Find the open-source solution that fits.

fullstack-pro-max is a Claude Code skill that selects a stack from project needs and organizes UI, backend, data, authentication, security, testing, SEO, and launch work across 13 modules. It includes standard-library-only Python helpers and can optionally use connected services such as Supabase or Vercel for live operations. The project reports only two author-run end-to-end field tests so far, so routing and generated results still require human verification.

Code to Reels turns a prompt into a 9:16 animated explainer short using Python, SVG, CairoSVG, and FFmpeg rather than a browser or After Effects. The workflow designs a mascot, boards a five-beat script, renders deterministic frames, and synthesizes sound effects, with staged approval points before expensive work. Its bundled example uses the Burton Method bee, but the palette and character can be replaced for another brand.

cc-usage reads Claude Code’s local JSONL transcripts and reports token totals, daily or weekly breakdowns, model-based pricing, and summary statistics across projects. It uses only Python’s standard library and does not access a subscription dashboard. The dollar figure is an API-price reference for the recorded usage, not what a subscription actually charged.

disk-cleanup scans more than twenty macOS developer-cache and build-artifact locations, groups them into safe, confirm-first, and display-only tiers, and reports sizes. It requires an explicit confirmation before deletion, previews expanded paths, and compares disk space before and after. User profiles, downloads, and Time Machine snapshots remain display-only.

anti-procrastination-skills offers seven Claude Code workflows for when avoidance comes from guilt, overwhelm, fear, or perfectionism. They capture and sort the mess, shrink a task, close a decision, reframe harsh self-talk, draft an imperfect first version, protect important work, and review real wins. The project presents these as an educational productivity aid, not medical advice or mental-health treatment.

video-digest processes local videos into Markdown digests containing spoken transcripts, on-screen text, URLs, handles, and timeline contact sheets. ffmpeg is the only hard requirement; faster-whisper and OCR engines are optional and degrade gracefully when absent. Independent stages cache their results and can resume, and the tool never uploads media or needs an account.

Dev Fable helps Claude Code handle multi-step development by planning phases, routing work to specialized subagents, and synthesizing their results. It can run independent perspectives in parallel for high-stakes decisions, while separate roles cover architecture and debugging, repetitive edits, and read-only exploration. The bundled agents are defaults that teams can remap to their own models and tools.

PCB STEP Slim removes electrical and cosmetic detail that makes PCB assemblies heavy while keeping the board outline and mechanically relevant components, including height-critical parts. Its reference-graph approach preserves a valid, closed STEP structure, original geometry, and component colors instead of re-tessellating the model. The result is intended for faster mechanical review in SolidWorks or other CAD tools.

Use a reasoning-first workflow to generate a desktop UI, set design direction, critique an existing screen, remove generic generated patterns, or envision a future interaction model. The skill combines transferable principles from multiple designers, derives an original token system, checks output with a deterministic slop linter, and records project decisions for later sessions. It targets desktop application shells; a separate sibling project covers browser-based interfaces.

Provide a Four Pillars chart, gender, and luck-cycle details to convene several competing BaZi schools. They review the chart in rounds, challenge one another, and make predictions with probabilities, time windows, and explicit failure conditions before you reveal outcomes for scoring. The Chinese-language workflow is intended as a reflective reasoning exercise, not health, financial, or legal advice.

Restaurant Digital AI Expert helps food-service operators and consultants assess digital transformation across restaurant formats and business chains. It combines a five-dimension maturity model with vendor selection, AI-scenario prioritization, ROI analysis, and food-safety frameworks, covering supply, kitchen operations, POS, delivery, members, and franchising. It is a methodology workbench, and its license limits use to personal learning, research, and non-commercial work.

Retail Digital AI Expert is a Chinese-language workbench for retail transformation across convenience stores, supermarkets, apparel, discount retail, DTC, e-commerce, franchises, and large chains. It combines maturity assessment, vendor selection, five-year TCO and ROI analysis, and AI-use-case prioritization, helping teams move from current-state diagnosis to a roadmap and proof-of-concept plan. Its license limits use to personal learning, research, and non-commercial work.

Explain Architecture scans the important parts of a codebase, such as manifests, entry points, migrations, and routes, then produces readable Mermaid diagrams for modules, data flow, ERD, request lifecycle, and deployment. It also writes a plain-English ARCHITECTURE.md, an AI-CONTEXT.md brief, and editable diagram sources, with PNG and PDF renderings for people to review.

Restaurant Digital AI Expert is an English workbench for global food-service transformation. It maps restaurant formats and business chains from supply and central kitchens through front-of-house, POS, delivery, members, finance, and franchising, then applies maturity assessment, vendor scoring, HACCP controls, AI-use-case prioritization, and ROI analysis. It is intended for operators and advisors planning technology choices and rollout, and its license limits use to personal learning, research, and non-commercial work.

Retail Digital AI Expert is an English international workbench for retail transformation across convenience, grocery, apparel, DTC, e-commerce, franchise, and global chains. It combines format diagnosis with maturity assessment, vendor selection, five-year TCO and ROI analysis, AI-use-case prioritization, and implementation roadmaps. The repository’s license limits use to personal learning, research, and non-commercial work unless the author gives written permission.

GB/T 9704 Format standardizes applicable government-document layout rules in Word files through a Claude skill or standalone command-line tool. It fixes margins, headings, fonts, spacing, page numbers, punctuation, numbering, and table formatting while leaving the document text untouched. Uncertain content issues are reported rather than guessed, and the Python-based tool does not require Word or WPS.

Salary Negotiation turns an offer letter and a few context answers into a single-file HTML playbook. It diagnoses leverage across base, equity, sign-on, and bonus, maps both sides’ power, drafts phone and email scripts, simulates recruiter pushback for two rounds, and sets SIGN, WALK, and FREEZE stop-lines. Compensation numbers must trace to market or user-provided sources; the final choice remains yours.

iphone-malware-assessment pulls crash logs, creates a resumable encrypted backup, and scans the backup and crash reports with MVT, libimobiledevice, and downloaded indicator feeds. Its report separates actual indicator matches from heuristic notes and includes coverage plus a full file sweep. It runs locally on macOS but cannot prove an unknown zero-day is absent; you need Homebrew, a USB connection, and a backup password you can retain.