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".

75

Quality

92%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill with excellent workflow clarity and progressive disclosure. The strictness rules are particularly valuable, providing non-obvious constraints (same transport medium, sequential gates, no push until Phase 5) that prevent common mistakes. The main weakness is that actionability depends entirely on the phase files, which are not provided — the overview itself contains no executable commands or concrete code examples.

Suggestions

Consider adding one concrete example command in the overview (e.g., the API call to fetch the agent record mentioned in Rule 0) so the skill has at least some directly actionable content without needing to open phase files.

DimensionReasoningScore

Conciseness

Every section earns its place. The ASCII phase diagram, the table, and the strictness rules all convey unique, non-obvious information. There's no explanation of concepts Claude already knows — it jumps straight into the workflow and constraints.

3 / 3

Actionability

The skill provides clear phase structure and strict rules, but the actual executable guidance (specific commands, API calls, code snippets) is deferred entirely to the phase files. The main file itself contains no concrete commands or copy-paste-ready examples — it's an overview that relies on referenced files for actionability.

2 / 3

Workflow Clarity

The 6-phase workflow is clearly sequenced with explicit gates between phases, validation checkpoints (eval must fail in Phase 2, must pass in Phase 4), feedback loops (stop and ask if uncertain), and a strict no-push-until-Phase-5 rule. The strictness rules add robust error prevention.

3 / 3

Progressive Disclosure

The SKILL.md is a clean overview with a well-organized table linking to six one-level-deep phase files. Each phase file is clearly signaled with its purpose. The main file contains only what's needed at the top level (workflow overview + strictness rules) while deferring details appropriately.

3 / 3

Total

11

/

12

Passed

Description

100%

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 an excellent skill description that clearly articulates a specific multi-step workflow for debugging production call issues. It provides comprehensive trigger terms covering natural user phrasings and explicitly states both what the skill does and when to use it. The domain-specific terminology (Cekura evaluators, production calls) makes it highly distinctive.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions in sequence: debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, and raises a PR with evidence. These are detailed, actionable steps.

3 / 3

Completeness

Clearly answers both 'what does this do' (debugs, reproduces, fixes, verifies, runs regression tests, raises PR) and 'when should Claude use it' with an explicit 'Use when...' clause containing multiple trigger scenarios and example phrases.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms including 'fix this prod call issue', 'debug and fix call ID', 'reproduce this production bug', 'regression test before raising PR', plus variations like 'production call bug', 'failing prod call', and 'test my fix against prod scenarios'.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: production call debugging with Cekura evaluators, regression testing, and PR creation with evidence. The domain-specific terms like 'Cekura evaluators', 'production call', and the specific workflow make it unlikely to conflict with generic debugging or PR skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

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.