productivity▌

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Lightweight validation framework for testing risky hypotheses before expensive product development. \n \n Defines five prototype flavors (feasibility checks, task-focused tests, narrative prototypes, synthetic data simulations, vibe-coded probes) matched to specific learning goals, not tooling preference \n Emphasizes disposability and narrow scope: PoL probes are reconnaissance missions meant to surface harsh truths and be deleted, not scaled into MVPs \n Includes fill-in template with hypothes

Mode: Cognitive/Prompt-Driven — No standalone utility script; use via agent context.

Find bugs that static code reading misses: state interaction side effects, race conditions between sequential calls, and handlers that silently undo each other.

Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.

Extract structured data from websites using BeautifulSoup and requests - turn any webpage into usable data.

Identify, design, and implement no-code automation workflows to save time and scale as a solopreneur. \n \n Covers the full automation lifecycle: auditing tasks for automation potential, calculating ROI, selecting tools (Zapier, Make, n8n), designing workflows, and testing before deployment \n Includes practical templates for common workflows like lead capture, client onboarding, content distribution, and payment tracking \n Emphasizes error handling, monitoring, and maintenance to prevent silen

Design a pricing strategy grounded in value delivery, competitive positioning, and willingness to pay.

PUA P9 管理者 — 写 Prompt 不写代码 \n \n 懂战略、搭班子、做导演。管 P8 不管 P7。你的代码是 Prompt。 \n \n 详细协议见 references/p9-protocol.md 。加载后按协议执行。 \n Agent Team 架构详见 references/agent-team.md 。 \n 核心行为遵循 /pua 核心 skill 的三条红线和旁白协议。

Verify data freshness by checking table timestamps and update patterns against a staleness scale. \n \n Identifies timestamp columns using common ETL naming patterns ( _loaded_at , _updated_at , created_at , etc.) and queries their maximum values to determine age \n Classifies data into four freshness statuses: Fresh (< 4 hours), Stale (4–24 hours), Very Stale (> 24 hours), or Unknown (no timestamp found) \n Provides SQL templates for checking last update time and row count trends over rece