Shape agent capabilities into your workflow.

Pitch Generator asks for missing context such as audience, goal, company stage, traction, timing, and the requested next step before producing a one-line pitch, a short paragraph, and an investment-style version. For pre-seed fundraising, it emphasizes problem validation, founder-market fit, and use of funds while adapting to different investor types. Local benchmark decks can inform messaging patterns without copying their claims or wording.

The plugin extracts scene-change keyframes, transcribes speech, and aligns both into timestamped summaries that Claude Code can use for later questions or implementation work. It can also produce a detailed walkthrough and a narration transcript. Setup requires Python, ffmpeg, and Whisper-related dependencies, and untrusted videos may carry prompt-injection risk.

The Claude Code skill provides an offline, modular reference for authentication, order placement, market data, WebSocket subscriptions, CTF operations, bridging, gasless transactions, fees, and error handling. Examples cover both Python and TypeScript. It guides integration work rather than operating as a trading bot, and real deployments must respect current geoblocking and rate-limit rules.

The skill interviews you about scope, constraints, and style preferences, presents viable pattern choices, and challenges unnecessary complexity before drafting the architecture. Its output covers structure, components, data flow, risks, migration or implementation tasks, and Mermaid diagrams. It supports greenfield planning, architecture reviews, and restructuring, with tailored references for Node/Express, Unity, and C++/CMake.

This portable pack contains 25 Agent Skills for recurring engineering work such as task breakdown, test-driven development, debugging, security review, migrations, documentation, pull requests, and deployment. Each skill defines completion checks and explicit points for human judgment. The same directory layout can be used with Claude Code, Codex, Cursor, and other compatible assistants.

With Claude in Chrome connected to a running development server, the skill captures the viewport, console errors, failed network requests, and page structure, then traces the problem back to source files. It can edit the code and recheck the browser, or instead produce an HTML report, file a GitHub issue, or watch for new errors.

This writing skill edits reports, proposals, emails, white papers, status updates, and other professional copy for common AI signals such as inflated significance, vague attribution, filler, formulaic transitions, and promotional language. It rewrites toward specific, direct statements while keeping the tone professional and confident. The same guidance can be installed or adapted across several AI and editor platforms.

Use one skill to assemble quantitative Polymarket bots with Kelly sizing, Bayesian updates, liquidity checks, and multi-source signals, and another to score wallets and flag whale, clustering, or possible insider activity. Templates, scanners, backtesting, and terminal alerts are included. The project is educational and recommends dry-run testing before risking capital.

Use a product requirements document and the actual repository to produce tailored SOUL.md, AGENTS.md, CLAUDE.md, and MEMORY.md files, or compare existing governance against current code and requirements. The skill marks unresolved decisions explicitly and audits before overwriting. This repository is the earlier stage of the workflow; its author recommends a separate successor for issue-driven automation.

Teach a coding agent to generate Glubean checks from specifications or natural language, execute them through MCP, inspect structured expected-versus-actual failures, and rerun after fixes. The same workflow supports phased migration from Postman, Apifox, OpenAPI, and legacy tests, or contract-first design before an endpoint exists. Stable files can move from exploration into regression suites and CI without a rewrite.

Use this knowledge base to draft prompts for interiors, exteriors, landscapes, aerial views, and commercial architectural scenes. It also guides composition, camera choices, lighting, materials, and image preparation, with workflow references for SketchUp, Revit, ArchiCAD, Blender, and D5 Render. A glossary maps more than 150 archviz terms to useful prompt language.

Specify a research area, desired result count, and optional university or country to collect matching faculty information. The skill prioritizes official department, faculty, and research-group pages, then uses Google Scholar for publication context, returning public emails and recent papers in Markdown or Excel. Students should still verify the records before contacting prospective supervisors.

Provide a product URL, feature list, research notes, or roadmap and receive an interactive HTML map connecting customer outcomes, needs, business goals, current solutions, confidence, and competitive context. Teams can use it in working sessions to distinguish essential value from differentiators, edit or rearrange nodes, track changes, and save a self-contained snapshot for later discussion.

Skill Finder reads local Claude Code history, transcripts, skills, settings, and CLAUDE.md files to identify repeated behavior across projects. It produces frequency tables, avoids recommending workflows already automated, and ranks quick wins across persistent instructions, skills, agents, and plugins; the analysis itself is read-only.

Harness Plan keeps a long development campaign resumable across Claude Code sessions using compact state, one active feature contract, session summaries, deterministic transition scripts, and risk-gated verification. The same /harness-plan command starts or resumes work, while optional change units split larger features into reviewable stages and companion discipline skills add more structured testing and safeguards.

Capsulate turns a tracking request into a Gmail search, an extraction schema, local structured data, and a self-contained HTML dashboard that opens in the browser. Gmail messages are fetched through the gws CLI and results stay under ~/.capsulate, but email snippets are sent to Anthropic's API for extraction, which matters for sensitive inboxes.

Upstream Sync avoids blindly merging an original repository into a customized fork. It fetches upstream diffs, compares each file with local modifications, chooses whether to apply, adapt, partially apply, or skip the change, edits files directly, records the last synchronized commit, and reports every decision so future runs remain incremental.

Context Bridge packages your stack, closed decisions, constraints, current state, and next task into a copyable Context Block for Cursor, ChatGPT, Gemini, Claude Code, and other tools. It can generate a handoff from the current session or decompile a messy conversation into a cleaner brief, including a compact memory block.