research
claudeReviewable ML research: literature, planning, methodology review, bounded runs, sweeps, implementation verification, ablations, retrospectives, Kaggle, and setup
10 skills · 2 agents · hooks
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Reviewable ML research: literature, planning, methodology review, bounded runs, sweeps, implementation verification, ablations, retrospectives, Kaggle, and setup
10 skills · 2 agents · hooks
Write fast, stable Biloba tests in Go/Ginkgo/Gomega: setup, polling and matcher idioms, locators, realistic input, visual assertions, API lookup, diagnostics, flake prevention, and flake hunts.
12 skills
Semantic code search and navigation for Claude Code. Requires a self-hosted cix (CodeIndeX) server — free, MIT, ~10-minute install (https://codeindex.app); the plugin is the client. Bundles the cix CLI, slash commands, behavioral hooks, and the cix + cix-workspace skills (CLI-based) plus the cix-workspace-investigator sub-agent for cross-project research across cix workspaces.
2 skills · 8 commands · 1 agent · hooks
Draft memos, demand letters, contracts, motions, deposition summaries, case timelines, and AI risk memos
4 skills · 8 commands
Guardrail hooks, a plan → implement → verify → crosscheck loop, a /critical-review exit gate with a pluggable reviewer backend, doc-tiering commands, a /setup-check, a browser-MCP skill and a terse output style for Claude Code.
1 skill · 10 commands · hooks
Plan summaries, portfolio reviews, tax-loss harvesting, ESG screens, regulatory tracking, and multi-jurisdiction tax
3 skills · 8 commands
Write job descriptions, draft policies, run RTO and severance comms, audit reviews and JDs for bias
3 skills · 8 commands
Wrapper skills over superpowers:* that inject tea-rags signals (risk, ownership, churn, impact) into brainstorming, planning, execution, debugging, and review flows
10 skills · hooks
Open-source maintenance: issue and repository analysis, PR review, feedback resolution, release-readiness assessment, setup, and 4 specialist agents
5 skills · 4 agents · hooks
Forge-focused skills and MCP configuration for Atlassian Forge: scaffold and deploy apps (forge create, templates, dev spaces), build Teamwork Graph connectors for Rovo Search/Rovo Chat, pre-deploy review, systematic debugging, plus Forge docs and Atlassian Design System lookups via MCP.
7 skills · 2 MCP servers
Skills for building Android apps with Tap Strap, TapXR, and TapBand (coming soon, same BLE API as TapXR): permissions, connect, taps, raw and processed air gestures, vision models, IMU motion, raw sensors, and knob / D-Pad recipes.
9 skills
PLAN/ACT/EVAL workflow, specialist agents, and reusable skills for systematic TDD development
6 commands · 1 MCP server · hooks
Git automation - PRs, releases, branches, worktrees
7 skills · hooks
Text-only factory skills for team leads: changing a running worker's spec, briefing workers, triaging stuck PRs
8 skills
Spec workflow, MUX orchestration, and product management
6 skills · 1 agent
Write fast, stable Biloba tests in TypeScript/Vitest: daemon and shared-Chrome setup, sessions and locators, polling assertions, realistic input, visual assertions, diagnostics, flake prevention, and flake hunts.
7 skills
Opinionated Go development skill — architecture, conventions, production readiness, repo/CI hygiene, review, and MCP/agent patterns — plus six language-agnostic companion skills: ponytail minimal-change mode, ponytail-review, ponytail-audit, pr-simplify, test-audit, technical-documentation.
7 skills
Run Codex review, adversarial review, and second-pass handoffs from Claude Code while keeping ThumbGate reliability memory in the loop.
6 skills · 1 MCP server
LSP and MCP support for DTCG design tokens - intelligent autocomplete, hover docs, diagnostics, code actions, and AI-native token discovery, validation, search, and conversion
1 MCP server · LSP
Text-only factory skills for the coder: guard changes, self-review
7 skills
Text-only factory skills for the researcher: research-brief, source-evaluation, tool-comparison, benchmark-protocol, plugin-evaluation, report-writing, evidence-review
7 skills
Reviews spec files and conducts exhaustive interview sessions to resolve ambiguities, gaps, and missing details until specs are implementation-ready.
3 skills · 3 commands
Control your Keenetic router from Claude: who is on the network, Wi-Fi, interfaces, routing policies, and safe configuration changes
4 skills · 1 command · 1 MCP server
Deterministic reliability instrument: live gauges + non-native repairs for coding agents. Requires the mindlas CLI on PATH (install from source: pip install -e .).
5 commands · hooks
Plan with a strong model, build with cheap ones, verify everything, escalate only on failure.
1 skill · 5 agents
Reflect on the current conversation and save reusable learnings across four categories (memory, lesson, skill stub, project-doc) — confirmation-first, Reflexion-style anti-patterns, dual-write to CLAUDE.md + AGENTS.md for Codex compatibility.
2 skills · 3 commands · hooks
Four trilingual Pokémon Champions skills: battle dex, metagame facts, exact damage/speed calculation, and audited single/double team building without a synthetic strength score.
5 skills
Todoist integration - link Claude Code sessions to tasks and automatically track progress
4 commands · hooks
Сжимай ответы Claude на русском или казахском. -65-80% токенов. Техника целиком. /cavemanov или /cavemanov-kk.
4 skills · hooks
Google Workspace MCP server (Gmail, Drive, Docs, Sheets, Slides, Calendar, Forms, Chat, Photos, Contacts) plus skills for the card/email DSL, code mode, and Qdrant search over past tool responses.
4 skills · 1 MCP server