agentifind
Set up codebase intelligence for AI agents. Runs the agentifind CLI to extract code structure using LSP (pyright/tsserver) with tree-sitter fallback, then synthesizes a CODEBASE.md navigation guide. Run this skill to get a complete codebase map in .claude/ directory.
omk-stitch
Google Stitch design-to-code workflow with design system management. Trigger when user mentions Stitch, design-to-code, UI design, visual comparison, design.md, design system, ShadCN conversion, redesign from screenshot, or wants to pull designs from Stitch into local code. Also trigger when user says '做个页面', 'build a landing page', '用 Stitch 设计', 'convert design', 'export from Stitch', '设计系统', or uploads wireframes/screenshots for UI generation.
sdd-development
Specification-Driven Development (SDD) methodology for building software where specifications are executable and drive code generation. Use when users want to: (1) Create feature specifications with /speckit.specify, (2) Generate implementation plans with /speckit.plan, (3) Create executable tasks with /speckit.tasks, (4) Follow test-first, library-first development, or (5) Implement constitutional architecture principles. Essential for structured AI-assisted development workflows.
synth-eval
Run evaluations against task apps using Synth AI platform
building-ai-agent-on-cloudflare
Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling".
synth-train
Run GEPA prompt optimization using Synth AI platform
web3-audit
Smart contract security audit for Immunefi bug bounty. Analyzes Solidity contracts on EVM chains using Slither + Foundry. Covers access control, reentrancy, DeFi economic exploits (flash loans, oracle manipulation, MEV), protocol-specific logic (lending, DEX, bridges, vaults), and generates Foundry fork PoCs. Every finding MUST have concrete evidence, invariant violation proof, and USD impact estimate.
frappe-core-utils
Use when working with utility functions in Frappe v14-v16. Covers frappe.utils.* for date/time, number/money, string, validation, and file path operations. Prevents reinventing stdlib alternatives that break timezone awareness, locale formatting, or multi-tenancy. Keywords: frappe.utils, nowdate, flt, cint, fmt_money, getdate,, date calculation, format number, money format, validate email, how to calculate days between. add_days, date_diff, validate_email, pretty_date, get_files_path.
section-11
Evidence-based endurance coaching protocol (v11.31). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.
save-rollback
[ROLLBACK:to-last-working]=>[SAY:plain-language|hide-git-commands]
save-rollback
When things go wrong, go back to the last working version.
chainflip-version-bump
Use when bumping the Chainflip runtime version on the (e.g. 2.1 to 2.2), removing old migrations, and updating engine/runtime versions. Triggered by phrases like "version bump", "bump to X.Y", "remove old migrations", "prepare next release".
