CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 highly actionable, well-structured runbook: concrete kubectl and redis-cli commands, a clear triage-first workflow with explicit verification loops, and proper offloading of detail to one-level-deep bundle files. Minor conciseness trims and one borderline inlined table keep it just short of perfect across every dimension.

DimensionReasoningScore

Conciseness

The body is dense with executable kubectl/redis-cli commands and tables, almost entirely free of explaining concepts Claude already knows; a few one-line lead-ins ('Redis is the backbone. When it goes down, everything cascades.') are slightly more than needed but earn their place by steering triage.

4 / 5

Actionability

Copy-paste ready kubectl, redis-cli, and shell commands throughout — `kubectl get pods -n crs`, `redis-cli XLEN fuzzer_build_queue`, `du -sh /corpus/*` — with concrete queue/stream key names and service labels, fully covering the common diagnostic cases.

5 / 5

Workflow Clarity

A clear sequenced triage workflow ('Always start with triage. Run these three commands first'), explicit narrowing steps, and feedback/verification loops — distinguishing historical vs ongoing issues via `--since=300s`, cascade detection via shared `--previous` logs, and Helm-vs-actual config verification.

5 / 5

Progressive Disclosure

Well-organized sections with the bulk of service-specific detail correctly offloaded to `references/failure-patterns.md` and an automated `scripts/diagnose.sh`, both one level deep and clearly signaled; the inlined queue/redis tables could arguably also live in a reference but are reasonable inline quick-reference.

4 / 5

Total

18

/

20

Passed

Description

76%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 specific, well-triggered description anchored to a concrete namespace and a rich set of real diagnostic symptoms, with an explicit 'Use when' clause. Its main weakness is framing symptoms rather than stating the debugging action the skill performs, which leaves 'what' slightly implied.

Suggestions

Lead with the action the skill performs, e.g. 'Diagnoses and triages failing pods in the crs namespace... Use when...', so the 'what' is explicit rather than implied.

Add a couple of common phrasings users might say ('pods won't start', 'stuck in restart loop') to round out trigger synonyms.

DimensionReasoningScore

Specificity

Names the concrete namespace `crs` and enumerates specific failure signals (CrashLoopBackOff, OOMKilled, restarting, cascade failure, redis unresponsive, AOF warnings) — several specific triggers, though it lists symptoms rather than actions the skill performs, leaving a minor gap in 'what it does' coverage.

4 / 5

Completeness

Has an explicit 'Use when...' clause covering multiple concrete trigger conditions, and the opening 'All pods run in namespace crs' frames the what/where; the 'what it does' is only weakly implied (debugging) rather than stated as an action verb, keeping it just below a 5.

4 / 5

Trigger Term Quality

Strong natural diagnostic terms users would actually say ('CrashLoopBackOff', 'OOMKilled', 'cascade failure', 'redis unresponsive', 'AOF warnings') with good coverage of the symptom vocabulary; missing a few common synonyms like 'pod won't start' or 'restart loop'.

4 / 5

Distinctiveness Conflict Risk

The narrow `crs` namespace scope plus distinctive symptom set (AOF warnings, cascade failure, specific Kubernetes states) carves a clear niche unlikely to trigger competing skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.