CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-fixing-prod-issues

Debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, then raises a PR with evidence. Use when the user wants to fix a production call bug, investigate a failing prod call, reproduce and fix a production issue, run regression tests before a PR, or says things like "fix this prod call issue", "debug and fix call ID", "test my fix against prod scenarios", "reproduce this production bug", or "regression test before raising PR".

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 a lean, well-sequenced overview with strong validation gates, but its actionability and progressive disclosure are undermined because all six referenced phase files are missing from the bundle and the body itself carries almost no executable detail.

Suggestions

Add the missing phase1-debug.md through phase6-pr.md files (or inline the per-phase executable steps) so the referenced navigation resolves and the skill becomes actionable.

Include concrete commands/code in each phase (e.g., the Cekura API calls to fetch the prod call, build/attach evaluators, run evals, and retrieve result URLs) rather than high-level descriptions.

Verify every relative link in the phase table points to an existing file before shipping.

DimensionReasoningScore

Conciseness

The body is lean — a phase diagram, a mapping table, and terse strictness rules — with no padding and no explanation of concepts Claude already knows; every line enforces the workflow rather than filling space, matching the 5 anchor.

5 / 5

Actionability

Guidance is high-level ('Build evaluator, attach metrics, run', 'Fetch prod call + logs') with only one concrete executable artifact (`GET /test_framework/v1/ai-agents/{id}/`); the specific steps to execute live in the referenced phase files, which are absent, so it falls to the 2 anchor for minimal concrete guidance with missing execution steps.

2 / 5

Workflow Clarity

A clear 6-phase sequence with explicit validation gates ('eval must fail before any fix', 'eval must pass now', 'Never push code until Phase 5 is complete'), a reproduce→fix→verify feedback loop, and an error-recovery ask-when-in-doubt rule, matching the 5 anchor.

5 / 5

Progressive Disclosure

Structure is well designed — an overview table signals one-level-deep phase-file references — but none of the six referenced files (phase1-debug.md … phase6-pr.md) exist in the bundle, so navigation is broken; per the guideline to score against the actual bundle, dead references pull it down to the 3 anchor.

3 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: third-person voice, comprehensive concrete actions, rich natural trigger phrases, and a clear what+when structure scoped to a distinct Cekura niche. It matches the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, then raises a PR with evidence' — giving comprehensive coverage of the skill's capabilities, matching the 5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (debug → reproduce → fix → verify → regression → PR) and 'when' via a concrete 'Use when...' clause with multiple trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms and variations: 'fix this prod call issue', 'debug and fix call ID', 'test my fix against prod scenarios', 'reproduce this production bug', 'regression test before raising PR', plus 'prod call'/'production call' variants — matching the 5 anchor for natural term coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Cekura production-call bug fixing with a regression-gated PR workflow) with distinct triggers tied to prod calls and Cekura evaluators, giving minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 missing

Warning

Total

15

/

16

Passed

Repository
cekura-ai/cekura-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.