- 📄 chain-of-verification-isolated.md
- 📄 chain-of-verification-process.md
- 📄 shared-capy-knowledge-protocol.md
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning. --- # Chain-of-Verification (CoVe) CoVe is a verification technique that improves response accuracy by making the model fact-check its own answers. Instead of accepting an initial response at face value, CoVe instructs the model to generate verification questions, answer them independently, and revise the original answer based on findings. ## Conventions Read capy knowledge base conventions at [shared-capy-knowledge-protocol.md](shared-capy-knowledge-protocol.md). **Capy restriction:** CoVe is a read-only verification tool. Do NOT call `capy_index` or `capy_fetch_and_index` during this workflow. Use `capy_search` only. If corrections reveal knowledge worth persisting, the calling agent handles indexing after CoVe completes. ## When to Use This Skill
Build Stellar blockchain applications in Swift using stellar-ios-mac-sdk. Use when generating Swift code for transaction building, signing, Horizon API queries, Soroban RPC, smart contract deployment and invocation, XDR encoding/decoding, and SEP protocol integration. Covers 26+ operations, 50 Horizon endpoints, 12 RPC methods, and 17 SEP implementations with Swift async/await and callback-based streaming patterns. Full Swift 6 strict concurrency support (all types Sendable).
Search and retrieve scientific papers from ArXiv
Spiceflow is a super simple, fast, and type-safe API and React Server Components framework for TypeScript. Works on Node.js, Bun, and Cloudflare Workers. Use this skill whenever working with spiceflow to get the latest docs and API reference.
Support discovery and research workflows using PM Brain’s discovery frameworks (research interviews, continuous discovery, JTBD, segmentation, opportunity assessment, idea validation, problem-solution space, product-market-fit).
Bug confirmation and reproduction. Use when: (1) a bug has been found by model checking and needs code-level validation, (2) reproducing a bug in the real system to confirm it is not a false positive, (3) assessing whether a TLA+ counterexample maps to a real triggerable scenario.
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Use this skill for creating or refining an academic slide deck and the talk built around it: structuring a conference talk, thesis defense, lab meeting, or paper-to-slides deck; deciding the narrative arc and slide breakdown; improving slide design and visual hierarchy; planning rehearsal, timing, Q&A, and backup slides; or generating the .pptx. Reach for it when the user is shaping the presentation itself. Do not use for writing the paper, producing standalone speaker notes/scripts/transcripts, making posters, creating isolated figures/charts outside a slide deck, or building non-academic presentations.
Generates multiple distinct visual variations of a component or page, exploring divergent styles, layouts, and aesthetic directions. Use when the user wants to explore design alternatives, iterate on a UI with variety, compare visual approaches, or generate multiple versions of a component or page.
- 📁 .github/
- 📁 bridge/
- 📁 core/
- 📄 .gitignore
- 📄 .npmignore
- 📄 CHANGELOG.md
IM bridge for AI coding tools — chat with Claude Code / Codex from Telegram, Discord, or Feishu. Approve permissions, get streaming responses, manage sessions from your phone.
- 📁 references/
- 📁 scripts/
- 📄 .gitignore
- 📄 README.md
- 📄 setup.py
Semantic code search and AI-powered codebase Q&A across indexed repositories. Use when understanding code beyond local files, exploring dependencies, discovering cross-project patterns, planning features, debugging, or onboarding. Queries like "How does X work?", "Show me Y patterns", "How is library Z used?". The default path is semantic search plus grep search; chat-with-codebase is slower, more expensive, and usually secondary.
One-time setup for /verify. Auto-detects dev server and indexes the app.
Architecture Decision Records management. Actions: create (new ADR), list (show all), search (find by keyword). Use when: (1) making architecture decisions, (2) choosing between technologies, (3) documenting trade-offs. Triggers: /adr, 'architecture decision', 'decision record', 'document decision'.
