Mohammad Sadeghian
Community@MSC72m
On a never-ending quest for knowledge and growth. I love diving deep into new concepts and finding ways to apply them to real-world problems
Agent Skills by Mohammad Sadeghian
Showing 66 vetted skills indexed across 1 GitHub repositories.
MSC72mdomain-modeling
Build and maintain project domain glossaries and architecture decision records.
MSC72midea-refine
Refines raw ideas into actionable one-pagers through structured divergent and convergent thinking.
MSC72mdebugging-and-error-recovery
Diagnose test failures, build errors, and runtime bugs through structured root-cause triage.
MSC72musing-agent-skills
Discovers and routes tasks to the appropriate engineering workflow skill.
MSC72msetup-pre-commit
Configures Husky pre-commit hooks with lint-staged, Prettier, typecheck, and tests.
MSC72mtest-driven-development
Implements code changes using the red-green-refactor test-driven development loop.
MSC72mplanning-and-task-breakdown
Decomposes specifications into ordered, verifiable implementation tasks with acceptance criteria.
MSC72mwayfinder
Plans large efforts as decision tickets on an issue tracker.
MSC72mincremental-implementation
Implements multi-file code changes in thin, tested, committed vertical slices.
MSC72msetup-matt-pocock-skills
Configures a repository's issue tracker, triage labels, and domain doc layout for engineering skills.
MSC72msetup-ts-deep-modules
Configures dependency-cruiser to enforce deep-module package boundaries in TypeScript repositories.
MSC72mvercel-react-native-skills
Applies React Native and Expo performance rules to mobile app code.
MSC72mwriting-for-agents
Write skills, AGENTS.md, and CLAUDE.md documents that agents consume predictably.
MSC72mwait-what
Re-pitches the previous AI response in ASD-STE100 Simplified Technical English with added context.
MSC72mapi-and-interface-design
Designs stable REST APIs, TypeScript contracts, and idempotent endpoints with consistent error semantics.
MSC72mloop-me
Grills users with iterative questions to produce implementable workflow specifications.
MSC72mhandoff
Generates a conversation summary document for continuing work in a new agent session.
MSC72mdiagnosing-bugs
Diagnose hard bugs and performance regressions through a structured six-phase feedback-loop workflow.
MSC72mgit-guardrails-claude-code
Configure Claude Code hooks to block dangerous git commands before execution.
MSC72mcode-review
Reviews git diffs against coding standards and originating specs using parallel sub-agents.
MSC72mto-tickets
Breaks plans and specs into tracer-bullet tickets with declared blocking edges.
MSC72mask-matt
Routes engineering situations to the appropriate skill or workflow in the repository.
MSC72mwizard
Generate interactive bash wizards that walk humans through manual setup procedures.
MSC72mto-questionnaire
Generates a Markdown discovery questionnaire for a recipient who holds knowledge the user lacks.
Frequently Asked Questions About Mohammad Sadeghian
FAQPage SchemaWhat tasks can I accomplish using MSC72m's skills?▼
The 74 skills cover test-driven development, root-cause debugging, multi-axis code review, spec-driven planning, ticket breakdown, incremental implementation, merge-conflict resolution, React/Next.js performance optimization, accessibility review, security hardening, observability instrumentation, deprecation and migration, and writing ADRs and domain documentation.
Who are these skills designed for?▼
Software engineers and engineering leads working in TypeScript, React, Next.js, or React Native codebases who want disciplined practices: red-green-refactor testing, deep-module design, pre-launch checklists, git guardrails, and adversarial review of high-stakes decisions like production auth or irreversible migrations.
How do I install and run these skills?▼
Skills are invoked by an agent when their trigger conditions match, such as failing tests or a review request. Some are user-invoked only (disable-model-invocation). The setup-matt-pocock-skills skill configures the repo's issue tracker, triage labels, and domain doc layout before first use of the engineering skills.
Are these skills open source and what do they cost?▼
The Vercel-authored skills (react-best-practices, react-native-skills, composition-patterns, view-transitions) carry MIT licenses at no cost. The pr skill credits Humanlayer's show-me skill. Remaining skills in the manifest declare no license, so treat them as unlicensed until the repository states otherwise.
What prerequisites or dependencies do these skills require?▼
browser-testing-with-devtools requires the chrome-devtools MCP server configured. setup-pre-commit needs Husky, lint-staged, and Prettier. setup-ts-deep-modules wires dependency-cruiser into a TypeScript repo. migrate-to-shoehorn targets @total-typescript/shoehorn. sync-agent-skills uses DevForge across Pi, OMP, Claude Code, OpenCode, and Codex.