batteryshark
- 48 skills
- 0 followers
- 9 hours ago last updated
- ▌ External Ip · batteryshark bundleResolve and cross-check a machine's public IP address through bounded external services with clear disagreement and network-failure reporting.
- ▌ Intellidiff · batteryshark bundleCompare files or directory trees, detect exact duplicate files, calculate SHA-256 checksums, normalize text for semantic comparison, and read targeted line ranges. Use when determining whether artifacts are identical, finding orphaned or changed files between folders, deduplicating collections, inspecting backups, or explaining content differences without modifying the inputs.
- ▌ Excalidraw · batteryshark bundleCreate, patch, validate, and render Excalidraw diagrams through deterministic JSON and layout checks before delivery.
- ▌ System Recon · batteryshark bundleCollect a bounded, read-only system inventory for troubleshooting while identifying privilege gaps and avoiding secrets or invasive enumeration.
- ▌ Local Ocr Vlm · batteryshark bundleRun OCR on local images through an OpenAI-compatible local vision endpoint (LM Studio, vLLM/vmlx). Use when you need offline, on-machine document OCR into markdown, including batch directory processing, without sending images to a hosted service.
- ▌ Docker Cleanup · batteryshark bundleSurvey and safely reclaim Docker disk usage with category-specific confirmation, export options, and platform-aware virtual disk handling.
- ▌ Publish Ready · batteryshark bundlePrepare a repository for public release by removing development residue and dead paths, consolidating documentation, tightening generated-sounding prose, checking for secrets and local-machine references, and proving that surviving quickstarts and checks work. Use before open-sourcing, sharing, handing off, demonstrating, or releasing a project.
- ▌ Github Publish · batteryshark bundlePublish a local project to GitHub or update an existing GitHub repository with deliberate visibility, scoped commits, appropriate ignore rules, useful metadata, and verified CI. Use when creating a repository, connecting a local checkout to GitHub, preparing the first push, publishing local changes, or repairing incomplete repository setup.
- ▌ Reverse Brief · batteryshark bundleReconstruct a concise implementation brief from an existing codebase or artifact when original requirements are missing, stale, or incomplete.
- ▌ Cron Job Manager · batteryshark bundleInspect, render, install, or remove named user crontab jobs with explicit mutation confirmation and marker-bounded edits. Use on Unix-like systems when a user wants recurring local command scheduling through cron rather than a platform-specific automation service.
- ▌ Macos Screenshot · batteryshark bundleCheck macOS screen-recording readiness and capture a full display, selected region, window ID, or interactive selection to a caller-chosen image path using the native screencapture command. Use for local visual evidence, UI debugging, or screenshot capture outside browser-specific tooling.
- ▌ MCP Testing · batteryshark bundleTest FastMCP servers through direct unit tests, in-memory MCP clients, elicitation handlers, and focused deployed-transport integration checks.
- ▌ Google Maps Query · batteryshark bundleQuery current Google Maps Platform geocoding, Places, and Routes APIs from a thin JSON CLI using an environment-supplied API key and explicit billable-call execution. Use when a user needs place IDs, coordinates, place details, text search, or route distance and duration from Google Maps data.
- ▌ Nano Banana Image · batteryshark bundleGenerate or edit images through Google's Gemini image API using environment-provided credentials, explicit output paths, and reproducible request metadata.
- ▌ Windows Elevation · batteryshark bundleChoose and execute the narrowest Windows elevation method while preserving output, with a guarded SYSTEM fallback for exceptional protected operations.
- ▌ Codebase Writeup · batteryshark bundleAnalyze a codebase and produce an evidence-backed technical narrative or onboarding guide covering purpose, stack, architecture, execution paths, data flow, external integrations, setup, safe-change guidance, operational constraints, and important gaps. Use for engineering handoffs, unfamiliar-project explainers, README or contributor documentation, technical writeups, due-diligence summaries, or requests to explain how a repository works.
- ▌ Apple Reminders · batteryshark bundleManage Apple Reminders on macOS through a native EventKit command with explicit confirmation for mutations and machine-readable results.
- ▌ Goal Epic Craft · batteryshark bundleTurn rough intent into a bounded goal or epic through a short interview, grade an existing goal against a written standard, or split a bounded epic into vertical slices. Use when a brief is too vague to execute, when asked to shape, bound, or scope a goal, epic, or project brief, or before delegating work to an autonomous agent.
- ▌ Project Tracker · batteryshark bundleCreate or update compact durable Markdown memory for long-running projects, including current objective, status, workstreams, attempts, decisions, important artifacts, open questions, and next actions. Use when capturing project state, reconstructing context, preparing a handoff, recording a pivot, or making future sessions resumable across engineering, research, automation, writing, and other multi-session work.
- ▌ Decision Records · batteryshark bundleCreate, recover, review, or update durable decision records that preserve context, constraints, considered alternatives, chosen direction, consequences, evidence, uncertainty, and reconsideration criteria. Use for architecture decisions, product or operational tradeoffs, design-rationale interviews, superseding stale records, or reconciling documented intent with actual practice.
- ▌ Windows AI Controls · batteryshark bundleAudit, disable, and restore selected Windows AI features through reviewable registry and policy changes with explicit elevation and verification.
- ▌ IOS Remote Install · batterysharkInstall an iOS build on a physical iPhone that is not on the local network — over Tailscale, TestFlight, or a cable — when Xcode's own wireless install cannot reach the device. Use when asked to push, deploy, update, or sideload an app to a phone that is away, travelling, in another state, or otherwise unreachable, or when devicectl reports a paired device as unavailable.
- ▌ Work Product Audit · batteryshark bundleAudit repositories and public documentation for internal notes, defensive explanations, unexplained assertions, stale project residue, hidden assumptions, and generated-sounding meta commentary. Use when scanning launch material, cleaning public prose, or deciding which reasoning belongs outside the finished deliverable.
- ▌ Code Quality Review · batteryshark bundleReview or improve source code for reader-facing maintainability across naming, functions, models, comments, error handling, tests, external boundaries, and concurrency. Use for broad code-quality audits, behavior-preserving cleanup, generated-code humanization, refactoring prioritization, or focused requests to reduce local cognitive load without redesigning the whole architecture.
- ▌ Codebase Archeology · batteryshark bundleInvestigate and preserve archived, inherited, abandoned, or poorly understood codebases by mapping project variants, toolchains, build assumptions, duplicate artifacts, historical value, and modernization options. Use for legacy project intake, repository preservation, compatibility work, build recovery, false-start comparison, or deciding what should be kept, merged, archived, or retired.
- ▌ Deliverable Hygiene · batteryshark bundleKeep or restore a codebase as a finished, human-readable work product by separating agent scratch from source, pruning excess documentation and tests, deleting obsolete compatibility paths, and validating that process residue does not leak into the deliverable. Use during implementation cleanup or when a repository has visibly drifted.
- ▌ Windows Mingw Build · batteryshark bundleBuild, troubleshoot, or set up native Windows C and C++ compilation with MinGW-w64, MSYS2, GCC, G++, Clang, LLVM, mingw32-make, static runtime linking, resources, DLLs, or Makefiles. Use when producing 32-bit or 64-bit Windows artifacts, selecting a Windows GNU toolchain, diagnosing architecture or linker problems, avoiding CMake, or avoiding bundled MinGW runtime DLLs.
- ▌ Engineering Diagrams · batteryshark bundleCreate or revise evidence-backed engineering diagrams that explain system context, component ownership, data movement, runtime interactions, state transitions, or trust boundaries. Use when a visual model would make architecture, behavior, lifecycle, dependencies, or security boundaries easier to understand or review.
- ▌ MCP Elicitations · batteryshark bundleImplement and test FastMCP user elicitation and MCP Apps interaction patterns with explicit accept, decline, cancel, validation, and security behavior.
- ▌ Google Calendar CLI · batteryshark bundleAuthenticate a desktop Google Calendar client, inspect calendars and events, query free/busy data, and create or delete events through a reviewable plan with hash-bound explicit confirmation. Use when a user wants direct Google Calendar CLI automation without an MCP server.
- ▌ MCP Server Create · batteryshark bundleScaffold and verify a portable FastMCP 3 server project with declarative configuration, library-first logic, tests, and safe transport defaults.
- ▌ MCP Server Design · batteryshark bundleDesign FastMCP 3 tools, providers, transforms, authorization, background work, output contracts, and human approval boundaries for a production server.
- ▌ MCP Server Upgrade · batteryshark bundleAudit and upgrade an existing MCP implementation to current FastMCP 3 patterns while preserving behavior and verifying protocol compatibility.
- ▌ Project Retrospective · batteryshark bundleTurn a completed or paused body of work into an evidence-based retrospective covering goals, outcomes, decisions, pivots, effective practices, friction, failed approaches, unfinished work, open questions, and concrete improvements. Use with conversation history, project trackers, session notes, plans, logs, or user-specified files and folders across engineering, research, writing, automation, and other projects.
- ▌
- ▌ Tier Plan · batteryshark bundleTurn one request into a routed work graph — decomposed into units, each assigned a capability tier, a reasoning budget, a verification command, and a dispatch order. Use this before executing large or multi-part work, when asked to "plan this out", "how would you split this up", "what should each model do", "estimate what this will cost", when a job is too big for one context and needs carving up, or when someone wants the delegation plan reviewed before any tokens are spent on execution. Produces a plan document, not the work itself.
- ▌ Claude Session Handoff · batteryshark bundleBuild a redacted, evidence-backed continuation brief from a Claude Code JSONL transcript. Use when resuming an interrupted agent task, handing work to another agent, or reconstructing objectives, edits, validation, and remaining work.
- ▌ Play Tic Tac Toe · batteryshark bundlePlay, resume, inspect, or clear a terminal tic-tac-toe game with persistent user-scoped state and deterministic aggressive or defensive AI. Use when a user asks to play tic-tac-toe, supplies a board position, makes a numbered move, or wants to resume a saved match.
- ▌ Orchestrate · batteryshark bundleRoute multi-part work across model tiers and reasoning budgets for the best quality-per-token. Use this whenever a request has several separable pieces, when work will be delegated to subagents or other models, when deciding which model or how much thinking a piece of work deserves, when a job is large enough that doing it all at the top tier would be wasteful, or when a cheaper agent keeps failing and you need to decide whether to retry, re-brief, or escalate. Trigger on migrations, audits, sweeps, reverse-engineering campaigns, batch refactors, multi-file analysis, "fan this out", "use subagents", "which model should do this", "make this cheaper", "parallelize this", or any plan where one context cannot hold the whole job.
- ▌ Model Fitness · batteryshark bundleMeasure which capability tier a model can be trusted with and where its reasoning budget stops paying, then write it into the orchestration roster. Use when a new or unfamiliar model is added, when deciding "can this smaller model handle X", when a delegated agent keeps failing and you need to know whether it is the model or the brief, when choosing a reasoning or effort level, or when setting up tiered delegation for the first time and the roster is empty. Runs a short probe battery and produces a tier ceiling, a budget plateau, and a roster entry.
- ▌ Norman Audit · batteryshark bundleAudit an interface for design failures, from source alone — a changed diff or a whole workspace. Hunts eight failure classes (controls that never earned their place, orphaned capabilities, scentless labels, excise steps, recall demands, mute actions, slip traps, state amnesia) across screens, forms, navigation, CLI commands, and error messages, and returns ranked one-line findings with fixes, citing file and line. Use to audit an interface or UX, review an interface change, find out why users cannot find features, or decide what a UI should drop. Reports only; does not apply fixes. Not for code quality, correctness, or security review.
- ▌ Architecture For Comprehension · batteryshark bundleEvaluate and map a repository's architecture for coherence, discoverability, predictable execution paths, local reasoning, onboarding friction, accidental complexity, and cognitive load. Use for system-level architecture reviews, newcomer usability probes, repository legibility scorecards, or requests to make a codebase easier to understand as a whole.
- ▌ Agent Create · batteryshark bundleScaffold a portable Markdown role prompt for a focused subagent or independent review role. Use when creating an agent definition, extracting a specialist role from a workflow, or defining explicit inputs, evidence standards, constraints, and output without depending on one orchestration vendor.
- ▌ Skill Create · batteryshark bundleScaffold a complete portable skill package that follows the Skill Tap contract. Use when creating a new reusable agent skill, turning a repeated workflow into a skill, or generating SKILL.md plus portable agents, a matching bin command, PEP 723 scripts, references, and validation-ready structure.
- ▌ Skill Refine · batteryshark bundleAudit and improve a portable skill for contract compliance, triggering, progressive disclosure, script correctness, portability, safety, and verification. Use for skill reviews, pre-publication checks, broken-skill diagnosis, quality scoring, or modernizing an older package to the Skill Tap contract.
- ▌ Skill Node Portability · batteryshark bundleAudit and modernize Node.js scripts inside portable skills with explicit dependencies, committed lockfiles, local npm commands, compiled runnable JavaScript, and no global-tool assumptions. Use when a skill contains JavaScript or TypeScript, relies on global npm installs, lacks deterministic setup, or fails when copied to another machine.
- ▌ Tetromino Guideline Review · batteryshark bundleAudit or plan a single-player falling-tetromino implementation against an explicit historical gameplay baseline covering field geometry, seven-bag generation, controls, lock-down, scoring, spins, game-over, UI, and audio. Use for evidence-based implementation reviews or remediation plans; this is an unofficial engineering checklist, not Tetris certification.
- ▌ Skill Python Portability · batteryshark bundleAudit and modernize Python scripts inside portable skills with PEP 723 dependency metadata, stable uv launchers, standard-library fallbacks, and no hidden virtualenv or global-package assumptions. Use when a skill invokes Python directly, has undeclared imports, fails outside its author’s machine, or needs contract-compliant bin and scripts structure.