MCP App StoreMCP App Store
from specialist-agent12
Generate and apply conventional commit messages with automatic type & scope detection plus pre-commit validation for secrets and debug artifacts.
This skill analyses a working tree/diff to auto-detect conventional-commit type and scope, generates a validated commit message (type(scope): description), warns about secrets or debug code, and can stage & execute the commit. It enforces formatting rules and helpful pre-commit checks to keep project history clean.
Use after completing a feature, bugfix, or refactor when you want a consistent conventional commit message and automated validation (secrets, console.log/debugger, file size warnings). Not for empty working trees.
Designed for developer-assistant agents and integrations with shell access (Claude Code, Cursor, Codex, or CLI-capable agents).
Smart Commit is a conventional commit generator skill that analyzes git changes, auto-detects commit type and scope from file patterns and diff content, validates for secrets and debug artifacts before committing, and then executes the commit. No bundled scripts — purely instruction-based. The SKILL.md is well-structured with clear steps, type/scope detection tables, validation checks, and even an anti-rationalization section to encourage good habits.
Clean, well-written skill with no security concerns. Purely declarative — no executable code, just instructions for the agent to follow. The pre-commit validation step (checking for .env files, console.log, debugger statements, large files) is a nice security touch. No network calls, no credential handling, no destructive commands beyond normal git operations. The anti-rationalization table is a thoughtful UX touch.
Test-Driven Development (TDD)
Run disciplined TDD cycles: write a failing test, implement the minimal fix, then refactor — for features and bugfixes where correctness matters.
/verify — Verification Before Completion
Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.
/learn — Interactive Learning Mode
Teaching-first implementation assistant: explains why decisions are made, walks through architecture, and produces incremental code with pedagogy for onboarding
Adaptive Planning (/plan)
Generate an implementation plan matched to task complexity — from quick mini-plans to full design documents — before writing code or making large changes.
Systematic Debug (/debug)
A four-phase, evidence-first debugging methodology agent skill: gather evidence, analyze patterns, formulate hypotheses, and implement & prove fixes.
Grill (Adversarial Code Challenge)
Performs adversarial stress-testing of code to find edge cases, race conditions, security holes, and logical flaws before deployment.
Conversion Rate Optimization (CRO)
Audit landing pages and user flows to find conversion friction and deliver prioritized, testable A/B recommendations.
Migration: Migrate Module
Automates a multi-phase migration of an Angular module to a target architecture with approval gates and validation after each phase.
Next.js: Migration — Migrate Component
Convert a Next.js Pages Router component/page to the App Router pattern, updating routing, data fetching, and component boundaries for Next.js App Router.
Review Review
Use when code changes need review before merge - validates architecture, types, security, and test coverage.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
GraphQL Inspector — Validate
Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
JJ Hunk
Programmatic hunk selection for Jujutsu (jj): list, split, commit, or squash specific hunks to enable partial commits and fine-grained history editing without a
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
Cursor Hello World Tutorial
A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr