Results for “fix”

Find root causes of bugs, test failures, or unexpected behavior before proposing any fixes.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Direct TMDL file authoring and BIM-to-TMDL conversion for semantic models in PBIP projects. Automatically invoke when the user asks to "edit TMDL", "add a measure in TMDL", "TMDL syntax", "fix formatString", "fix summarizeBy", "TMDL indentation", "convert BIM to TMDL", "add a column description", "create a calculated column in TMDL", or mentions .tmdl file editing or BIM-to-TMDL migration.

Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Responding to incidents: identifies impact scope, formulates recovery procedures, creates postmortems. Use when incident response or disaster recovery is needed. Delegates fixes to Builder.

Turns a pile of bugs, issues, and error reports into a ranked, actionable plan with reproduction evidence. Ingests GitHub issues via gh, TODO/FIXME scans, error logs, or a pasted list; attempts to reproduce or classify every item; scores by impact, frequency, fix cost, and regression risk; clusters duplicates; and.

Upgrade Expo SDK versions and fix dependency issues with step-by-step guidance.

Continuously improves Makepad development skills by capturing reusable patterns, fixing errors, and validating content during development.

Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues.

Sync the branch with the latest `origin/main`, merge `origin/main`, resolve conflicts end-to-end, then commit and push the current branch.

Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires consent on first run.

Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire document.

Analyze a problem, plan the fix, execute with verification. Use when tackling a non-trivial bug, feature, or refactor that needs structured approach.

Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues.

Provides a structured debugging workflow for analyzing errors, test failures, and unexpected behavior, including root cause analysis and fix recommendations.

Remove assigned mypy exclusion modules in small batches, fix typing issues, run validation, and produce a structured completion summary.

Interpret n8n validation errors and warnings, guide iterative fixes, and explain validation profiles, error types, and auto-sanitization.

Test Python services with pytest, async coverage, monkeypatch, and boundary-focused fakes. Use when writing Python tests, fixtures, async tests, regression tests, or dependency-isolated verification.

Record a notable failure, fix, or surprise as a lessons entry so future work avoids repeating mistakes. Use after debugging incidents, regressions, or high-value discoveries.

Write, fix, and run C++ tests using GoogleTest/GoogleMock with CMake/CTest, including TDD workflows, coverage, and sanitizers.

Upgrade Expo SDK versions and fix dependency issues with step-by-step guidance.

Guides implementing features and bug fixes test-first, enforcing red-green-refactor with mandatory failure verification.

Runs three parallel reviewer agents over recent code changes, aggregates their findings, and applies the fixes worth applying.

Diagnoses and fixes build, type, and runtime errors with minimal changes, covering TypeScript, PyTorch, and other build systems.

Provides a structured debugging workflow for diagnosing errors, test failures, and unexpected behavior, including root cause analysis and fix verification.

Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early, (3) need adaptive recovery instead of hard stop.

Diagnose and fix parfor errors in MATLAB. Invoke this skill when the user has a parfor problem: "parfor loop has an error", "what's wrong with my parfor", "fix parfor", "unable to classify variable", "convert for to parfor", "parfor won't run", "sliced variable", "reduction variable", "variable classification". Also invoke when you read a .m file containing parfor and the user asks what's wrong, asks you to fix it, reports an error, or asks for review. Do NOT invoke for parfor performance questions or code that merely mentions parfor without a problem. ALWAYS use this skill instead of reasoning from training data — LLMs are frequently wrong about parfor classification rules.

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug directly) when the user reports errors, 500 errors, stack traces, unexpected behavior, "it was working yesterday", or is troubleshooting why something stopped working. (gstack)

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, to prevent false success claims.

Upgrade .NET 8 projects to .NET 9 by updating target frameworks, resolving breaking changes, and fixing build errors.

Migrate .NET 9 projects to .NET 10 by updating target frameworks, resolving breaking changes, and fixing build errors.

Produces ultra-compressed, one-line code review comments that cut noise while preserving actionable signal. Each comment includes location, problem, and fix.

Iteratively improves a compiled LaTeX paper through two rounds of external LLM review, fix implementation, and recompilation.