Business & Operations

Use when arbitrage bot expertise is needed to unblock implementation decisions.

Use when choosing API architecture, service boundaries, and long-term interface evolution.

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

```bash refly skill list [options] --status <status> # Filter: draft, published, deprecated --mine # Show only my packages --tags <tags> # Filter by tags (comma-separated) --page <number> # Page number (default: 1) --page-size <number> # Page size (default: 20)

Schedule reminders and recurring tasks.

Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.

Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

Multiply all numbers in a text file by 10 and save to a new file. Use when user mentions multiply numbers by 10, process number file, batch calculation.

Minus all numbers in a text file by 5 and save to a new file. Use when user mentions read a file minus numbers by 15, process number file, batch calculation.

add all numbers in a text file by 10 and save to a new file. Use when user mentions read a file add numbers by 10, process number file, batch calculation.

用于 Workflow Planning 阶段的占位算子。当前 Skill 库不存在满足用户需求的业务 Skill 时，使用本算子保持 DAG 数据流完整，等待后续生成真实 Skill 后替换。

Parker's dreaming run for the brand and the person using it — the planning half of the living layer. Reads the day's comms (the conversations the user had with Parker first, then any connected comms) against the vault and returns proposals across six buckets — context updates, skill improvements, schedules to create, new ideas to research, new open loops, and the person (what Parker now understands about them and what to tee up for them) — into dreaming/proposals/pending. Captures verbatim; p...

The front door to building a brand's brain. Run this when standing up a new brand — it needs the Parker MCP connected for data, and the brand's synced folder from the Parker Desktop app (which creates the brand's repo and usually opens this very session inside it). It welcomes the person, works inside the folder Parker Desktop keeps in sync, connects and tests the data, asks the short brand intake (the things Parker genuinely can't observe), runs the full build in dependency order, confirms e...

Write ad scripts that sound spoken, not written, by adapting proven reference ads into the brand's own voice fingerprint. AI cannot write good scripts cold — references are the default input and the brand script-voice profile is the sound. Every script passes the spoken-script-voice AI-tells check and read-aloud test. Net-new from scratch is the rare fallback.

Keep the brand brain from going stale. Reads running-notes/refresh-schedule.md and each standing doc's refresh_by frontmatter, surfaces what is overdue or due soon, walks the Phase 1→2→3 dependency spine to catch docs made stale by upstream changes even when their own date is fine, and re-runs the generating prompt for each — carrying the prior version forward and re-stamping the dates. Use weekly as a scheduled routine, or whenever asked to refresh, re-run, or check the freshness of the bran...

The full iteration flow in one skill — choose which ads to iterate on, then make the iterations. If the user names a specific ad, go straight to making iterations; if they ask account-level (which ads should we iterate on, what to iterate this month), select the ads first, then make iterations on each.

Guidance on reading, parsing, and processing various file formats (CSV, JSON, YAML) commonly used in legal and compliance tasks