Name: debug-buttercup
Rating: 68.8 (1 reviews)
Author: administrakt0r

debug-buttercup

All pods run in namespace crs. Use when pods in the crs namespace are in CrashLoopBackOff, OOMKilled, or restarting, multiple services restart simultaneously (cascade failure), or redis is unresponsive or showing AOF warnings.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is debug-buttercup in administrakt0r/AI-Agents-Safe-Coding-Skills

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 content is an excellent, lean diagnostic runbook: highly executable, concisely written assuming Kubernetes competence, with a clear triage workflow and well-signaled one-level-deep references. The main defect is that the referenced bundle files (references/failure-patterns.md and scripts/diagnose.sh) are not present, leaving broken deep links.

Suggestions

Add the missing bundle files so the references resolve, or remove the references and inline the essential per-service failure patterns and the diagnose.sh logic.

Add a brief explicit remediation/validation loop after triage (e.g. 'confirm the issue is resolved by re-checking restart count and --since=300s logs') to close the workflow with a feedback checkpoint.

Consider moving the large queue-name/consumer-group reference table into references/failure-patterns.md or a dedicated references file to keep the overview leaner.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable kubectl/redis-cli commands and operationally useful facts (queue keys, consumer groups, env vars) with almost no padding or explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Provides copy-paste-ready, fully executable commands covering the common diagnostic cases, including exact jsonpath expressions, redis INFO fields, and stream-inspection commands with clear placeholders.	5 / 5
Workflow Clarity	Opens with an explicit ordered triage sequence ('Run these three commands first', then 'narrow down') plus validation checkpoints (distinguishing ongoing vs historical issues, verifying Helm values took effect), but stops at diagnosis without an explicit remediation feedback loop.	4 / 5
Progressive Disclosure	Well-structured with clear section headers and one-level-deep references ('see references/failure-patterns.md', '{baseDir}/scripts/diagnose.sh') that are clearly signaled, but those referenced bundle directories do not exist on disk, which is more than a minor organization gap and prevents a 5.	4 / 5
	Total	18 / 20 Passed

Description

78%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 highly specific and distinctive, anchored to a concrete namespace and real failure-mode trigger terms that an on-call engineer would naturally use. Its main weakness is an implied rather than explicitly stated capability verb, leaving the 'what' slightly under-specified relative to the strong 'when'.

Suggestions

Lead with an explicit action verb stating what the skill does, e.g. 'Diagnoses and triages failures in the Buttercup platform running in the crs namespace.'

Add a couple of natural-language synonyms for trigger terms (e.g. 'pod crashes', 'tasks stuck') alongside the technical terms to broaden keyword coverage.

Consider mentioning the diagnostic script or triage snapshot as a concrete capability so the 'what' is explicit, not just implied.

Dimension	Reasoning	Score
Specificity	Names the concrete domain ('crs namespace' pods) and several specific failure conditions (CrashLoopBackOff, OOMKilled, cascade failure, Redis AOF warnings) rather than vague language, with minor coverage gaps.	4 / 5
Completeness	Provides a strong explicit 'Use when...' clause with concrete triggers, and an implied-but-clear 'what' (debug Buttercup in crs namespace) supplied by context; the 'what' could be stated more explicitly with a verb.	4 / 5
Trigger Term Quality	Uses natural on-call terms an SRE would actually say (CrashLoopBackOff, OOMKilled, cascade failure, Redis unresponsive, AOF warnings), with a few common synonyms/variations missing.	4 / 5
Distinctiveness Conflict Risk	A clear niche scoped to the 'crs' namespace with Buttercup-specific failure-mode triggers, giving it minimal overlap or conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/debug-buttercup/SKILL.md
Commit: 57c135b

Reviewed: 3 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.