Claude Skills by therapys

Run the agent as an autonomous maintainer of a product — set it up once, then loop on small, verified, logged improvements while keeping the product deployable at all times. Use when the user says 'maintain this product by itself', 'run it on autopilot', 'set up an autonomous maintainer', 'keep improving this overnight', 'self-maintaining product loop', or wants the agent to continuously ship and verify changes until stopped.

Read this skill before making git commits

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Compress one or more SKILL.md files so they consume less context on load while preserving 100% of their value — same triggers, capabilities, guardrails, thresholds, and output. Use when the user says 'compress this skill', 'optimize skills for context', 'make skills use less context', 'slim down the skills', 'reduce skill token usage', 'shrink SKILL.md', or wants a skill or whole skill suite trimmed without losing behavior.

Reverse-engineer a project's real, shipped design language into a reusable design skill, so any agent can build or restyle pages that match it. Use when the user says 'create a design skill from this project', 'make a design skill from the current project', 'extract the design system', 'capture this app's design as a skill', 'codify our design language', or 'reverse-engineer the design system into a SKILL.md'.

Measure and improve the readability of English copy with the Flesch–Kincaid grade-level test. Use when proofreading or simplifying READMEs, documentation, product copy, help text, announcements, or other prose, especially when a target reading grade is requested.

Design and implement distinctive, production-ready frontend interfaces with strong aesthetic direction. Use when asked to create or restyle web pages, components, or applications (HTML/CSS/JS, React, Vue, etc.).

Use the gog CLI for safe Google Workspace automation: Gmail and email, Calendar and events, Drive files, Docs, Sheets, Contacts, Tasks, Chat, and other Google services. Covers auth, stable JSON, scoped reads, and approved writes.

Drive PostHog through the claude.ai `exec` connector — query analytics and entities (HogQL, insights, funnels, retention, web analytics), investigate LLM spend, and audit MCP tool quality. Use when the user mentions PostHog or HogQL, an insight/dashboard/funnel/cohort/experiment, asks 'how much are we spending on LLMs / which model is most expensive / why did cost spike', 'which MCP tool errors most / is slowest / how reliable is tool X', or asks to query or aggregate product data. Read befor...

Take the current changes from a dirty tree to an open pull request — branch, commit, push, and open the PR. Use when the user says any of: 'create a pr to main/dev', 'open a pr', 'push to main', 'commit and push', 'push this to git', 'ship it', 'push to the linear branch and open a draft PR', or asks to do the same across multiple repos ('push to each repo except infra').

Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs around the fire window, and rank likely causes. Use whenever the user asks "why did this alert fire", "what caused alert X", "investigate this alert", "RCA for the alert that paged me", "what's wrong with [service]" in the context of a recent fire, or otherwise asks for a root-cause analysis of a firing or recently-fired alert. Read-only...

Teach the user anything so it actually locks in and is understood, not just memorized. Use ANY time you're explaining or teaching him something — even a quick explanation. Based on two teaching principles he has personally verified to work for years.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

Generate or refresh a repo's AGENTS.md (the source-of-truth agent context file) and its one-line CLAUDE.md pointer. Use when the user says 'update the claude.md', 'update AGENTS.md', 'analyze this project and update the context file', 'write an AGENTS.md', or after a stack/structure change makes the current file stale.

Add a correct, minimal visual to a lesson — a diagram or geometric picture — that renders inline in the Obsidian log. Use when an idea is genuinely clearer as a picture: a dependency graph, system/flow, sequence, state machine, tree, comparison, or a spatial/geometric thing (coordinate geometry, number line, vectors, a plot, a physical layout). Outsources authoring+rendering to a maker subagent that verifies the image by looking at it, then you embed the returned file.