CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-errors

Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error messages, and hit/user counts. Covers tracing data flow through call stacks, identifying producers of invalid data vs. consumers that crash, enriching error messages for telemetry diagnosis, and avoiding common anti-patterns like silently swallowing errors.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A well-crafted debugging skill with concrete code examples and sound strategy, but it reads as a prose-heavy strategy guide rather than a tightly sequenced workflow, and verification steps are present but not woven into explicit feedback loops.

Suggestions

Add an explicit validate-fix-retry feedback loop (e.g., 'If unit tests or the build fail, fix and re-run until both pass') to lift workflow_clarity to 3.

Tighten explanatory prose in the 'Do NOT fix at the crash site' and 'Understanding error construction' sections to reduce token cost without losing the domain insight.

Consider promoting the end-of-file verification steps into the main workflow sequence so checkpoints are explicit rather than appended as guidelines.

DimensionReasoningScore

Conciseness

The guidance is domain-specific rather than generic padding, but passages like 'Fixing at the crash site... only masks the real problem. The invalid data still flows through the system and will cause failures elsewhere' could be tightened; it is mostly efficient with some unnecessary explanatory prose.

2 / 3

Actionability

Provides concrete, specific TypeScript examples (reviveUri, _validateUri, ListenerLeakError construction), explicit search instructions, and copy-paste-ready guidance, matching the fully executable score-3 anchor.

3 / 3

Workflow Clarity

The Approach is structured as numbered strategies/branches rather than a linear sequence, and verification steps ('Run the relevant unit tests', 'Check for compilation errors') are present but listed implicitly at the end without explicit validate→fix→retry feedback loops.

2 / 3

Progressive Disclosure

No bundle files exist and the file is a single self-contained SKILL.md with clear sections and no nested references, but at ~95 lines the inline content is fairly substantial and could be better organized rather than qualifying for the under-50-line score-3 exception.

2 / 3

Total

9

/

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.

A strong, specific description that clearly states capabilities, explicit use-when triggers, and a distinct niche in third person. It does not pad with vague claims or generic language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'tracing data flow through call stacks', 'identifying producers of invalid data vs. consumers that crash', and 'enriching error messages for telemetry diagnosis', matching the score-3 anchor.

3 / 3

Completeness

Explicitly answers both what ('Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard') and when ('Use when investigating error-telemetry issues...'), satisfying the score-3 anchor.

3 / 3

Trigger Term Quality

Includes natural terms a user investigating this dashboard would say — 'stack traces', 'error messages', 'hit/user counts', 'error-telemetry issues' — with good coverage of the domain's common phrasings.

3 / 3

Distinctiveness Conflict Risk

The niche is tightly scoped to the VS Code error telemetry dashboard with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
posit-dev/positron
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.