Find the open-source solution that fits.

devsweep locates Docker and WSL virtual disks, scattered build artifacts, and caches on Windows, then shows a read-only scan and dry-run preview before any cleanup. Deletion requires an explicit execute step, while vhdx files are compacted rather than removed. It uses PowerShell and may need an elevated shell for system operations.

This Claude Code skill pairs a creative planning SOP with Remotion implementation guidance. The SOP defines the brief, brand, scene plan, copy, music, approvals, and delivery, while the skill handles canvas rules, mockup entries, cursor motion, transitions, audio, and per-scene checks. It targets short product or feature launch videos rather than narrative films.

Opposing Counsel Critique examines submissions, witness statements, expert reports, pleadings, and written advice from an adversarial perspective. It calibrates the analysis to document type, forum, stage, and practice area, then produces a core theory, surgical attack points, gap analysis, and response preparation. It is designed for England and Wales and does not edit the source document.

Handoff turns SESSION_HANDOFF.md into an append-only register for parallel Claude Code sessions. Each closing session adds a unique, status-marked section, another workstream can resume it by code, and consumed entries become tombstones before purge. It also appends a sprint report and never overwrites a still-pending handoff.

Cold Project Archiver finds projects that have not changed for a chosen period, records their files, and uploads them to Baidu Netdisk or Aliyun Drive with resumable retries and per-file verification. Local deletion stays locked until the remote copy is complete and the user confirms; a preflight step can also normalize unsupported filenames.

Nomira guides a naming session from strategy to shortlist: it clarifies the idea a name must carry, generates many candidates, removes awkward or derivative options, and compares survivors through sound, language, and trademark pre-checks. Each finalist includes a rationale and risk flag; the pre-check is not legal clearance, so the final choice remains human.

Break an AI-generated draft into factual, citation, legal, and interpretive claims, then route each claim to suitable authoritative sources. The audit reports salience, source quality, scores or qualitative legal verdicts, fairness concerns, and action items. It is tailored to England and Wales practitioners, especially healthcare law, and is not legal advice.

Turn a recipe from text, a photo, a URL, or a cookbook page into a Cookidoo MyRecipes entry guide. Each step separates typed prose, fan or manual settings, and linked ingredients, with English and Spanish support. The skill also flags TM7 editor limits and workarounds instead of pretending unsupported controls exist.

Generate a lead follow-up system for new inquiries, reactivation, no-shows, or missed calls. It supplies SMS, email, and AI-call copy, objection handling, a timed cadence, and a CRM build specification, with the call step routed through RizzDial.

Process invoices, receipts, business cards, IDs, and forms through the Space OCR API, storing extracted fields with page coordinates in queryable sheets. The skill supports asynchronous batch uploads, filtered queries, location views, and row edits; its Python client uses only the standard library and does not require an MCP server.

Triage a commercial question across 15 data domains, detect available specialized sources, and guide setup when a source is missing. The skill delegates retrieval and synthesis to existing research tools, then adds citation checks, source tiers, corroboration, disconfirmation, timestamps, and explicit coverage gaps.

Run Lighthouse, axe, Playwright, link and HTML checks, security-header probes, and secret or sink scans against a production build. ShipShape ties each finding to tool output and rule names, tests responsive breakpoints, and treats missing inputs as skipped instead of silently passing them.

Develop copy and visual direction around a buyer's dominant motive, then score candidates for pattern interruption, emotional intensity, curiosity, and scarcity. A five-voice council selects a direction while critics can veto cringe, incongruence, or untruth; the process also produces a design specification and treats conversion lift as a testable hypothesis.

Add, list, complete, and review reminders through a natural-language command, with records stored in a local JSON file. A SessionStart hook shows overdue, due-today, and upcoming items when Claude Code opens, while completed reminders remain available in history. It uses Bash and Python 3 without external dependencies.

Walk a folder tree, extract PDF text with PyMuPDF, and write one Markdown file per subfolder. The companion cleanup script previews non-Markdown files and only deletes them when explicitly applied; conversion uses no OCR, layout reconstruction, or cloud service.

Research shipped app patterns through Mobbin, turn them into an approval-gated Flutter design spec, and implement production widgets with Material 3, Cupertino, or custom styling. The workflow previews every state, supports adaptive layouts, generates accessibility tests, and can add golden tests before running validation.

agent-skills bundles separate Claude Code skills for editable draw.io diagrams, project and business analysis, BPMN modeling, single-file HTML presentations, and reversible PPTX anonymization. Each skill lives in its own folder with a SKILL.md and can be installed independently rather than used as one unified command.

starter-skill asks whether you need the backend, web, or mobile layers, then scaffolds a Bun workspace with Convex functions and Auth, a React/Vite TanStack web app, and an Expo SDK 56 native app. It drives setup from the CLI and starts with a local Convex deployment, making it a foundation for new full-stack projects.