Doublefin avatar

Doublefin

Official

@visdomtech · United States of America

0Followers
|
6Public Repos
|
25Published Skills

Doublefin provides 27 engineering discipline skills covering test-driven development, multi-agent code review, security hardening, and production launch readiness.

Skills Distribution
DomainDeveloper To...Software Engineeri.. (40%)Code Review & Qual.. (25%)Security & Perform.. (15%)Planning & Require.. (12%)

Agent Skills by Doublefin

Showing 25 vetted skills indexed across 1 GitHub repositories.

visdomtechvisdomtech

idea-refine

Refines raw ideas into actionable concepts through structured divergent and convergent thinking.

Official
Intermediate
visdomtechvisdomtech

debugging-and-error-recovery

Diagnose test failures, build errors, and runtime bugs through systematic root-cause triage.

Official
Intermediate
visdomtechvisdomtech

test-driven-development

Implements code changes using the red-green-refactor test-driven development loop.

Official
Intermediate
visdomtechvisdomtech

planning-and-task-breakdown

Decompose specifications into ordered, verifiable implementation tasks with acceptance criteria.

Official
Intermediate
visdomtechvisdomtech

incremental-implementation

Implements multi-file code changes in thin, tested, committed vertical slices.

Official
Intermediate
visdomtechvisdomtech

api-and-interface-design

Design stable REST APIs, TypeScript interfaces, and module contracts with consistent error semantics.

Official
Intermediate
visdomtechvisdomtech

multi-agent-planning

Synthesizes three parallel design agent proposals into one read-only implementation plan.

Official
Advanced
visdomtechvisdomtech

context-engineering

Configures rules files, specs, and context budgets for AI coding agents.

Official
Intermediate
visdomtechvisdomtech

frontend-ui-engineering

Build accessible, responsive React components and pages following design system standards.

Official
Intermediate
visdomtechvisdomtech

shipping-and-launch

Guides production launches with pre-launch checklists, staged rollouts, monitoring, and rollback plans.

Official
Intermediate
visdomtechvisdomtech

spec-driven-development

Creates structured specifications and capability maps before writing any code.

Official
Intermediate
visdomtechvisdomtech

multi-agent-review

Dispatches seven parallel review agents to audit code changes with build verification and readiness scoring.

Official
Advanced
visdomtechvisdomtech

dev-cycle

Executes a plan, TDD implement, review, and simplify pipeline for multi-file code changes.

Official
Advanced
visdomtechvisdomtech

as-goal

Orchestrates an autonomous multi-role agent pipeline that iterates until measurable exit gates pass.

Official
Advanced
visdomtechvisdomtech

deprecation-and-migration

Plans deprecation and incremental migration of legacy systems, APIs, and database schemas.

Official
Intermediate
visdomtechvisdomtech

observability-and-instrumentation

Instruments production code with structured logging, metrics, tracing, and alerting.

Official
Advanced
visdomtechvisdomtech

interview-me

Extracts underlying user intent through one-question-at-a-time interviews before planning or coding.

Official
Intermediate
visdomtechvisdomtech

doubt-driven-development

Subjects non-trivial decisions to fresh-context adversarial review before they stand.

Official
Advanced
visdomtechvisdomtech

source-driven-development

Verifies framework code against official documentation and cites sources for every implementation decision.

Official
Intermediate
visdomtechvisdomtech

performance-optimization

Diagnose and fix frontend, backend, and database performance bottlenecks through measurement-driven workflows.

Official
Advanced
visdomtechvisdomtech

browser-testing-with-devtools

Tests and debugs web pages in real browsers using Chrome DevTools MCP.

Official
Intermediate
visdomtechvisdomtech

pr-review

Reviews GitHub PRs and local commits with parallel multi-agent analysis and automated fix loops.

Official
Advanced
visdomtechvisdomtech

git-workflow-and-versioning

Structures git commits, branching, worktrees, and semantic versioning for code changes.

Official
Intermediate
visdomtechvisdomtech

adhd

Generates divergent coding ideas through parallel isolated cognitive frames with scoring and clustering.

Official
Advanced

Frequently Asked Questions About Doublefin

FAQPage Schema
What tasks can I accomplish using Doublefin's skills?▼

Doublefin's 27 skills cover the full engineering lifecycle: spec drafting, task breakdown, test-driven development, incremental implementation, multi-agent code review, security hardening against the OWASP Top Ten, performance optimization, observability instrumentation, deprecation management, and production launch preparation with rollback strategies.

Who are Doublefin's skills designed for?▼

The skills target software engineers and coding agents handling non-trivial, multi-file changes. They serve developers who need systematic debugging, adversarial decision review, WCAG-compliant frontend builds, semantic versioning, and evidence-based production readiness rather than ad-hoc code generation.

How do Doublefin's multi-agent review skills work in practice?▼

The pr-review skill runs 3 parallel agents (completeness, correctness, impact) on GitHub PRs or local commits, while multi-agent-review escalates to 7 specialized agents covering architecture, security, performance, and lifecycle. Findings are driven to resolution via the dev-cycle pipeline with re-review.

Are Doublefin's skills open source and what do they cost?▼

The skills are publicly available in Doublefin's GitHub registry at no cost. The adhd divergent-ideation skill explicitly carries an MIT license, permitting free use, modification, and redistribution in personal and commercial projects.

What prerequisites or dependencies do Doublefin's skills require?▼

Most skills are self-contained methodology guides requiring no external dependencies. The browser-testing-with-devtools skill specifically requires the chrome-devtools MCP server to be configured for DOM inspection, console error capture, network analysis, and real-browser performance profiling.