wdm0006

Manages Python library releases including semantic versioning, changelog maintenance (Keep a Changelog format), release automation with GitHub Actions, and deprecation workflows. Use when planning releases, writing changelogs, automating release pipelines, or…

Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use…

Design and review long-running batch or sync jobs that process many items against a remote API and persist checkpoint state — exit codes that report partial failure, checkpoints that are safe to resume, per-item tolerance vs. fatal abort, telling "zero" apart…

Land a change everywhere the same fact is stated — enumerating the full surface inventory (landing copy, docs, machine-readable summaries, changelog badges repeated across every page, sitemap, README, descriptions embedded in code, and untyped frontend…

Compute statistics, scores, and flags from samples that may be too small to support them — undefined dispersion returned as 0.0 and tripping a minimum threshold, sentinel choice (None vs 0 vs NaN), threshold blocks gated on "was this measured", reports that…

Designs and implements pytest test suites for Python libraries with fixtures, parametrization, mocking, Hypothesis property-based testing, and CI configuration. Use when creating tests, improving coverage, setting up testing infrastructure, or implementing…

Audits Python libraries for security vulnerabilities using Bandit, pip-audit, Semgrep, and detect-secrets. Identifies SQL injection, command injection, hardcoded credentials, secrets exposed through tracebacks, weak cryptography, and insecure deserialization.…

Provides an opinionated reference architecture for production Python web apps — FastAPI + async SQLAlchemy + Postgres, pydantic-settings config, Stripe billing, server-rendered Jinja or a decoupled SPA, deployed as a single Docker image on a managed platform…

Generates a prioritized follow-up list from Evergreen CRM based on overdue actions, stale contacts, and interaction cadences. Use when planning your week, checking who needs attention, or building a daily outreach list.

Identifies dormant contacts in Evergreen CRM and drafts natural re-engagement messages. Use when you want to reconnect with people you haven't spoken to in months, revive stale relationships, or systematically re-engage your extended network.

Generates a narrative summary of everything known about a contact in Evergreen CRM — how you met, what you've discussed, mutual connections, and pending threads. Use when you need to quickly refresh your memory before reaching out, replying, or meeting…

Generates a weekly relationship management digest from Evergreen CRM — interactions logged, follow-ups completed vs missed, network growth, and a spotlight contact. Use for weekly reviews, accountability, or planning the week ahead.

Monitors news and web mentions for Evergreen CRM contacts and their companies — funding rounds, product launches, press coverage, job changes. Use to surface timely conversation starters and stay informed about your network's activities.

Parses recent Gmail activity and logs interaction summaries to Evergreen CRM contacts — without storing full email bodies. Use when you want to sync email activity to your CRM, update interaction history, or keep Evergreen current with your communications.…

Parses unstructured text (email signatures, business cards, LinkedIn profiles, meeting notes) into structured Evergreen CRM contacts. Use when adding new contacts from raw text, importing contacts from emails or messages, or batch-creating contacts from event…

Researches and enriches Evergreen CRM contacts with publicly available information — LinkedIn details, company info, recent news, and shared context. Use when a contact has sparse details, before an important meeting, or when batch-updating stale records.

Generates a weekly summary of your idea.log activity — new ideas captured, progress made, ideas completed or abandoned — with suggestions for what to focus on next. Use at the start or end of each week.

Reviews all pending ideas in idea.log, cleans up stale or duplicate entries, improves descriptions, suggests tags, and helps prioritize what to work on next. Use when your idea backlog feels cluttered or you want to start a focused work session.

Picks an idea from your idea.log backlog and autonomously starts building it — scaffolding a project, writing initial code, setting up the repo. Use when you want to turn an idea into a real project without doing the setup yourself.

Breaks a large or complex idea into smaller, actionable sub-ideas, each with their own first steps and tags. Creates the sub-ideas in idea.log and links them back to the parent. Use when an idea feels too big to start.

Finds ideas that have been sitting untouched in your backlog and helps you decide what to do with each one — revive it, refine it, or abandon it. Use when your backlog has accumulated cruft over time.

Conducts an interactive conversation to flesh out a vague or half-formed idea into something specific and actionable. Asks clarifying questions, suggests tags and first steps, and updates the idea in idea.log. Use when you have a rough concept that needs…