Coding & Dev Tools Agent Skills
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Coding & Dev Tools
9,772 skills
samyakjhaveri critique-swarm
Launches four parallel adversarial review agents covering security, scope, fidelity, and test gaps, then synthesizes findings into a ranked verdict for plans or feature branches.
0
samyakjhaveri scaffold-context
Generates a CONTEXT.md routing file for a specified project subdirectory, following the canonical anatomy and ensuring it meets size and content constraints.
0
samyakjhaveri paper-review-sim
Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.
0
samyakjhaveri hpc-code-reviewer
Reviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.
0
samyakjhaveri cuda-omp-translator
Reference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.
0
samyakjhaveri auto-paper-improvement-loop
Iteratively improves a compiled LaTeX paper through two rounds of external LLM review, fix implementation, and recompilation.
0
samyakjhaveri tdd
Guides test-driven development with a red-green-refactor loop, emphasizing behavior-focused tests and vertical slicing over horizontal test writing.
0 · bundle
samyakjhaveri diagnose
Runs a disciplined debugging loop for hard bugs and performance regressions, covering reproduction, hypothesis testing, instrumentation, fixing, and regression testing.
0
samyakjhaveri executing-plans
Loads an implementation plan, reviews it critically, executes each task with verification, and reports completion, stopping to ask for help when blocked.
0
samyakjhaveri code-review-graph
Scopes code-review blast radius and detects architectural hotspots using Tree-sitter AST analysis and GraphRAG, with an MCP server for graph-based analysis.
0
samyakjhaveri using-git-worktrees
Creates isolated git worktrees with smart directory selection and safety verification for feature work.
0
samyakjhaveri requesting-code-review
Dispatch a code-reviewer subagent to catch issues before they cascade, with guidance on when to request review and how to act on feedback.
0 · bundle
samyakjhaveri test-driven-development
Guides implementing features and bug fixes test-first, enforcing the red-green-refactor cycle with mandatory failure verification.
0 · bundle
samyakjhaveri subagent-driven-development
Executes implementation plans by dispatching a fresh subagent per task and running two-stage reviews for spec compliance and code quality.
0 · bundle
samyakjhaveri finishing-a-development-branch
Guides completing development work by verifying tests, presenting structured options for merging, creating a pull request, keeping, or discarding a branch, and cleaning up worktrees.
0
samyakjhaveri verification-before-completion
Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, ensuring evidence precedes any success claims.
0
neuralblitz bdd
Writes Behavior-Driven Development scenarios using Gherkin syntax to create executable specifications and test behavior.
1
neuralblitz ddd
Designs bounded contexts, creates domain models, uses aggregates, and implements value objects for complex domain logic.
1
neuralblitz android
Develops native Android apps with Kotlin and Java, covering UI, performance, and Play Store deployment.
1
neuralblitz caching
Implements multi-level caching with strategies for invalidation, stampede prevention, and performance monitoring.
1
neuralblitz automata
Implements finite automata, regular expressions, parsers, and lexers for building text processors and pattern matchers.
1
neuralblitz debugging
Debug application issues with techniques for Python, JavaScript, performance profiling, production incidents, and network problems.
1
neuralblitz api-design
Design clean REST APIs with proper resource modeling, HTTP methods, pagination, versioning, and OpenAPI documentation.
1
neuralblitz clean-code
Improves code readability and maintainability by applying SOLID principles, meaningful naming, small functions, proper error handling, and DRY practices.
1
neuralblitz api-gateway
Designs API gateway architecture and implements routing, authentication, rate limiting, transformation, caching, logging, and circuit breaking.
1
neuralblitz application
Designs application architecture, selects patterns, structures code modules, and manages dependencies for new projects.
1
neuralblitz build-tools
Automates multi-language software builds with Makefiles, dependency management, testing, packaging, and CI/CD integration.
1
neuralblitz code-review
Provides code review best practices, checklists, and example feedback for quality, security, performance, and maintainability.
1
neuralblitz browser-apis
Provides design patterns and architectural approaches for implementing and integrating browser APIs in software projects.
1
neuralblitz code-quality
Measures code quality, identifies code smells, and implements quality gates using static analysis and technical debt tracking.
1
neuralblitz coding-agent
Runs Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
1
neuralblitz anti-patterns
Identifies common software anti-patterns in code and suggests refactoring solutions to improve code quality.
1
mariadb-corporation mariadb-show
Explains MariaDB-specific SHOW statement syntax, including replication terminology, filtering rules, and diagnostic commands like SHOW EXPLAIN and SHOW ANALYZE.
0
mariadb-corporation mariadb-grant
Documents MariaDB-specific GRANT behavior, including privilege scope levels, implicit account creation, MariaDB-only privileges, roles, proxy grants, resource limits, and TLS options, to help write accurate GRANT statements.
0
mariadb-corporation mariadb-delete
Covers MariaDB-specific DELETE syntax and behavior, including RETURNING, multi-table forms, temporal-table deletion, and DELETE vs TRUNCATE differences.
0
mariadb-corporation mariadb-insert
Documents MariaDB-specific INSERT syntax and behavior, including RETURNING, ON DUPLICATE KEY UPDATE, INSERT IGNORE, and various forms and modifiers, to help write and review INSERT statements.
0
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include tdd, requesting-code-review, test-driven-development. Rankings shift as installs change; sort this page by "Most downloaded" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds add <owner>/<name>, or copy the file into your agent's skills directory.