.github/skills/bug-report-formatter/SKILL.md
Format messy bug reports, error logs, stack traces, or casual defect descriptions into a structured, Jira-ready bug report. Classifies severity and priority automatically. Optionally creates a Jira Bug ticket via the Atlassian MCP. Use this skill whenever the user says "format this bug", "write a bug report", "turn this error into a Jira ticket", "file a bug from these logs", "clean up this defect report", "create a bug ticket", "I found a bug — help me report it", or pastes a stack trace or error log and asks what to do with it.
npx skillsauth add dneprokos/skills-examples bug-report-formatterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Turn messy input into a clean, structured bug report — ready to paste into Jira or filed directly via the Atlassian MCP.
Use it for requests like:
Do not use it for:
jira-mcp-assistant for tasks, stories, epics)api-test-scenario-generator)The user may provide any combination of:
If the input contains no indication of expected vs actual behavior and no steps to reproduce, ask the user for the missing pieces — but ask at most two clarifying questions in a single message. Never block on optional details like environment or app version; use Unknown instead.
Read references/severity-guidelines.md to propose:
State your reasoning briefly (one line). The user can override before the report is created.
Apply references/bug-report-template.md to produce a complete report with these sections:
[Area] Concise description of the failureInfer environment details from log headers or user-agent strings when possible. Mark anything that cannot be inferred as Unknown.
Display the full formatted report in a single fenced markdown block. Then ask:
Does this look good?
Offer exactly these two options:
OK — proceedEdit — I want to change somethingIf the user chooses Edit, apply their corrections and re-display the updated report. Do not proceed to step 5 until the user explicitly accepts the report.
After the user accepts the report, ask:
Do you want to create this as a Bug in Jira?
Offer exactly these two options:
Yes — create the Jira issueNo — I'll paste it manuallyIf Yes:
cloudId using getAccessibleAtlassianResources. If multiple sites exist, present them and ask the user to pick one.PROJ, QA, SCRUM).createJiraIssue with:
issueTypeName: "Bug"summary: the report title (without the [Area] prefix brackets if the tracker already scopes by project)description: the full formatted report body (use contentFormat: "markdown")additional_fields: { "priority": { "name": "<High|Medium|Low>" } }Unknown when they cannot be inferred.createJiraIssue returns an error, surface it exactly — do not guess at the issue URL.data-ai
Install and configure Windows Credential Manager style secret storage for PowerShell using SecretManagement and SecretStore. Use when users ask to install secret manager support, set up Credential Manager for GitHub token storage, or bootstrap GitHubToken for PR skills.
development
Generate a complete, compilable unit test file from an Analyst test plan and Architect strategy. Uses AAA pattern, language-specific frameworks (NUnit, JUnit 5, pytest, Vitest), correct mock/real dependency instantiation, constructor null-guard tests, parameterized tests, and setup/teardown hooks. Input is the Analyst JSON plan plus Architect strategy summary. Use when asked to generate test code, write test implementation, create test file, or implement tests from a plan. Also invoked as Phase 3 by the unit-test-generator agent.
development
Define the mocking strategy and assertion style for a unit test plan. Classifies each dependency as mock or real, resolves assertion framework and test file location from project patterns, lists constructor null-guard tests with expected exception types, and specifies abstraction interfaces for non-deterministic calls. Input is a JSON test plan from ut-analyst. Use when asked to define mocking strategy, plan test architecture, classify dependencies as mock vs real, or design test structure. Also invoked as Phase 2 by the unit-test-generator agent.
testing
Analyze a class or function and produce a structured JSON test plan. Classifies all dependencies (interface, abstract, valueObject, dto, primitive), detects non-deterministic calls, enumerates test cases using black-box techniques (Equivalence Partitioning, Boundary Value Analysis, Decision Table, State Transition), and lists constructor null-guard requirements. Use when asked to analyze a class for testing, create a test plan, classify dependencies, or produce test case inventory. Also invoked as Phase 1 by the unit-test-generator agent.