Find the open-source solution that fits.

Starting from a vague idea, the skill asks one question at a time about the goal, reason, and definition of done before producing a structured brief that can be copied or saved in the project. Quick, standard, and deep modes add different levels of detail, and unanswered essentials are left as gaps rather than silently invented.

The skill checks line counts in MEMORY.md and oversized files in a custom file-based auto-memory setup, with read-only diagnosis as the default. Trimming or splitting requires explicit approval and includes backup, verification, and audit logging; it is designed mainly for a specific macOS setup, not Claude Code’s built-in memory features.

The skill classifies a project as a local tool, full-stack product, automation agent, AI web app, or mobile app, asking only a few questions when needed. It previews the folder tree and key files before writing, then creates CLAUDE.md, an initial build prompt, dependency files, environment templates, and a numbered prompt chain for later work.

The skill routes requests into sprint planning, deep-work design, a weekly ritual, or an accountability check. It centers each sprint on one observable deliverable, allocates real time blocks, and reviews missed commitments without motivational filler; very small tasks and situations requiring professional mental-health support fall outside its intended use.

The skill detects whether a question involves trade-offs, diagnosis, prioritization, competition, or an emotional decision, then applies one of twelve frameworks such as first principles, inversion, OODA, or pre-mortem. It ends with a concrete action and a blind spot, supports explicit framework selection, and is not intended for factual lookups or professional financial, legal, or medical advice.

With ProLine Partner API access, an agent can create leads, book inspections, move deals through stages, write project notes, and look up team members. The repository also syncs CRM data into local SQLite for reporting and deal-quality scoring and includes weather-based rain-day decisions; both partner and company credentials are required, and several API operations remain blocked or nonfunctional.

Before any UI is produced, the skill requires a specific cultural register with real references rather than a vague style label, then seals the allowed colors, typography, and other tokens. Four gates check token use, prohibited patterns, hero hierarchy, and copy specificity, while ten starter registers and a companion task-first UX skill provide reusable starting points.

The setup pairs two Windows machines with Syncthing, replicates the Claude Code Desktop session folder, and runs a PowerShell merge script at login so conversations from the other workspace appear locally. It does not support the Claude CLI, macOS, or Linux, concurrent offline edits can conflict, and Microsoft Store sandbox redirection must be checked during installation.

Give the CLI an EXE or DLL and one or more virtual addresses to translate them into file offsets and print aligned x86-32 linear disassembly for inspection or Claude-assisted analysis. It uses pefile and Capstone, assumes addresses relative to the static ImageBase, and deliberately omits symbols, control-flow recovery, decompilation, and PDB parsing.

Choose a recipe for a proposal, contract, tutorial, report, or other document, supply the content and brand settings, and Katib composes component-based HTML and CSS into a PDF through WeasyPrint. It includes varied page layouts and 21 starter recipes, while custom recipes, components, and brand profiles can be packaged, shared, imported, or installed from its registry.

Drop lecture PDFs into the input folder and run the Claude Code skill to produce a site configuration and deployable HTML containing equation sandboxes, flashcards, multiple-choice quizzes, diagram labels, and concept checks. It targets students, instructors, and ed-tech builders, but the pre-0.3 packages are not yet published, so the repository must be cloned, installed with Bun, and served over HTTP for local use.

The skill detects the stack, classifies frontend, backend, data, jobs, integrations, and infrastructure layers, explores routes and services, then writes a portfolio poster, a detailed multi-page diagram, and an optional user journey. A state file enables cheaper incremental updates after later commits, while the first run is more context-intensive and diagrams.net or draw.io is needed to view and edit the results.

The skill records a founder or small team’s skills, geography, constraints, network, and goals, then structures ideas, compares candidate verticals, brings in external research, and pressure-tests a beachhead recommendation. It supports both a guided sequence and an open advisor mode, but the current MVP stops at intake, exploration, vertical comparison, and beachhead selection; positioning, customer evidence, GTM, and ongoing review are deferred.

This small Claude Code plugin library currently offers two manual workflows. The ETL skill stages raw research material before transformation, while Tournament dispatches multiple parallel drafters, ranks their outputs with a decisive judge, and can synthesize the strongest result; automatic model invocation is disabled so people choose when the extra process is worth using.

Describe a product or service and the skill generates candidate brand names, checks default and custom TLDs in real time, then ranks the shortlist by availability, length, pronunciation, and meaning. It is aimed at founders and indie makers who want to shorten the naming loop. A local whois command is required, and some .app or .dev results rely on best-effort DNS checks.

Use natural-language requests to send, check, forward, or bulk-deliver SMS and RCS messages through a mobile messaging interface. The skill covers text and template messaging, with support described for richer media and interactive cards. It is intended for agent workflows and requires Python 3.6 or newer, the requests library, and valid APP_ID and APP_SECRET credentials.

Run a project, decision, or team meeting through six timed stages: purpose, principles, vision, brainstorm, organization, and next actions. The roughly eleven-minute structure keeps one discussion phase from consuming the rest and ends with concrete, owned, dated actions. The plain Markdown skill can be installed in Claude Code or adapted to other agent runtimes.

Route a learning goal to one of five modules for path planning, concept explanation, focused study sessions, source synthesis, or mathematics rebuilding. Plans include exit checks, explanations end with a control question, and sessions require an observable deliverable rather than passive consumption. It is designed to make learning active and verifiable.