digitaldreams
UserMy dev identity as a Claude Code plugin — a full Laravel team in a box: SDLC pipeline, task board, coding agents, and audit skills.
Categories
Indexed Skills (25)
api-contract
Designs the REST API contract from tasks/requirements.md, tasks/system_design.md and tasks/system_model.md, writing tasks/api_contract.md. Use whenever the user says "api contract", "design the api", "api spec", "endpoint design", or as the SDLC pipeline step between system-modeling and task-breakdown.
architecture
Creates a practical web architecture design from analyzed requirements, with interactive decision checkpoints — the user picks ecosystem, pattern, and repo strategy from recommended options. Reads tasks/requirements.md and writes tasks/architecture.md. Use whenever the user says "design the architecture", "architecture doc", "create architecture.md", or as the SDLC pipeline step after requirement analysis.
blast-radius
Trace the full impact of a proposed change or deletion before anything is edited. Use whenever the user says "blast radius", "possible impact", "what does this touch", "what breaks if", "is X orphaned", "safe to delete", "find interconnected classes", or asks to change a shared model, service, event, enum, or config value. Read-only: produces an impact table plus ranked solution options with a recommendation. Never applies the change itself. Required before any modification to code used by more than one feature.
code-standards
The binding, numbered definition of good code for this codebase. Generation agents read it BEFORE writing any code; review skills cite violations by rule id (CS-n). Use whenever the user says "code standards", "what is good code", "coding rules", or before generating application code in any pipeline step.
deployment
Produces a release procedure for the current application, writing tasks/deployment.md. Inspects the repo (CI config, .env.example, migrations, queue/scheduler usage) plus tasks/architecture.md when present. Use whenever the user says "deployment plan", "release checklist", "how do we ship this", "prepare for production", or as the end-of-pipeline SDLC step.
design-system
Analyzes the project and generates a custom, opinionated design system with Tailwind CSS CSS-first configuration (@theme), writing tasks/design_system.md from requirements, wireframes, information architecture, and the frozen architecture. Use whenever the user says "design system", "design tokens", or "set up the Tailwind theme".
information-architecture
Generates the information architecture — sitemap, page inventory, navigation, access control, URL rules — from tasks/user_journeys.md and tasks/requirements.md, writing tasks/information_architecture.md. Use whenever the user says "information architecture", "IA", "site map", or "navigation structure".
log-analyzer
Laravel log file analyzer for expert-level bug diagnosis. Use this skill whenever the user mentions 'laravel.log', 'check the log', 'analyze logs', 'log file', 'there's an error in the log', or asks to diagnose, investigate, or fix a bug from a Laravel log file. Triggers on any mention of Laravel errors, exceptions, undefined variable errors, or stack traces from a Laravel application. This skill reads the log file, isolates actionable errors (ignoring INFO/DEBUG/routine logs), identifies the root cause by tracing into App-namespaced source files, inspects database table structure when model-related, and recommends a minimal, pattern-consistent fix. Always use this skill before attempting to diagnose any Laravel bug from a log.
manual-test-cases
Write or review manual test cases that a non-technical product owner can execute by following exact click paths. Use whenever the user says "manual test cases", "test cases for product owner", "steps a non-tester can follow", "review the test cases", or asks for human-runnable test documentation. Every named entity is validated against seeders before delivery; ambiguous steps are rejected and rewritten. Output goes to tasks/manual_test_cases.md.
performance-audit
Laravel performance sweep of the current codebase, writing ranked findings to tasks/performance_audit.md. Hunts N+1 queries, missing indexes, cache opportunities, sync work that belongs on queues, and oversized payloads. Use whenever the user says "performance audit", "why is it slow", "find N+1", "optimize queries", or before a release. Standalone — no pipeline docs needed.
readability-sweep
Three-pass readability cleanup of application source: remove inline comments, extract cohesive blocks into intent-named private methods, and challenge every class and method name. Use whenever the user says "readability sweep", "no inline comments", "remove comments", "check naming", "make the code readable", "extract private methods", or asks to scan the project for readability violations. Edits allowed. Scope is application source only (not tests/config) unless told otherwise. Runs lint and the full test suite after changes.
red-first
Regression-test-first bug fixing: reproduce, write a failing test that proves the bug, show it red, then fix to green with the minimal pattern-consistent change. Use whenever the user reports a bug, pastes failing behavior or a stack trace, or says "fix this bug", "found a bug", "write the failing regression test", "prove the bug first". A bug is not fixed until a test proves it was real. When a log file is the evidence, delegate diagnosis to the log-analyzer skill, then return here for the test-first fix.
requirement-intake
Turns an untagged task on the board — a paragraph of intent — into an approved, executable plan before any code is written. Covers the workflow/ scratch folder, the questions protocol, sizing, and what must be exported before a task can finish. Use when a board task has no [tag], or when asked how requirements become plans.
requirements
Brutally honest requirements analysis. Reads tasks/requirements.md, tears it apart, asks the user the top blocking questions interactively, discovers components, adds competitor analysis, and writes tasks/requirement_analysis.md ending with rewritten drop-in requirements. Use whenever the user says "analyze requirements", "requirement analysis", "review my requirements", or hands over a raw requirements document as the first step of the SDLC pipeline.
review
Review procedure for task PRs — deterministic tool output first, LLM judgment second, verdict on the board. Use when reviewing a task's pull request or when asked for a task-agent review.
security-audit
Security audit of the user's own codebase, two modes. FIND mode: adversary persona hunts every real security hole in scope and writes them to tasks/security_risks_{date}.md. VALIDATE mode: a fresh security-specialist persona verifies each reported finding was real and each implemented fix is correct. Use whenever the user says "security audit", "red team", "find security issues", "security holes", "act as a bad guy", "attack the app", "validate the security fixes", or "verify the security report". Authorization context: the user owns this codebase and is auditing it for defensive hardening.
system-design
Turns frozen architecture decisions into a behavioral blueprint: component contracts, API design, key flows, data flow, applied patterns, failure handling. Reads tasks/architecture.md and tasks/requirements.md, writes tasks/system_design.md. Use whenever the user says "system design", "create the system design doc", or as the SDLC pipeline step after architecture.
system-modeling
Renders the frozen system design as UML diagrams: sequence diagrams from key flows, state diagrams for stateful entities, ERD from the entity list, class diagram for the domain model. Reads tasks/system_design.md, writes tasks/system_model.md. Use whenever the user says "system modeling", "UML diagrams", "sequence diagram", "state diagram", "ERD", or "model the system".
task-breakdown
Breaks analyzed requirements down into Epics and vertically-sliced actionable tasks, writing the tasks/epics.md planning document from requirements, architecture, system design, IA, and journeys. Use whenever the user says "break down the requirements", "epics and tasks", or "create the development task breakdown". Never writes tasks/tasks.md — that board belongs to the task-manager agent, which converts epics into board tasks.
task-workflow
Core loop for executing tasks from the tasks.md board — claim, plan checkpoint, worktree, implement, quality gates, draft PR, bounded review-and-fix rounds, optional gated merge, human notification. Use whenever asked to work the task board, run the next task, or continue a task in progress.
understand
Build a complete mental model of a codebase, module, or feature before any change is discussed. Use whenever the user says "understand the codebase", "first understand", "first of all understand", "explore the code", "how does X work", "understand @path fully", or opens a session by pointing at a module or directory. Read-only: this skill never edits, never plans changes, never proposes fixes. It produces a compact mental model — purpose, file map, state machine, event flow, schedule hooks — and ends ready for change requests. Always run this before planning any modification.
user-journey-map
Designs the intended user journeys for an unbuilt product: personas, current workarounds, step-by-step flows with screens and expected friction, writing tasks/user_journeys.md. Use whenever the user says "user journey", "journey map", or "map the user flows".
vsa
Vertical Slice Architecture guardian, two modes. PLACE mode: decide where a new class, event, DTO, or module belongs under VSA rules, or design a new module/slice map from scratch. AUDIT mode: scan for slice-isolation violations (cross-slice imports, cross-module coupling, misplaced events) and prescribe the move that fixes each. Use whenever the user says "VSA", "which slice", "where does this class go", "slice isolation", "organize the slices", "cross-slice import", "should this move to module root", or asks how to structure a feature in a slice-based codebase.
wireframe
Creates clean, focused wireframes showing layout and content structure for a named page, driven by tasks/information_architecture.md and tasks/user_journeys.md. Use whenever the user says "wireframe", "wireframe the X page", or "layout sketch". Pass the page name as the argument.
release-notes
Write or update developer-facing release notes for the current application. Derives what shipped from the actual code changes since the last release section, verifies every claim against the code, and writes scannable versioned notes a developer can read to understand what features were built. Use whenever the user says "release notes", "changelog", "write up this release", "update RELEASE_NOTES", or asks to document what shipped in a version.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.