Loading...
Loading...
Found 1,831 Skills
Best practices for building CLI applications across languages. Covers CLI design principles (Unix philosophy, command structure, subcommands vs flags), argument parsing (required/optional args, flags, environment variables, config files, precedence), user interface (help text, version info, progress indicators, color output, interactive prompts), output formatting (human-readable vs machine-readable JSON/YAML, exit codes), error handling (clear messages, suggestions, debug mode), cross-platform considerations (paths, line endings, terminal capabilities), testing strategies (integration tests, output verification, exit codes), documentation (README, man pages, built-in help), and language-specific libraries. Activate when working with CLI applications, command-line tools, argument parsing, CLI utilities, argument handling, commands, subcommands, CLI frameworks, or building command-line interfaces.
This blog post explores how to optimize HTTP client selection in Flutter applications based on the platform, using Cronet on Android and Cupertino's native client on iOS for improved performance and caching.
Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. Load this automatically at the beginning of sessions for cross-tool continuity.
Third-party perspective analysis and improvement skills for marketing pages. Targets: Landing Pages (LP), Home Pages (HP), Pricing Pages, Feature Pages, Blogs. Integrates CRO frameworks and direct response principles (Schwartz/Hopkins/Ogilvy). Usage scenarios: (1) Page audit/analysis requests (2) Conversion improvement consultations (3) Copywriting improvements (4) A/B test design (5) Implementation prioritization. Trigger examples: "Analyze my LP", "Want to increase conversion rate", "Review pricing page", "Improve hero section", "Optimize CTA", "HP improvement proposal"
Pre-commit quality checklist covering lint, typecheck, tests, code-spec sync, API changes, database migrations, cross-layer verification, and manual testing. Blocks commit if infra or cross-layer specs lack executable depth. Use when code is written and tested but not yet committed, before submitting changes, or as a final review before git commit.
Guides integrations across Fusion Core service APIs from a single installable skill. USE FOR: service discovery across apps, people, context, roles, notifications, reports, tasks, and other Fusion Core APIs; cross-service integration planning; choosing the right endpoint/model guidance for a workflow. DO NOT USE FOR: modifying Fusion backend source code, non-Fusion APIs, or generic cloud architecture work without a Fusion service integration target.
Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning, and cross-domain insights. Detects language, translates English to Chinese (faithfulness-expressiveness-elegance), guides reader to understand the author and encounter real questions. Use when user says '伴读', '陪我读', '读这篇', 'read with me', 'companion read', or shares a text/URL wanting guided reading.
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. OCD-level review and synchronization of project documents and agent memory after a session. MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "sync up", "tidy up docs", "tidy up", "update memory", "organize", "wrap up", "this phase is done", "newcomers can start directly", or any phrase suggesting a development milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. A standalone "tidy" with prior development context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
E2E testing with Playwright - Page Objects, cross-browser, CI/CD
Tauri development guidelines for building cross-platform desktop applications with TypeScript, Rust, and modern web technologies
FOX v0.1 — Fully autonomous multi-strategy trading for Hyperliquid perps via Senpi MCP. Forked from Wolf v7 + v7.1 data-driven optimizations (14-trade analysis: 2W/12L). Tighter absolute floor (0.02/lev, ~20% max ROE loss), aggressive Phase 1 timing (30min hard timeout, 15min weak peak, 10min dead weight), green-in-10 floor tightening, time-of-day scoring (+1 for 04-14 UTC, -2 for 18-02 UTC), rank jump minimum (≥15 OR vel>15). Scoring system (6+ pts), NEUTRAL regime support, tiered margin (6 entries max), BTC 1h bias alignment, market regime refresh 4h. 8-cron architecture. Independent from Wolf. Requires Senpi MCP, python3, mcporter CLI, OpenClaw cron system.