps versus fully executable anchor 5.

4 / 5

Workflow Clarity

The numbered 'ask in order' decision tree is a clearly sequenced workflow covering transient, user-input, permanent, boundary, and fallback cases; no validation checkpoints are required since the skill is advisory rather than destructive, but it lacks the explicit feedback loops of anchor 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Don't swallow errors, Fail fast at boundaries, Logging, User-facing errors) with content appropriately contained in one file and no need for external references; just over the ~50-line simple-skill threshold, so it does not quite reach the no-reference anchor-5 exception.

4 / 5

Total

16

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capabilities and explicit trigger conditions in third person. Trigger-term coverage is broad but could add a few synonyms, and the debugging phrase introduces minor overlap risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'distinguishing recoverable from unrecoverable errors', 'retry-with-backoff patterns', 'structured error logging with correlation IDs', 'crafting helpful user-facing error messages' — giving comprehensive coverage; not below 5 since no meaningful action area is missing.

5 / 5

Completeness

Explicitly answers both 'what' (reviewing/writing robust error-handling code with the listed capabilities) and 'when' ('Use when the user asks about error handling, exception management...'), matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Strong natural triggers ('error handling, exception management, try-catch patterns, error logging, retry logic, debugging runtime failures'), but a few common synonyms (e.g. 'exceptions', 'crash', 'failure handling') are absent, so it does not reach comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Error handling is a clear niche with distinct triggers, but the phrase 'debugging runtime failures' creates minor overlap risk with a general debugging skill, keeping it just below anchor 5.

4 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fernandezbaptiste/skill-review-sandbox
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.