Claude Skills by v1truv1us

Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

Summarize authored commits over a user-specified time period into a concise update

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Continuous iteration loop pattern for well-defined tasks with clear completion criteria. Use when getting tests to pass, implementing features with automatic verification, bug fixing with clear success conditions, or running automated development overnight. Provides prompt templates, safety guidelines, and integration patterns for ai-eng-system workflows.

Create a new OpenCode skill with AI assistance. Uses skill-creator for intelligent skill generation.

Build agent workflows with the Claude/Anthropic SDK. Use when creating Claude-powered workflow runners, multi-step research/review/fix loops, streaming, tool-use, retries, or mirroring agents/research-runner/anthropic.

Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow parity, tool calling, structured outputs, or adding a Gemini variant beside Cursor/OpenCode/Claude runners.

Build agent workflows with the OpenAI Agents SDK or Codex-style runner. Use for OpenAI-backed workflow adapters, handoffs, tool calling, research runners, or mirroring agents/research-runner/codex.

Build local agent workflows with the OpenCode SDK. Use when creating OpenCode-backed runners, Ralph loops, local repo automation, prompt sessions, retries, or mirroring agents/research-runner/opencode.

Build Pi-backed agent workflow adapters. Use when driving Pi from scripts, creating runners that mirror agents/research-runner/pi, integrating Pi subagents, or adding Pi parity for workflow SDK runners.

Coordinate a multi-repo refactor by fanning out subagents per repo, gathering changes onto a single feature branch named cook/refactor-<slug>-<short-sha>, and pushing for review. Pairs with the branch-guard PreToolUse hook to make pushes to main physically impossible.

Read the auto-memory graph (~/.claude/projects/*/memory/*.md), find cross-session patterns, and write a digest. The skill never mutates memory — output goes to a fresh file the user reads. The cron-driven version is the daily-brief-sdk dream-digest workflow, which writes to a separate dedicated directory.

Long-running Jira investigation that self-continues past natural stops until a written hypothesis with evidence citations is produced. Pairs with the cooking Stop hook and hard-stops at 10 iterations.

Full SEO and performance audit for any website. Use when asked to check SEO, run a lighthouse scan, audit performance, check accessibility, or validate structured data.

Self-continuing loop that fixes a deliberately failing test, reruns it, and exits cleanly when green. Smallest cooking-routines skill — pairs with the cooking Stop hook to keep iterating past natural stops.