AI & ML

lprior-repo Bundle

Ruthless QA agent that ACTUALLY executes commands/APIs and deeply inspects results like a product owner.

menkesu Skill

Builds AI-native products using Dan Shipper's 5-product playbook and Brandon Chu's AI product frameworks. Use when implementing prompt engineering, creating AI-native UX, scaling AI products, or optimizing costs. Focuses on 2025+ best practices.

skinnyandbald Skill

Detects your project's full technology stack, then generates a comprehensive research prompt tailored to a specific topic like security, performance, or testing.

jagreehal Bundle

Dispatches independent subagents in parallel with clear contracts and merge discipline. Use this skill when multiple independent research or implementation strands can proceed without shared mutable state. Do not use when/for sequential dependent steps, or creating git worktrees themselves (use git-worktrees).

no-problem-dev Skill

SwiftUI プレビュー・Swift REPL・Apple ドキュメント検索。Xcode ネイティブ MCP 経由でのみ利用可能。「preview」「SwiftUI preview」「プレビュー」「REPL」「playground」「Swift 実行」「Apple docs」「ドキュメント検索」などのキーワードで自動適用。

no-problem-dev Skill

テストケースの作成を対話的に支援するユーティリティスキル。アプリの画面を観察しながらテストケースを生成できる。「テストケース作成」「QA ケース作成」「テスト項目作成」などのキーワードで自動適用。

no-problem-dev Skill

QA テスト結果を集約し、構造化レポートを生成するフェーズスキル。失敗テストの分析と次のアクション提案を含む。「QA レポート」「テスト結果」「QA 結果」などのキーワードで自動適用。

no-problem-dev Skill

テストケースの実行制御を行うフェーズスキル。各テストケースを qa-runner → qa-judge のパイプラインで実行し、アプリ状態管理と結果収集を担当する。ios-qa-workflow から参照される。

no-problem-dev Skill

QA テストスイートの解析・前提条件解決・実行計画策定を行うフェーズスキル。ios-qa-workflow から参照される。「テスト計画」「QA 準備」「テストスイート解析」などのキーワードで自動適用。

no-problem-dev Skill

AI QA Agent のメインオーケストレーター。テストスイートまたは個別テストケースの QA を段階的に実行する。フェーズスキルに委譲して段階的開示を行い、サブエージェントでコンテキスト隔離を実現する。「QA」「動作確認」「テストケース実行」「smoke test」「E2E」「手動テスト」「結合テスト」などのキーワードで自動適用。

microsoft Bundle

Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "skill structure", "review skill", "skill PR", "skill compliance", "SKILL.md format", "skill frontmatter", "skill best practices".

ihj04982 Skill

Generate and run end-to-end tests with Playwright. Invokes e2e-runner agent. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts. Use when testing critical user journeys or multi-step flows.

ihj04982 Skill

Restate requirements, assess risks, and create step-by-step implementation plan. Invokes planner agent. WAIT for user CONFIRM before touching any code. Use when starting a new feature, making architectural changes, or requirements are unclear.

ihj04982 Skill

Incrementally fix TypeScript and build errors. Invokes build-error-resolver agent. Use when build fails, type errors occur, or the user asks to fix the build.

ihj04982 Skill

Comprehensive security and quality review of uncommitted changes. Invokes code-reviewer agent. Use when reviewing PRs, before committing, or when the user asks for a code review.

ihj04982 Skill

Safely identify and remove dead code with test verification. Invokes refactor-cleaner agent. Use when cleaning unused code, removing duplicates, or reducing bundle size.

ihj04982 Skill

Lists available Cursor agents (planner, architect, tdd-guide, code-reviewer, security-reviewer, build-error-resolver, e2e-runner, refactor-cleaner, doc-updater) and when to use each. Use when the user asks which agent to use, how to delegate work, or what agents are available.

musserlab Bundle

Phylogenetic tree visualization and formatting with ggtree (R) or iTOL (web). Use when rendering a phylogenetic tree as a figure, choosing tree layout, coloring branches or labels by taxonomy, collapsing clades, displaying support values, or adding overlays to a tree. Do NOT load for tree inference (use protein-phylogeny skill) or domain annotation (future separate skill).

beshkenadze Bundle

Create new Claude Agent Skills. Use when asked to create, build, or develop a skill.

benjaming Bundle

Run a structured prompt N times and consolidate via deterministic vote (self-consistency, Wang et al. 2022). Use when output stability matters more than latency — code review, finding extraction, classification, triage. Triggers on "self-consistency", "consensus", "vote on", "stable output", "run N times and merge".

beshkenadze Skill

Run a model through the omni-bench benchmark to MEASURE it — produce a run-artifact and score it, then read the numbers. Use when asked to run, benchmark, measure, evaluate, or "test the results of" a model with omni-bench — ASR (WER/CER, RTFx) or text generation (tok/s, TTFT, prefill tok/s, prompt-cache speedup). Covers the adapter seam (Transcriber/Generator), the prepare→run→score→diff CLI flow, the offline no-download smoke task, and how to interpret each metric. NOT for publishing to a leaderboard (use omni-bench-publish) or changing the framework itself (use omni-bench).

benjaming Bundle

Build or harden a reliable browser-automation skill through a self-improving loop, with no Anthropic API key. Each iteration runs a headless `claude -p` inner agent that drives a local isolated Chrome via chrome-cdp, reads the run trace, adds one heuristic to strategy.md, and repeats until the task passes — then publishes a standalone skill. Use when asked to make a browser navigation task reliable, build/improve a browser automation skill, auto-tune a web workflow, or run a "self-improving browser loop". Local Chrome only (no Browserbase/remote, no codegen, no parallel fan-out).

lohasle Skill

Manages connected MCP sources for enterprise search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.

lohasle Bundle

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows. Use when users want to customize a plugin, replace tool placeholders, or configure MCP servers for a plugin. This skill requires Cowork mode with mounted plugin directories and will not work in remote or standard CLI sessions.

ruvnet-ruvector Skill

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

ruvnet-ruvector Skill

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

mhylle Bundle

Build evaluation harnesses for AI-assisted implementations — capability evals, regression tests, graders (exact-match, LLM-judge, code-exec, rubric), and standardized metrics (pass@k, accuracy, latency, cost). Use when the user wants to set up or run evals, benchmark agents/skills, create regression test suites for prompts or AI features, compare model/prompt variants, or measure implementation quality. Triggers on "set up evals", "create eval harness", "benchmark this skill", "regression test the prompt", "run evals", "/eval-harness", or any request to systematically measure AI output quality.

mhylle Bundle

Create composable AI agent systems in NestJS projects following the "tools all the way down" architecture. Use this skill when users want to: (1) Create new AI agents with orchestrator/planner/executor/evaluator components, (2) Build agentic systems that can call other agents as tools, (3) Implement DAG-based planning with parallel execution, (4) Add database-backed state persistence for agent runs, (5) Create custom evaluators for quality assurance. Triggers on "create agent", "build agent", "agent system", "agentic", "orchestrator", "planner/executor pattern", or NestJS AI agent requests.

mhylle Bundle

Tasktracker-native Socratic brainstorming. Refines a raw idea into a frozen brainstorm document tree stored in tasktracker (NOT in docs/brainstorms/*.md), with every chosen/deferred/rejected option recorded as a decision and an optional one-way promotion into a task tree. Use whenever a user wants to brainstorm, explore, refine, or "think through" an idea AND the work is (or will be) tracked in tasktracker. Triggers on "tt brainstorm", "brainstorm with tasktracker", "brainstorm in tasktracker", "explore this idea (tasktracker)", "/tt-brainstorm", or any brainstorm-style request inside a session that already has a tasktracker active task or project. Prefer this over the plain /brainstorm skill whenever a tasktracker MCP is available — the artifacts integrate with /tt-create-plan and /tt-implement-plan, so picking the file-based variant in a tasktracker project just creates orphan markdown.

spielewoy Skill

L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope + original prompt + potential flaws) is on record.

spielewoy Skill

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

nansen-ai Skill

Routing guide -- when to use `nansen agent` (AI research) vs direct CLI data commands. Use when deciding how to answer a user's research question with Nansen tools.

benjaming Skill

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

benjaming Skill

Audit and refactor CLAUDE.md, AGENTS.md, and .claude/rules/ files to follow progressive-disclosure principles. This skill should be used when the user wants to reorganize, clean up, or optimize their instruction files and rules by splitting monolithic files into a minimal root, domain-scoped rules with path globs, and linked reference docs. Triggers on requests like "refactor my CLAUDE.md", "clean up my rules", "audit my instructions", "organize my agent config", "optimize my rules files", or "migrate my CLAUDE.md to rules".

mhylle Bundle

Tasktracker-native implementation planning. Turns a frozen brainstorm (or a clear requirement) into a phased plan persisted as tasktracker phase tasks — NOT as a docs/plans/*.md file. Creates requirements with formal acceptance criteria, registers architecture components, generates phases via createPhaseFromTemplate (backend-feature / ui-fix / refactor / schema-migration / bug-investigation / docs-only / data-housekeeping), links every task back to its requirement, and uses getProjectReadiness as the completion gate. Use whenever the user wants to plan, design, or scope an implementation AND the work is (or will be) tracked in tasktracker. Triggers on "tt create plan", "tt plan", "plan this in tasktracker", "create a plan (tasktracker)", "/tt-create-plan", or any plan-creation request inside a session that already has a tasktracker active task or project. Prefer this over the plain /create-plan skill whenever a tasktracker MCP is available — the resulting phase tasks integrate with /tt-implement-plan and /imp

mhylle Bundle

Adversarial brainstorming using agent teams for multi-perspective analysis. Use when users want thorough idea exploration with real debate between independent perspectives. Triggers on "team brainstorm", "adversarial brainstorm", "brainstorm with team", "debate this idea", or when the user explicitly requests team-based analysis. Higher token cost but significantly deeper analysis than single-agent brainstorm.