debugging-failures

Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing into the Go runtime, parallel output interleaving, reproducing with --seed, and progress reports for hangs. Use when a suite failed and you need to know why. Also invokable as /ginkgo:debugging-failures.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%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 highly actionable with tested, copy-paste ginkgo/jq commands and a clear sequenced workflow with feedback loops. Structure is well-organized with no bundle files; only minor conciseness tightening is warranted.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (e.g. 'the headline location lies; see below'), with no padding of basic concepts; a few explanatory passages and the prose rationale blocks could be trimmed slightly.	4 / 5
Actionability	Fully executable copy-paste ginkgo and jq commands cover the common cases (verdict, all failures, panics, drill-by-name, slowest specs) with tested, real-schema filters.	5 / 5
Workflow Clarity	Clear three-step sequenced workflow (read terminal verdict, query JSON with jq, clean up) with explicit feedback loops (reproduce via --seed, narrow with --focus, drill with -v) and validation guidance (include 'panicked'/'timedout' states; avoid --fail-fast).	5 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized into clearly headed sections that fit a focused topic, so the under-50-lines/no-external-references simple-skill exception applies.	5 / 5
	Total	19 / 20 Passed

Description

86%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.

The description is concrete, trigger-rich, and clearly answers both what and when, with strong distinctiveness. Minor room to add a few more synonyms or file extensions for full keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (run with --json-report into a gitignored/temp location, read terminal verdict, use jq to extract failure details) and specific failure modes, with minor gaps in coverage rather than the exhaustive multi-action list of the 5 anchor.	4 / 5
Completeness	Explicitly states both what it does ('Diagnose a failing Ginkgo suite as an agent...use jq to extract structured failure details') and when to use it ('Use when a suite failed and you need to know why').	5 / 5
Trigger Term Quality	Includes natural user phrases like 'failing Ginkgo suite', 'suite failed', and 'need to know why', plus the tool name Ginkgo, but misses some synonyms and file extensions, falling just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — Ginkgo suite failure diagnosis via JSON+jq — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: onsi/ginkgo
Path: plugins/ginkgo/skills/debugging-failures/SKILL.md
Commit: f2d0f65

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.