Tamircohen28
UserPersonal Claude Code plugin — 15 bundled skills, smart worktree hooks, and MCP server stubs. One /plugin install and you're set.
Categories
Indexed Skills (16)
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
dark-terminal-doc
Create rich technical HTML documents — comparison tables, reference sheets, feature breakdowns, changelogs, release notes — using a dark terminal-inspired design system. Use when the user asks to produce a polished HTML doc, reference page, or technical comparison that should look sharp and developer-facing. Triggers on: "make a comparison table", "write a reference doc", "create a feature breakdown", "produce a technical document", "styled HTML doc".
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Claude to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
docs-review
Audit and fix every Markdown doc in this repo (README.md + docs/**) — visual cleanliness, freshness vs git history, removal of stray plan/work files, and validity of all links. Use whenever the user wants a docs sweep, refresh, audit, cleanup, link-check, or consistency pass.
plan-dev
Plan development work — structure tasks into phases, review with user, then create GitHub issues. Use when the user asks to plan, decompose, structure, organize, or break down a task, spec, issue URL, or list of fixes into phases before coding.
pr-dev
Manage PR lifecycle — fetch fresh PR state, address every unresolved review thread, fix CI, get user approval, then squash-merge and clean up. Use when the user wants to drive a PR through review and merge.
start-dev
Start development — create worktree, implement tasks, validate, push, and open a PR. Use when the user has approved a plan or wants to begin coding from a GitHub issue, task description, or spec file. Covers everything from 'here's what to build' to 'PR is open for review'.
targeted-debug
Focused debug of a specific production issue — read only files named in the stack trace, error message, or user input; form a hypothesis from observable evidence; do NOT explore the codebase broadly. Use when the user wants to understand a specific bug or error WITHOUT spinning up a full /investigate pipeline.
task-audit
Audit a completed development task or branch — review git diff quality, commit conventions, test coverage of changed files, leftover TODO/FIXME markers, and overall PR readiness. Use after finishing an implementation task to verify quality before requesting review.
changelog-review
Claude Code documentation expert. Fetches live official docs to answer questions about Claude Code features, or diffs changelogs between versions to show what changed. Use when the user asks about Claude Code capabilities, hook events, skills, subagents, MCP servers, settings, CLI flags, or asks what changed between two versions.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
mcp-pagination
When using MCP tools that support pagination (Jira, Slack, Google Calendar, Trino, GitHub, etc.), ALWAYS include pagination parameters. Use this skill whenever working with list/search MCP operations to enforce mandatory pagination.
repo-polish
Take a personal project directory, scan for employer IP, clean it up, and scaffold world-class repo infrastructure (README, user docs, engineering docs, CI/CD, PR templates, CLAUDE.md, CHANGELOG, CONTRIBUTING, LICENSE), then upload to GitHub account TamirCohen28 after approval. Trigger on: 'polish this repo', 'prepare project for GitHub', 'make it public-ready', 'clean up and publish', 'world-class repo', 'repo-polish', or any request to prepare a project for open-source / personal GitHub release.
find-skill
Search the leading skill / agent / plugin marketplaces in real time and rank the top N matches for a user query. Use when the user asks 'find a skill for X', 'is there a plugin that does Y', 'what skill should I use to Z', 'recommend an agent for W', 'compare skills for ...'. Queries Anthropic claude-plugins-official, OpenAI Codex Directory, Gemini CLI Extensions, Smithery, mcp.directory, VoltAgent/awesome-agent-skills, wshobson/agents, obra/superpowers, mattpocock/skills, and Claude marketplace aggregators. Returns a numbered list with a match score (0-100), a quality score (0-10), name, description, and URL. Trigger words: 'find skill', 'find a plugin', 'skill for', 'plugin for', 'agent for', 'recommend a skill', 'search skills'.
session-report
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.