ehartye/hartye-claude-plugins

Plugin marketplace

Claude Code plugin marketplace - Salesforce development and automation tools

GitHub stars: 1
plugins: 20
last updated: Oct 27, 2026

View on GitHub

Add marketplace

/plugin marketplace add ehartye/hartye-claude-plugins

Run it inside Claude Code, then install plugins from it with /plugin.

Plugins

1academia-fetchFind papers worth reading via OpenAlex, then retrieve them from academia.edu with your own subscription and stage them for wiki-master ingest - human-paced rather than a crawler, with an enforced per-run delay and ceiling, and an open-access short-circuit that skips the subscription entirely when a paper is legitimately free elsewhere0.2.0version

2agent-beepsProcedural and recorded-source hybrid game/UI SFX, plus procedural game music for coding agents: editable Web Audio patches and songs, deterministic sample preparation, portable source bundles, verified baked/live delivery, measurements, craft lint and owner auditions with a learned taste model.0.34.1version

3agent-drawVector-first 2D authoring: editable SVG, transparent PNG/PDF, drawn pose sequences, named-part animation and game atlases. Native bitmap lettering exports fixed-cell printable-ASCII BMFont assets with hash receipts. Includes 768 human/compact-RPG starter drawings in elevated and overhead facings, guide identities and walk/run galleries. Craft guidance covers connected anatomy, boot clearance, selective ink, playable surfaces and shared character/environment perspective. Includes a curated native Inkscape CLI and Python inkex API quick reference with runnable examples. Three skills: draw-setup, draw-authoring, draw-export. Node.js 22+ and existing Inkscape 1.2+; optional encoding/atlas exports need existing FFmpeg. No npm dependencies; Linux CI plus scoped Windows native export checks.0.5.1version

4agent-engineSkills for game-engine selection and for building and verifying games with agent-sprites, agent-meshes and agent-beeps assets across Unity, Godot and web engines (Phaser, three.js, React Three Fiber, Babylon.js). Includes runnable web 3D examples with GPU verifiers. The Unreal importer, system, native game and UEFN skills are in agent-unreal. Saved import, cook and runtime acceptance remain separate.0.26.0version

5agent-game-studioProcess skills and references that tell an AI agent which phase a game project is in, what comes next, who decides each question and what evidence passes each gate. Technology-agnostic; works for new projects and for adopting an existing one.0.1.1version

6agent-marketingEvidence-led marketing for family-made tools, apps and games: audience discovery, channel strategy, paying-demand and non-English market research with sourced decision reports, campaigns, collateral, monitoring, reception and experiment decisions, and game-launch planning with readiness gates and weekly maker-hours checks, with decisions, next steps and collateral picks tracked in the ledger and the desk. Ten skills, a portable evidence ledger, a dependency-free Node CLI and a local campaign desk.0.11.1version

7agent-meshesNamed-part 3D authoring for coding agents: rigged, animated GLBs, verified builds and offline previews. Native Blender builds support declared files/trees, fixed environments, project roots, pins, shared defaults, batch hashing and bounded rollback reuse. Static-prop Unreal checks report geometry, collision and import settings, accept explicit import options and include signed-axis calibration. Mesh-from-arrays preserves UV and FLOAT_COLOR masks. Managed identity excludes generated Python bytecode; native previews inspect active vertex RGB. Includes researched tool selection for Blender Python, Unreal procedural meshes, R3F, Godot, Unity and code-CAD, project-owned face recipes, rig banks and character craft. Seven skills cover selection, setup, authoring, rigging, building, believable form and quality review.0.32.0version

8agent-proseWriting-craft toolkit for coding agents: poems and song lyrics, game dialogue and barks, instructions and docs, textbook teaching, reader targeting and single or batch passage suitability assessment, academic and professional prose, screen and stage scripts, YouTube scripts, speeches, professional presentations and webinars. Twenty-one skills include prose-reading-level for evidence-linked rubric judgments, proposed changes and saved suggestion dispositions, and prose-annotate and prose-annotation-review for source-bound highlights, vocabulary, explanations, links, a shared review workbench and portable publication data for Markdown, static HTML and structured content. Native drafts are measured and linted against cited craft rules. Illustrated storyboards retain editable panels, choices and character quest tracks. Variant sets, owner reviews and a taste model support rewrites; prose audit reports style hallmarks, never authorship. Slide-file creation uses the available presentation tool.0.13.0version

9agent-spritesEditable pixel-art authoring for agents: reusable parts, independent child animation, exact frame timing, construction replay, offline normal-map lighting, paired atlases, GIF proofs and a shared live workbench.0.96.1version

10agent-stalkerTrack agent team task assignment, messages, and tool use across Claude Code sessions into SQLite with queryable CLI and web dashboard0.5.1version

11agent-testsTest-efficiency toolkit for coding agents: structure tests by project phase and risk, audit a suite for redundant, shim, worktree-hostile, unwired, over-frequent and costly native UI tests, and remediate with evidence.0.7.0version

12agent-unrealSkills for working in Unreal Engine 5.8 from a coding agent: choose the engine system that fits a goal, with a reference per system (Lumen, Nanite, Virtual Shadow Maps, Niagara, Gameplay Ability System, Enhanced Input, AI, Sequencer, networking and more); audit a project's structure, tests and performance practice against Epic's documentation and plan the fixes; build, package and profile a native C++ game; import sprites, meshes and sounds with a guarded importer; and author for UEFN. Includes example scripts that list plugin states, dump the Python surface and build and validate Niagara scenes.0.19.0version

13agent-vidsMarketing and training videos of web apps for coding agents - analyse the app, recommend a brief with cited craft rules, storyboard it, and render narrated, captioned, craft-checked video with Playwright capture and ffmpeg; 60 evidence-backed rules for length, calls to action, text size relative to the frame, contrast, captions and narration language, reusable LinkedIn, YouTube and Shorts channel profiles and style flavors, voice auditions, and a LAN review page where the owner picks and orders exhibits and finalizes the stitched video. Repeatable stepped capture for browser games, a Steam trailer channel and lossless store stills. Five skills: vid-setup, vid-discover, vid-brief, vid-storyboard, vid-render0.5.0version

14agent-workflowSubscription-backed Codex workflows with native plugin/skill access and verified skill selection. New runs retain verified capability source packages through host cache changes, preserving genuine native activation and saved source identities. Workers have unbounded wall time by default, revisioned live deadline controls and idempotent independent task admission into active runs. Original inputs, capability ceilings and shared attempt budgets remain enforced. Durable command and observer evidence, signed Windows process host, reviewed worktree artifacts and authenticated map/inspector dashboard. Four skills, nine recipes, Node 24+. No custom MCP or API-key fallback. Opt-in Windows OpenSSH Session 0 compatibility retains its shared UI disclosure. Inert plans expose exact compiled schema result budgets before worker dispatch. New launchers use exact prepared caller runtimes without changing another session's shared default.0.6.3version

15book-nomCapture printed books into the family wiki - iPhone document scans to wiki-ready markdown via local OCR/VLM routing (Tesseract + Qwen via Ollama), with spread splitting, per-page provenance metadata, selective page images, and an optional guarded polish pass. Human-in-the-loop split calibration: draggable split lines feed the pipeline verbatim and double as detector ground truth. Includes the book-capture skill documenting the scan/calibrate/process/polish/ingest workflow0.2.1version

16h-superpowersAn agentic skills framework for AI coding assistants - composable workflows for planning, TDD, debugging, and code review4.16.0version

17hartye-skillsGeneral-purpose utility skills for Claude Code - small, self-contained techniques useful across many projects. beautiful: distinctive frontend design that avoids templated, AI-generated aesthetics, covering direction, typography, layout, motion and interface copy. ship-it: commit, branch, push, PR and squash-merge pending work in one step. yoda: write, audit and diagnose skills - why a SKILL.md never fires, gets ignored, or competes with another. rubber-duck: get a second opinion from the other vendor model and record it verbatim0.4.0version

18md-publisherTurn markdown documents (with embedded mermaid) into themed, searchable, paged PDFs via WeasyPrint AND Microsoft Word DOCX via python-docx. 5 skills (publish with --format pdf|docx|both, preprocess, theme-advisor, theme-gallery with live palette swatches + typography samples, install-fonts) + 6 bundled themes (atlas/phosphor/arcade in light + dark) + interactive custom-theme creation + cross-platform Google Fonts installer + macOS/Linux/Windows native-dep probes via bootstrap --doctor0.5.4version

19sf-browser-controlSalesforce browser automation via SF CLI - 45+ tools for session management, Lightning navigation, form filling, record operations, and Setup automation1.0.0version

20wiki-masterMaintain a Karpathy-style LLM wiki on Obsidian via the native obsidian CLI - discover and clip web sources, ingest PDFs/DOCX, then query, lint, and relink them into a cross-referenced knowledge vault0.79.0version

Details

Repository: github.com/ehartye/hartye-claude-plugins
Categories: community
Listed since: Feb 4, 2026