kinhluan-skills

Plugin kinhluan-skills from marketplace kinhluan in kinhluan/skills. Commands read from the repo's manifest — 7 days ago.

Skills (74)

• agent-browser

  Open, use, explore, and debug websites and Electron apps with the agent-browser CLI. Use when an agent must see or operate a real web page (navigate, click, fill, log in, extract), learn an unfamiliar web app, dogfood or bug-hunt it, debug console errors, failing requests, slow pages or React render

• agent-desktop

  Open, use, explore, and debug native desktop apps on macOS, Windows, or Linux with the agent-desktop CLI, through the OS accessibility tree. Use when an agent must launch an app, read its UI state, click, type, choose menus, handle dialogs or notifications, map an unfamiliar app, reproduce a desktop

• agent-expertise-protocol

  Design or review governance rules for expert agents, including authority boundaries, uncertainty, handoffs, escalation, and evidence standards. Use when defining agent roles or clarifying which actions require user approval; it is not automatically active outside an invoked governance task.

• ai-figure-generation

  Generate scientific figures, diagrams, and illustrations using AI image models (DALL-E, Midjourney, Stable Diffusion) from research content. Use when creating visuals for slides, papers, or posters. Converts technical concepts into publication-ready imagery through structured prompts.

• api-security

  Design, review, test, or harden REST, GraphQL, RPC, webhook, OAuth, and gateway security. Use for API authentication, object/function/property authorization, schemas, abuse controls, SSRF, inventory, rate limits, tokens, or OWASP API risk review.

• architecture-decision-records

  Create and manage Architecture Decision Records (ADRs) using MADR 4.0.0

• architecture-review

  Review C4 vs code, fitness functions, and architecture drift. Use when checking design-to-code sync, fitness-function coverage, or deciding whether a finding belongs to SE or SRE.

• art-of-war-software-engineering

  Evaluate a major software or product initiative across alignment, timing, technical terrain, accountable leadership, and delivery method. Use for build/buy/partner decisions, strategic timing, resource allocation, or a go/hold/stop review before committing substantial effort.

• browser-automation

  Build or operate browser automation, web extraction, Playwright workflows, and Manifest V3 extensions. Use for navigation, form filling, scraping, browser tests, Chrome extension design, or reliable DOM interaction with explicit safety and privacy controls.

• business-product-leadership

  Frame product strategy and decisions across customer problems, Jobs-to-Be-Done, value propositions, MVP scope, product economics, experiments, pricing, go-to-market, and adoption. Use when a product owner or founder needs an evidence-based decision and accountable next step.

• c4-level1-context

  Specialized in System Context diagrams (Level 1) with User Journey integration.

• c4-level2-container

  Create or review a C4 container diagram showing the separately runnable/deployable applications and data stores inside one software system, their responsibilities, technologies, and relationships. Use for C4 Level 2 architecture views, not physical deployment topology.

• c4-level3-component

  Specialized in Component diagrams (Level 3) with folder structure mapping.

• c4-level4-code

  Specialized in Code diagrams (Level 4) of the C4 model. Use this skill

• c4-model

  Professional C4 model architecture hub for "Design-to-Code Sync". Use this skill to navigate the C4 hierarchy, map diagrams to stakeholders, avoid architectural anti-patterns, and choose the right level for designing or documenting existing codebases.

• clean-architecture

  Design or refactor code boundaries so business policy does not depend on volatile frameworks, databases, UI, or infrastructure. Use for Clean/Hexagonal/Onion architecture, dependency-rule reviews, ports and adapters, use cases, component boundaries, or testability.

• cloud-security

  Cloud security best practices for AWS, GCP, and Azure. Use when securing cloud infrastructure, configuring IAM, hardening S3 buckets, setting up VPC security, compliance (SOC2, ISO 27001), or auditing cloud resources for misconfigurations.

• code-quality-gate

  Design, diagnose, or repair automated code quality gates using linters, type checkers, tests, coverage, SAST, and SonarQube or SonarCloud. Use when CI quality checks fail, a team needs a pre-merge policy, or static-analysis findings require triage.

• collaborative-engineering-agent

  Coordinate a bounded software change from intent through implementation, review, and verification while preserving user ownership and repository conventions. Use for multi-step engineering delivery, task breakdown, cross-discipline risk review, or preparing issue/PR artifacts.

• conference-paper

  Write conference papers (4-6 pages), poster abstracts, and prepare oral/poster presentations. Use when targeting conferences like NeurIPS, ICML, CVPR, ACL, IEEE venues, or preparing conference presentations.

• container-security

  Review or harden container images, runtimes, Kubernetes workloads, clusters, registries, and software supply chains. Use for Docker/Kubernetes security, image scanning, provenance, admission policy, RBAC, secrets, network policy, or runtime detection.

• database-design

  Design, review, or evolve database schemas and data access for relational (PostgreSQL, MySQL, Oracle) and wide-column or key-value stores (Cassandra, ScyllaDB, Redis). Use for data modeling, choosing keys, constraints and indexes, transaction isolation and locking, zero-downtime migrations, multi-te

• ddd-core

  Professional Strategic Domain-Driven Design (DDD) Hub. Use this skill

• ddd-patterns

  Select and design advanced Domain-Driven Design integration patterns such as anti-corruption layers, outbox/inbox, sagas, CQRS, and event sourcing. Use when bounded contexts need reliable coordination, translation, asynchronous consistency, or separate read/write models.

• ddd-tactical

  Model and review tactical Domain-Driven Design inside one bounded context using aggregates, entities, value objects, domain services, repositories, factories, and domain events. Use when code must enforce domain invariants or an anemic/overgrown domain model needs redesign.

• defense-prep

  Prepare for PhD or Master's thesis defense. Use when preparing defense presentation, anticipating committee questions, practicing oral defense, or structuring defense slides.

• dependency-management

  Keep libraries, frameworks, and runtimes current and free of exploitable vulnerabilities. Use when inventorying dependencies or generating an SBOM, checking end-of-life status, planning a framework or runtime upgrade (Java, Quarkus, Vert.x, Spring, Node, Python, Go), configuring Renovate or Dependab

• diffusion-release-tracking

  Analyze feature adoption through Rogers' Diffusion of Innovations and design evidence-based phased rollouts. Use when interpreting adopter behavior, deciding whether to expand a release cohort, or defining calibrated rollout criteria and stop conditions.

• docker-containerization

  Docker containerization best practices and patterns for production deployment. Multi-stage builds, security scanning, health checks, compose, BuildKit, and distroless images.

• dora-core

  Measure and improve software delivery performance with DORA's current five-metric throughput and instability model. Use when baselining one application or service, diagnosing delivery friction, selecting improvement experiments, or reviewing metric instrumentation.

• evolutionary-architecture

  Design and maintain architectures that support guided, incremental change.

• exam-rubric

  Grade CS work with an explicit rubric. Separate collaboration from plagiarism. Use when scoring exams, assignments, orals, lab reports, or suspected copied code.

• experiment-tracking

  Track, log, compare, and reproduce experiments. Use when running experiments, recording results, comparing baselines, debugging poor performance, analyzing results, or preparing results tables for a paper.

• federated-learning-dqn

  Federated learning with Deep Q-Networks for privacy-preserving optimization. Domain-specific skill — only route when user explicitly mentions federated learning, FL, DQN, or privacy-preserving distributed RL.

• git-workflow

  Design or apply a Git collaboration workflow, including trunk-based development, release branches, branch naming, commits, and tags. Use when a user is choosing a branching model, documenting repository conventions, preparing commits, or planning releases.

• golang-development

  Implement, review, debug, or modernize Go code and modules with idiomatic APIs, concurrency, error handling, testing, profiling, and tooling. Use for Go services, libraries, CLIs, goroutine/channel issues, module management, or performance work.

• internal-critique

  Self-review a paper or thesis chapter before sharing with advisor or submitting. Simulates tough reviewer feedback to identify weaknesses before external review. Use when finishing a draft, preparing for advisor meeting, or doing pre-submission sanity check.

• javascript-typescript

  Implement, review, debug, test, or modernize JavaScript and TypeScript for browsers, Node.js, services, and frontend applications. Use for typing, async behavior, React/UI code, package tooling, tests, runtime compatibility, or performance.

• journal-q1-polish

  Polish paper for Q1 journal submission (ISI/Scopus). Use after paper draft is complete — handles notation sync with thesis, De-AI/De-translation protocol, and Q1 results table standards.

• kinhluan-router

  Select the smallest set of relevant skills from the kinhluan collection. Use when the user asks to choose a skill, several domains overlap, or the correct specialist is unclear; route from current intent and evidence without forcing a universal workflow sequence.

• kubernetes-orchestration

  Kubernetes deployment and orchestration patterns

• merge-request-review

  Review a GitHub pull request, GitLab merge request, or local proposed change against its stated intent, or prepare your own PR for review. Use when the user asks for a PR/MR review, issue-link verification, risk assessment, an approve/request-changes recommendation, or help authoring and answering r

• milestone-tracker

  Track PhD/Master's milestones, deadlines, committee meetings, and research timeline. Use when planning PhD schedule, checking progress, preparing for committee meetings, managing submission deadlines, or when behind on timeline.

• paper-audit

  Audit a research paper against its public codebase to detect mismatches between claims and implementation. Use when reviewing papers with code, verifying reproducibility, or checking for implementation gaps. Inspired by Feynman's /audit workflow.

• paper-writing

  Write or structure academic papers, thesis chapters, or technical reports. Use when drafting a conference paper, journal article, thesis chapter, or any academic writing. Covers structure, academic tone, LaTeX, and section-by-section guidance.

• pasture

  Work well inside pasture, a macOS setup that runs several coding agents (Claude Code, Codex, Grok, Antigravity) side by side under herdr. Use when HERDR_ENV=1 or pasture-* commands exist, or when the user mentions pasture, herdr, the collie, parallel agents, pasture-task, pasture-duo, worktrees, Sap

• payment-systems

  Design, review, or debug systems that move money, such as wallets, payment gateways, checkout, payouts, refunds, and bank or card integrations. Use for money representation, double-entry ledgers, payment state machines, idempotency keys, timeouts with unknown outcome, retries, webhooks, outbox event

• penetration-testing

  Plan and conduct authorized, bounded penetration tests with non-destructive validation and defensible reporting. Use for a system the user owns or is explicitly authorized to assess, including rules of engagement, evidence collection, vulnerability verification, remediation, and retesting.

• phd-proposal

  Write, structure, or review a PhD/Master's research proposal. Use when drafting a research proposal, preparing for committee review, writing a thesis outline, or aligning methodology with academic requirements.

• problem-discovery

  Test whether a specific real-world problem is important enough to address before defining a solution or MVP. Use when evaluating product demand, refining a target segment, planning discovery research, or deciding whether to build, defer, pivot, or stop.

• product-analytics

  Product analytics and experimentation frameworks. Use for defining metrics, designing A/B tests, analyzing funnels and cohorts, measuring feature impact, and setting up analytics infrastructure.

• product-ux-research

  User research methods for product teams. Use for creating personas, journey mapping, usability testing, card sorting, and heuristic evaluation to build user-centered products.

• progress-report

  Write research progress reports for advisors, committee meetings, and funding agencies. Use when preparing monthly/quarterly reports, meeting notes with advisor, or annual progress summaries.

• proposal-defense

  Prepare for PhD/Master's proposal defense — slide structure, committee Q&A simulation, proposal presentation, and defense logistics. Use when preparing to defend your research proposal before the committee.

• publication-strategy

  Select a legitimate publication venue, verify current submission requirements, plan a submission, write a rebuttal, and manage revision or resubmission. Use for journal/conference selection, deadline planning, peer-review responses, camera-ready preparation, or publication-risk checks.

• python-development

  Implement, review, debug, test, package, or modernize Python applications and libraries. Use for Python typing, async code, FastAPI/Pydantic, data access, project tooling, dependency management, testing, or performance work.

• research-design

  Design a rigorous experiment protocol including methodology choice, baselines, metrics, ablation studies, and reproducibility plan. Use before running any experiment, when designing evaluation strategy, or when reviewing experimental validity.

• research-question

  Formulate research questions, hypotheses, and contribution statements from identified literature gaps. Use when defining a research problem, framing a thesis topic, identifying novelty, or writing the "contribution" section of a proposal or paper.

• research-watch

  Design, run, or maintain a recurring watch for new research papers, authors, citations, venues, and topic trends. Use when a user wants literature alerts, a periodic evidence digest, or an update process for a living literature review.

• research-workspace-standard

  Standardized directory structure and artifact management for agentic

• scheduling-algorithms

  Model, select, implement, or evaluate scheduling algorithms for operating systems, workflows, clusters, cloud resources, and real-time systems. Use for queues, DAG scheduling, preemption, fairness, deadlines, makespan, utilization, or scheduling research.

• second-brain-reflection

  Systematically extract lessons from tasks, compress them into reusable rules, and store them in the appropriate memory tier (Local, Global, or Private). Use this skill at the end of every major mission or experiment to build your 'Second Brain'. tags: ["knowledge-management", "reflection", "compress

• security-analysis

  Review code, configuration, dependencies, architecture, CI, or LLM/agent integrations for security vulnerabilities and missing controls. Use for secure code review, vulnerability and dependency-alert triage, OWASP-oriented audits, secrets handling, supply-chain and DevSecOps checks, prompt-injection

• slide-automation

  Create or update reproducible presentation decks from papers, theses, reports, Markdown, data, or figures using PowerPoint, Beamer, Marp, reveal.js, or repository tooling. Use when the user needs slide structure, automated deck generation, figure placement, or rendered-deck verification.

• socratic-teaching

  Teach CS by Socratic questions, one at a time, no lecture. Stop when the student can restate and apply the claim. Use when tutoring, teaching, or asked to học Socratic.

• sota-survey

  Conduct a rigorous state-of-the-art literature survey, scoping a question, searching primary scholarly sources, screening studies, extracting comparable evidence, synthesizing disagreements, and identifying defensible gaps. Use for literature reviews, related-work maps, or current-paper searches.

• tdd-red-green-refactor

  Drive implementation with TDD (red-green-refactor). Use when writing new behavior, fixing a bug, or refactoring behind a failing test first. pytest, Jest/Vitest, Go testing.

• technical-english-cs

  Expert guidance for writing high-quality Technical English in Computer

• technical-report

  Write technical reports — experiment reports, system design documents, code documentation, and internal research memos. Use when documenting technical work that doesn't fit paper format.

• thesis-writing

  Write PhD/Master's thesis — full chapter structure, literature review chapter, methodology chapter, results chapter, discussion chapter, and conclusion. Use when drafting thesis chapters, organizing thesis structure, or converting papers into thesis format.

• threat-modeling

  Security threat modeling and risk assessment using STRIDE, Attack Trees, and DREAD scoring. Use when designing secure architecture, conducting security design reviews, assessing risks, or creating threat models for applications, systems, or cloud infrastructure.

• vietnamese-cs-terminology

  Expert guidelines for translating Computer Science terminology into academic

• vietnamese-writing-standard

  Standard guidelines for Vietnamese orthography, punctuation, and professional

• why-strategic-rationale

  Establish the strategic rationale for a product or feature before building. Use this skill when evaluating a new product idea, justifying an initiative to stakeholders, validating whether a feature is worth building, or preparing a pitch document. Combines Value Proposition Canvas (structured analys

Hooks (1)

• UserPromptSubmit

  python3

Similar plugins