heru-agent-skills

Plugin heru-agent-skills from marketplace heru-agent-skills in heruumhmd/my-agent-skills. Commands read from the repo's manifest — 19 days ago.

Skills (53)

• academic-journal-latex-workflow

  Use when drafting, structuring, writing, formatting, or debugging academic journal papers, conference articles, or thesis chapters in LaTeX.

• agent-browser-automation

  Automates browser workflows using native Rust CDP clients and accessibility-tree snapshots. Use when scraping dynamic web pages, filling forms, running automated browser QA tests, or driving web sessions with compact @eN element references without raw DOM or screenshot token overhead.

• agent-memory-and-instincts

  Use when enforcing persistent architectural habits, distilling agent lessons, managing long-term agent memory, and avoiding repeated coding mistakes.

• agent-runtime-and-containerization

  Packages agent skills into hardened OCI containers, Kubernetes jobs, Agent-to-Agent (A2A) endpoints, and vendor-agnostic REST microservices (POST /run) using initializ/forge and skrun-dev/skrun. Use when packaging agent skills for production infrastructure, containerizing autonomous agent tasks for

• agentic-harness-patterns

  Applies production agent context harness engineering patterns to prevent context rot. Use when architecting long-running agent loops, managing working memory persistence with mutex locks, implementing Select-Writeback-Compress-Isolate operations, or consolidating tool schemas to save context tokens.

• api-and-interface-design

  Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

• applied-ml-system-design

  Use when designing machine learning architectures, choosing between heuristics vs classical ML vs deep learning vs LLMs, or designing inference pipelines.

• browser-testing-with-devtools

  Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MC

• ci-cd-and-automation

  Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

• code-archeology-and-anti-slop

  Enforces rigorous anti-slop engineering and deep codebase archeology. Use when investigating unfamiliar legacy systems, determining historical architectural intent via git history, tracing blast radius before proposing complex edits, or purging AI-generated verbosity, ceremonial wrappers, and specul

• code-review-and-quality

  Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when t

• code-simplification

  Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

• codebase-context-indexing

  Use when managing large codebases, indexing multi-file repositories, building local semantic code indexes, or retrieving pinpoint symbol definitions and dependencies for AI agents.

• codebase-knowledge-graph

  Constructs and navigates interactive AST and semantic knowledge graphs for massive repositories (>100k LOC). Use when exploring unfamiliar legacy codebases, querying dependency call-graphs (.ua/), running multi-subagent codebase mapping pipelines, or making targeted changes without loading entire re

• constraint-driven-development

  Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-i

• context-engineering

  Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

• debugging-and-error-recovery

  Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root caus

• deprecation-and-migration

  Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to

• documentation-and-adrs

  Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

• doubt-driven-development

  Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes

• frontend-ui-engineering

  Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-gene

• git-workflow-and-versioning

  Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work acro

• hyper-efficient-agent-architecture

  Use when orchestrating the 4-Engine Hyper-Efficient Agent Architecture (CodeAct, Actor-Critic, LangGraph Stateful Pipelines, and Speculative Drafting).

• idea-refine

  Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine th

• impeccable-frontend-design

  Eliminates generic AI slop from frontend user interfaces with deterministic design rules and design polish workflows. Use when crafting bespoke UI/UX, running design audits, eliminating generic AI patterns like default Inter fonts, purple-blue gradients, or nested card borders, or polishing web typo

• incremental-implementation

  Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, when you're about to write a large amount of code at once, or whe

• interview-me

  Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invo

• langgraph-stateful-agent-design

  Use when designing, implementing, or debugging multi-agent workflows, state machines, cyclical agent loops, human-in-the-loop validation, and persistent agent checkpoints.

• laravel-service-action-architecture

  Use when developing, refactoring, or architecting backend applications in Laravel and PHP following Thin Controller and Fat Action patterns.

• mcp-server-and-tool-integration

  Builds, tests, and deploys Model Context Protocol (MCP) servers and tool connectors. Use when creating custom MCP servers in TypeScript or Python, exposing databases, APIs, or local tools to AI agents, configuring stdio and SSE transports, or integrating official MCP reference servers.

• ml-data-preprocessing-and-leakage-prevention

  Use when preparing datasets, handling missing values, feature scaling, encoding categorical variables, or splitting data for machine learning.

• ml-model-evaluation-and-metrics

  Use when evaluating machine learning models, calculating metrics, analyzing confusion matrices, error analysis, or establishing model benchmarks.

• neural-network-training-recipe

  Use when developing, training, debugging, or optimizing neural networks and deep learning models in PyTorch or TensorFlow.

• observability-and-instrumentation

  Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the availabl

• performance-optimization

  Optimizes application performance across frontend, backend, slow database queries, indexes, and N+1 patterns. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when query indexes need tuning, or when profiling reve

• planning-and-task-breakdown

  Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

• pydantic-ai-structured-agents

  Use when building production-ready, type-safe AI agents with strict schema validation, structured output models, dependency injection, and tool calling.

• repo-workflow-and-triage

  Standardizes repository workflows, issue triaging, and ticket specification by decoupling repo metadata from skill logic. Use when onboarding agents to a repository, organizing issue tracking in docs/agents/, converting user bug reports into actionable specifications, or triaging project tickets aut

• reverse-engineering-and-binary-analysis

  Analyzes compiled binaries, bytecodes, protocols, and firmware using static decompilation and dynamic tracing. Use when reverse engineering executables (ELF, PE, Mach-O), analyzing disassembled assembly, decompiling bytecodes (APK, Java, .NET, WASM), inspecting binary network protocols, unpacking fi

• security-and-hardening

  Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data,

• shadcn-ui-engineering

  Use when building modern frontend interfaces with React, Next.js, and TailwindCSS using accessible shadcn/ui components.

• shipping-and-launch

  Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

• smolagents-code-first-agents

  Use when building ultra-lightweight, code-first AI agents that think in code using Hugging Face smolagents.

• source-driven-development

  Grounds every implementation decision in official documentation. Use when you want to verify an approach against the official docs before implementing it, or when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness

• spec-driven-development

  Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requ

• subagent-orchestration-and-delegation

  Use when delegating focused responsibilities like research, security audit, code review, ML data audit, or LaTeX drafting to specialized subagents.

• superpowers-autonomous-engineering

  Executes multi-hour autonomous software engineering through disciplined worktree isolation, granular task slicing, and test-driven development. Use when building complex features autonomously, running disciplined TDD cycles that delete unverified code, orchestrating subagent-driven workflows, or enf

• test-driven-development

  Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a f

• thermonuclear-code-review

  Executes uncompromising structural critique to eliminate cognitive debt, enforce file modularity, and demand code-judo reframing. Use when conducting deep architectural code reviews on complex pull requests, when challenging high-cyclomatic branching and leaky abstraction boundaries, when diffs thre

• token-optimization

  Maximizes LLM token efficiency, prompt compression, and context budget economics. Use when reducing token consumption, compressing codebases or prompts, preventing context rot, maximizing static prompt cache hits, pruning verbose tool logs, generating compact AST skeletons, or optimizing token usage

• unslop-code-and-prose

  Removes artificial AI writing tells, chatbot idioms, sycophancy, and filler from technical writing and code comments. Use when editing pull request descriptions, documentation, ADRs, commit messages, or code docstrings to eliminate AI cliches, passive fluff, superficial ing phrases, and empty abstra

• using-agent-skills

  Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.

• uv-python-package-manager

  Use when managing Python environments, installing packages, creating virtualenvs, running scripts, or configuring Python dependencies via uv.

Subagents (6)

• academic-paper-writer

  Academic LaTeX Specialist and Scientific Writer for drafting, structuring, formatting, and proofreading journal articles, thesis chapters, and conference papers in LaTeX (IEEE, ACM, Springer, Elsevier, SINTA, Scopus standards).

• code-reviewer

  Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.

• ml-research-engineer

  Senior Machine Learning Engineer that inspects datasets, audits data leakage, reviews neural network training pipelines (Karpathy recipe), validates evaluation metrics, and ensures reproducible experiments.

• security-auditor

  Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

• test-engineer

  QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

• web-performance-auditor

  Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.

Similar plugins