CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

parse-error-logs

Parse build errors, test failures, type-check output, and validation logs into structured data. Use when processing npm/pnpm output, TypeScript errors, Jest failures, or any validation command results for quality gates.

70

Quality

88%

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

77%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.

The body is well structured and highly actionable, with concrete per-tool patterns, a complete output schema, and illustrative worked examples. Its main defects are a dangling reference to a missing patterns.json and some redundancy between the Step 5 output spec and Example 1. Moving the worked examples into a referenced file (and actually shipping the referenced patterns file) would align the progressive-disclosure structure with the rest of the quality.

Suggestions

Either add references/patterns.json with the promised regex patterns or inline the key regexes in Step 2 and delete the 'Supporting Files' section — the referenced file does not exist in the bundle.

Trim Example 1's second error object (structurally identical to the first) and cut the overlap between Step 5's 'Expected Output' and Example 1 to reduce token cost.

Move the four full worked examples to an EXAMPLES.md reference (one level deep, clearly signaled) so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is efficient — it explains no background concepts and goes straight to patterns, fields, and formats — but Example 1's second error object structurally duplicates the first and overlaps Step 5's 'Expected Output' block, so minor trimming is possible (anchor 4, not the fully lean anchor 5).

4 / 5

Actionability

Guidance is mostly executable: sample error patterns per tool type, a defined field-extraction schema, a complete JSON output contract, and four full input→output worked examples. The gap is that the actual regex patterns are delegated to 'patterns.json', which is not present in the bundle, leaving a minor missing detail (anchor 4 rather than 5).

4 / 5

Workflow Clarity

Five steps are clearly sequenced, each with defined expected input or output, an Error Handling section provides fallback behavior for empty/unrecognized/partial/invalid input (error-recovery guidance), and a final Validation checklist covers the failure modes — matching the anchor-5 example with checkpoints and a checklist.

5 / 5

Progressive Disclosure

Sections are well organized, but the single external reference ('patterns.json: Regex patterns for common error formats') points to a file that does not exist in the bundle (no references/ directory), breaking navigation, and four full worked examples are inlined in an overview that could point to them instead — matching anchor 3 ('references present but not clearly signaled / could be better organized').

3 / 5

Total

16

/

20

Passed

Description

92%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.

This is a strong description: it states a clear, multi-part capability and an explicit 'Use when...' trigger clause with the exact tool names users would mention. The only weakness is modest keyword coverage — a few natural synonyms (tsc, compiler output, lint) would round it out.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'Parse build errors, test failures, type-check output, and validation logs into structured data' — giving comprehensive coverage of its domain with a clear transformation target, matching the anchor-5 exemplar structure.

5 / 5

Completeness

It explicitly answers both 'what' (parse error output into structured data) and 'when' ('Use when processing npm/pnpm output, TypeScript errors, Jest failures, or any validation command results for quality gates') with concrete trigger phrases, matching the anchor-5 exemplar.

5 / 5

Trigger Term Quality

Natural tool terms users would actually say are present ('npm/pnpm output', 'TypeScript errors', 'Jest failures', 'quality gates'), but common variations like 'tsc output', 'lint errors', or 'compiler output' are missing, placing it between the good-coverage (4) and comprehensive (5) anchors.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (parsing tool error output into structured data) with tool-specific triggers (npm/pnpm, TypeScript, Jest) that other skills would not claim; only the phrase 'any validation command results' adds slight breadth, but not enough to create real conflict risk.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

maslennikov-ig/claude-code-orchestrator-kit

Path

.claude/skills/parse-error-logs/SKILL.md

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.