maxedapps

@maxedapps source repo

18 skills
0 followers
19 hours ago last updated

▌
Parse Document · maxedapps
Use this skill when the user wants to parse, search, or visually inspect local documents such as PDFs, Word/DOCX files, PowerPoint/PPTX decks, Excel/XLSX/CSV spreadsheets, or images such as PNG, JPG, TIFF, and WebP. It helps the agent use the pi-docparser tools efficiently: document_parse for text/JSON extraction, document_search for phrase locations and bounding boxes, and document_screenshot for visual page inspection.

0
installs
▌
Use Subagents · maxedapps bundle
Portable playbook for bounded subagent delegation on any coding-agent harness. Use this skill whenever considering delegation, decomposition, parallel research, review or implementation, independent validation, or an explicit request to spawn or manage subagents. Works with the host's built-in subagent tools, extensions/plugins, or a safe agent CLI. Do not use for ordinary background shell, server, or process work.

0
installs
▌
Use Worktrees · maxedapps
Manages Git worktrees for isolated feature or milestone work. Use this skill whenever work should happen in a worktree, a worktree needs syncing with its target branch, or a finished worktree branch should be merged or cleaned up. Do not use for ordinary single-checkout branch work or subagent delegation that does not require worktree operations.

0
installs
▌
Generate Image · maxedapps bundle
Generates AI images through fal.ai HTTP queue workflows from a Bun CLI. Use this skill when a task needs AI image generation, schema inspection, image upload, or queue polling through fal.ai. Do not use for video, audio, 3D, or non-image workflows.

0
installs
▌
Implement Plan · maxedapps bundle
Implements existing Markdown plans exhaustively through delegated task loops, validation, and review closure. Use this skill when asked to implement, execute, carry out, or continue an existing plan. Do not use for creating a plan from scratch or only reviewing a plan without implementing it.

0
installs
▌
Use Pi Subagents · maxedapps bundle
Pi-specific launcher for bounded scout, research, and worker agents via the Pi RPC script adapter. Use this skill when on Pi, native `subagent_*` tools are inactive, and you need to launch, follow up, status, stop, or clean RPC children. Apply together with `use-subagents` policy (delegation, isolation, verify, cleanup). Do not use when a native subagent runtime should own the lane, for recursive delegation, ordinary background processes, or automatic Git/worktree management.

0
installs
▌
Vps Setup Hardening · maxedapps bundle
Runs a manually initiated, safety-gated VPS setup and hardening workflow for Ubuntu 24.04 LTS, Ubuntu 26.04 LTS, and Amazon Linux 2023 on EC2. Use this skill when, and only when, the user explicitly invokes vps-setup-hardening by name and supplies a VPS or SSH target, optionally with tool, firewall, access, and runtime preferences. Do not use for ordinary SSH administration, application deployment, compliance auditing, isolated package installation, targeted firewall repair, or automatic infrastructure changes.

0
installs
▌
Create Changes Report · maxedapps bundle
Creates a self-contained, interactive HTML report that explains completed repository changes as the primary code-review artifact. Use this skill whenever an agent changed code, tests, configuration, schemas, or infrastructure and is about to finish, summarize the work, or hand it off—even when the user did not request a report. Also use when asked to explain or report on completed repository changes. Do not use for read-only code reviews, tasks without repository changes, pre-implementation plans, or live-data dashboards.

0
installs
▌
Explain · maxedapps bundle
Runs a manually initiated explanation workflow that produces concise, evidence-grounded Markdown and standalone HTML for code, systems, data relationships, and prior plans, reviews, or agent statements. Use this skill when, and only when, the user explicitly invokes explain by name. Do not use for ordinary Q&A, implementation or fixes, performing a new code review, slide creation, exhaustive documentation, or render-only conversion of supplied Markdown.

0
installs
▌
Use MCP · maxedapps bundle
Uses configured or ad-hoc Model Context Protocol servers through mcporter with targeted discovery, structured tool calls, resource reads, and explicit authentication gates. Use this skill when the user asks to use an MCP server, call an MCP tool, inspect MCP capabilities, or access an MCP-backed service through mcporter. Do not use for implementing or debugging MCP servers or protocols, ordinary API/web work, or a service already covered by a dedicated trusted skill or tool.

0
installs
▌
Decomplex · maxedapps bundle
Reviews proposed or existing work for unnecessary complexity and triages complexity-increasing recommendations without editing the reviewed targets. Use this skill when asked to simplify or decomplex source, tests, configuration, dependencies, plans, designs, or architecture; challenge over-engineering; audit unnecessary complexity; or triage recommendations that would add complexity. Do not use for general defect review, implementation or fixes, style-only cleanup, or conceptual explanations that need no durable review report.

0
installs
▌
Code Review · maxedapps bundle
Reviews repository diffs, PRs, codebases, and completed implementations for material, evidence-backed defects and plan compliance. Use this skill when asked to review, audit, critique, find code issues, or evaluate implemented plan work. Do not use for draft-plan review or implementation unless fixes are explicitly requested.

0
installs
▌
Create Plan · maxedapps bundle
Creates, reviews, and improves lean implementation plans through orchestrated research, evidence-backed synthesis, and iterative independent review closure. Use this skill when the user asks to plan a feature or change, create an implementation handoff, or review or improve an unimplemented plan before coding. Do not use to implement a plan, audit completed implementation against a plan, or answer a small conceptual question that needs no implementation handoff.

0
installs
▌
Create Skill · maxedapps bundle
Creates, rewrites, reviews, and evidence-backed improves Agent Skills that are concise, unambiguous, progressively disclosed, and agent-actionable. Use this skill when authoring or revising a SKILL.md, its routing description, references, assets, scripts, or reusable workflow guidance. Do not use for installing third-party skills or one-off preferences without reusable evidence.

0
installs
▌
Web Research · maxedapps bundle
Researches current web and external technical information through source-backed discovery, retrieval, and repository, document, or media inspection. Use this skill when the user needs current facts, docs, articles, URLs, repositories, PDFs, videos, comparisons, or version-specific library/API/framework evidence. Do not use this skill alone for interactive browser tasks such as login, forms, or UI-state inspection; use an available browser automation capability.

0
installs
▌
Awesome Tests · maxedapps bundle
Designs, writes, improves, and reviews behavior-focused automated tests and test strategies. Use this skill when adding or repairing tests, creating implementation plans that change runtime or application behavior and must specify tests or validation, assessing test code or coverage quality, diagnosing flaky, brittle, fragile, or false-green tests, or conducting code reviews that materially touch tests or validation. Do not use for unrelated production implementation, plans or reviews with no testing or validation work, running an unchanged test command only, manual exploratory QA alone, or conceptual testing explanations without a concrete target.

0
installs
▌
Create Report · maxedapps bundle
Creates concise, evidence-backed, actionable standalone HTML reports for decisions, assessments, research, and status outcomes. Use this skill when asked to create, build, or package a polished standalone HTML report, decision brief, cited research report, risk-assessment report, project-status report, or executive HTML report and no domain-specific workflow owns the task. Do not use as an automatic completion gate; for completed repository-change handoffs use `create-changes-report`; for defect reviews use `code-review`; when `explain` is explicitly invoked use `explain`; for slide decks use `create-slides`; `create-plan`, `decomplex`, and `implement-plan` keep their domains; live KPI dashboards or apps are implementation, not this skill.

0
installs
▌
Create Slides · maxedapps bundle
Creates and materially redesigns polished, dependency-free HTML slide decks from five styled templates, with stepped and automatic reveal animations driven by named motion presets, a cross-slide title morph, and PDF plus MP4 export at 1080p, 2K and 4K with reveals optionally timed to a narration/caption track. Use this skill when asked to create, build, redesign, restyle, or export a slide deck, presentation, pitch deck, talk, tutorial/video slides, course slides, slide b-roll for a video, or keynote-style slides as a web page. Do not use for ordinary websites or apps, editing proprietary slide files (PowerPoint, Keynote, Google Slides), research-only requests without a deck deliverable, or generating slide images only.

0
installs

18 published skills