# hdprajwal > Open-source publisher. Listings imported from github.com/hdprajwal — credited to the original author with their license. - **Listings:** 25 - **Total installs:** 0 - **Profile:** https://agentstack.voostack.com/s/hdprajwal - **Website:** https://github.com/hdprajwal ## Published listings - [Brainstorming](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-brainstorming) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-brainstorming` Turn an idea into an approved spec before any code. Use before any creative work — new features, components, behavior changes. Reads context, asks one question at a time, proposes 2-3 approaches, writes a short spec to docs/-spec.md, and gets sign-off. Hands off to writing-plans. Never writes code before the spec is approved. - [Council](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-council) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-council` A decision chamber for high-stakes, ambiguous calls. Five specialist advisors (contrarian, first-principles, expansionist, outsider, executor) attack the question independently; a blind second round tears every proposal apart without knowing who wrote it; a fresh chairman delivers a verdict — a decision, not a menu. Use for hard go/no-go and tradeoff calls. Heavy (~11 subagents) — reserve for dec… - [Rust Review](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-rust-review) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-rust-review` Review Rust code for correctness, safety, idioms, and performance — run clippy/fmt, audit unsafe and unwrap, check ownership/borrowing and error handling, spot async pitfalls, and confirm tests. Use when reviewing or hardening Rust before merge, or when asked to make Rust more idiomatic. Runs the toolchain first, then reads for what tools can't catch. - [Humanize](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-humanize) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-humanize` | - [Litreview](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-litreview) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-litreview` Run a structured academic literature review — scope the question, search the literature, screen for relevance, extract findings into a comparable matrix, synthesize themes and gaps, and cite cleanly (BibTeX). Use for research papers, related-work sections, grant background, or surveying a field before building. Tracks what was searched so the review is reproducible, not cherry-picked. - [Screen Capture](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-screen-capture) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-screen-capture` Take screenshots on Wayland/Hyprland with grim + slurp — full screen, a chosen monitor, an interactive region, or the active window — and save to a file or pipe to the clipboard. Use whenever an agent needs to see the screen, capture UI state, grab a region for analysis, or produce an image to reason over. The "eyes" for visual computer use. - [Dispatching Parallel Agents](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-dispatching-parallel-agents) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-dispatching-parallel-agents` Dispatch one focused agent per independent problem and run them concurrently. Use when facing 2+ tasks with no shared state and no sequential dependency — several unrelated test failures, multiple broken subsystems, a batch of independent issues. Each agent gets a self-contained brief and returns a summary; you review for conflicts and integrate. - [Subagent Driven Development](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-subagent-driven-development) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-subagent-driven-development` Execute a plan with a fresh subagent per task and a two-stage review after each — spec compliance first, then code quality — running continuously until done, then finishing on a branch → PR → merge. Use when you have a plan from writing-plans whose tasks are mostly independent and you want to stay in the current session. - [Issue To Pr](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-issue-to-pr) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-issue-to-pr` Take one independent open GitHub issue from the queue to an open PR by composing skills you already have — isolation, implementation, and review — then stop at the PR for your merge approval. Use to clear a GitHub issue queue one issue at a time (\"take issue #42 to a PR\", \"work the next issue\", \"grab an issue\"). One issue per run; never merges to main on its own. - [Teach](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-teach) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-teach` Teach the user a topic from first principles — decompose to bedrock, rebuild it, make them derive it — over multiple sessions in a stateful, per-topic workspace. Use on "teach me X" or "help me learn Y". Adapted from Matt Pocock's teach skill. - [Writing Flow](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-writing-flow) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-writing-flow` | - [Visual Computer Use Loop](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-visual-computer-use-loop) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-visual-computer-use-loop` Operate the Hyprland desktop the way a human would — look at the screen, decide the next action, do it, then look again to confirm. Combines screen-capture (see), hyprland-control (windows/workspaces), and gui-input-automation (click/type) into one observe → reason → act → verify loop with coordinate calibration. Use for GUI tasks no CLI can do. - [Writing Plans](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-writing-plans) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-writing-plans` Turn an approved spec into a bite-sized implementation plan an engineer with zero context could execute — exact files, exact code, exact commands, Red-Green TDD steps, frequent commits. Use when you have a spec for a multi-step task. Saves to docs/-plan.md and hands off to executing-plans or subagent-driven-development. - [Spec To Issues](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-spec-to-issues) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-spec-to-issues` Break a spec, PRD, or design into independent first-principles tasks and publish them as tracker issues — GitHub for now, adapter-shaped for other platforms. Decomposes into tracer-bullet vertical slices with dependencies and acceptance criteria, gets your approval, then creates an epic + linked child issues. Use to turn a spec into a trackable backlog ("break this spec into issues", "push these… - [Using Git Worktrees](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-using-git-worktrees) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-using-git-worktrees` Make sure work happens in an isolated workspace before a feature or plan. A feature branch is the default and is enough for most work; reach for a worktree only when you need a second checkout at once (parallel agents, comparing branches, long build running). Detects existing isolation, prefers the harness's native worktree tool, falls back to git, verifies a clean baseline. - [Api Design](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-api-design) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-api-design` Design stable, well-shaped interfaces before implementing them — HTTP/REST endpoints, MCP tools, or library/module APIs. Use when adding a public endpoint, defining a contract between modules, designing MCP tools, or shaping a library's surface. Focuses on naming, contracts, error shapes, versioning, and backward compatibility — the parts that are expensive to change later. - [Unslop](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-unslop) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-unslop` | - [Incremental Implementation](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-incremental-implementation) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-incremental-implementation` Build in thin vertical slices — implement one piece, test it, prove it runs, commit, then expand. Use for any change touching more than one file, when you're about to write a lot of code at once, or when a task feels too big for one step. Each increment leaves the system working and committed. - [Session Handoff](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-session-handoff) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-session-handoff` Write or restore a handoff note when pausing or switching between projects, so the next session (you, another agent, or the user) resumes without re-deriving context. Use when wrapping up for now, context is getting long, switching to another repo, or starting back up on a project left mid-task. Captures state + next step, not a transcript. - [Document Toolkit](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-document-toolkit) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-document-toolkit` Read, extract, fill, and generate Office/PDF documents from Python — PDF (pypdf / pdfplumber), Word (.docx, python-docx), and Excel (.xlsx, openpyxl). Use whenever a .pdf, .docx, or .xlsx is the input or the desired output: extract text/tables, merge/split, fill forms, build a report, read or write a spreadsheet. Prefers libraries over brittle shell parsing. - [Shadcn Audit](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-shadcn-audit) — Skill · Free — `agentstack add skill-hdprajwal-agent-skills-shadcn-audit` Security auditor for shadcn components from third-party registries. Use this skill whenever the user mentions installing, adding, or using a shadcn component from a third-party source — even if they just say "add @acme/button" or paste a shadcn registry URL. Trigger it proactively when you see `npx shadcn add`, a namespaced component like `@v0/...` or `@acme/...`, or any URL ending in `.json` tha… - [Gui Input Automation](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-gui-input-automation) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-gui-input-automation` Send synthetic keyboard and mouse input on Wayland/Hyprland — type text, press key combos, move the cursor, click, scroll, drag. Use wtype for keyboard (no setup, rootless) and ydotool for the mouse (needs a one-time uinput/daemon setup the skill walks through). The "hands" for visual computer use. Wayland only — xdotool does not work here. - [Mcp Builder](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-mcp-builder) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-mcp-builder` Build, scaffold, and review MCP (Model Context Protocol) servers that give LLMs well-designed tools over an external API or service. Use when creating or improving an MCP server in TypeScript (MCP SDK) or Python (FastMCP) — tool design, transports (stdio local / streamable HTTP remote), error shapes, and evaluation. Grounds tool design in the official spec. - [Executing Plans](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-executing-plans) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-executing-plans` Run a written plan inline in the current session with review checkpoints: load it, review it critically, run each task exactly with its verifications, prove it actually runs, then finish on a branch → PR → merge. Use when you have a plan from writing-plans and tasks are coupled enough to keep in one session. Stops and asks when blocked. - [Hyprland Control](https://agentstack.voostack.com/l/skill-hdprajwal-agent-skills-hyprland-control) — Skill · Free · security-reviewed — `agentstack add skill-hdprajwal-agent-skills-hyprland-control` Inspect and control the Hyprland Wayland desktop from the shell via hyprctl — list/query windows, focus/move/resize/close them, switch and move things between workspaces, launch apps onto a target workspace, read monitor and cursor state. Use on Hyprland (Wayland) for any window or workspace management. Not for X11 (use wmctrl/xdotool there). --- Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add `.