baku-mind-cleaner
2617Skill Claude CodeCodex
A Chinese-language guide for sorting a crowded set of tasks, concerns, or ideas into clear priorities and next actions.
35,518 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
A Chinese-language guide for sorting a crowded set of tasks, concerns, or ideas into clear priorities and next actions.
Skill Claude CodeCodex
Emulates Claude Fable 5's coding discipline on any model (Opus 4.8, Sonnet 5, etc.) — spec-first planning, a self-verification harness, parallel sub-agent delegation, file-based memory, evidence-grounded progress reports, and minimal-change engineering. Supports intensity levels lite, full (default), and ultra, plus a…
Skill Claude CodeCodex
Structured planning pipeline with 4 adaptive phases (Specify, Design, Tasks, Execute) and persistent knowledge accumulation for development teams. Auto-sizes depth by complexity from quick fixes to multi-component features. Commands: /explore (understand problem + map context), /plan (write spec → design → tasks)…
Plugin Claude Code
Bundles 3 commands, 15 agents · 898 tokens together
PRD Implementor, PR Review, PDQC — commands and subagents.
gyujeongion/claude-code-sparring
Skill Claude Code
A structured debate between two AI models: one argues for a position and the other challenges it for up to six rounds. A moderator summarizes where they agree or disagree.
Plugin Claude Code
Bundles 1 skill · 218 tokens together
Spec-driven development orchestrator. Turns vague feature requests into production-grade specs before code is written.
Command Claude Code
You're helping the user create a Product Requirements Document — the most important document before building. This defines WHAT to build, WHO it's for, and WHY it matters.
Plugin Claude Code
Bundles 1 skill · 198 tokens together
Validate whether a demand is real before you build it. Frame a falsifiable hypothesis, fan out parallel agents across two pillars (top-down: industry reports / market size / capital signals; bottom-up: Hacker News / App Store reviews / search & social), enforce a 7-axis demand scorecard with ≥2-source triangulation…
Plugin Claude Code
Bundles 12 skills, 1 command, 3 agents, 5 hooks · 1,374 tokens together
Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and spec/supervise/wrap/verify-completion skills. Install once, use in every project. AI-agnostic core (Claude Code / Codex / Gemini).
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Minimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use…
Skill Claude CodeCodex
An AI assistant workflow for choosing university applications in China's Gaokao system, the national college entrance examination. It compares scores and rankings with school and major choices while accounting for regional admission rules.
Skill Claude CodeCodex
Adversarial specification writer. Takes a brief (from grill-me or user) and produces a structured spec.md with YAML frontmatter, requirements, acceptance criteria, and target files. Git-aware pipeline: each run on its own branch, squash-merge on approval.
Skill Claude CodeCodex
Lead free-form implementation work through bounded delegation: define the exact outcome, launch the smallest useful executor team, integrate the result, and prove completion. Use when the user asks Work to build, fix, implement, refactor, or change something without selecting a focused Work skill.
Skill Claude CodeCodex
Reveal consequential blind spots after answering. Use proactively for exploration, research, product thinking, architecture, planning, creative work, and decisions, or when the user asks what they missed, what to ask next, or to challenge an idea. Skip routine execution unless a hidden issue could materially change…
jneaimi/blooms-ai-collaboration
Skill Claude CodeCodex
Structured thinking skill implementing Bloom's AI Collaboration Framework v3. Auto-scales depth from stakes (reversibility + reliance): quick 3-question framing for reversible exploration, standard 6-question protocol for real decisions, deep mode with epistemics + teach-back + independent audit for binding one-way…
Skill Claude CodeCodex
Activates ground-truth mode -- a critical thinking partner with hard anti-sycophancy rules. Use whenever someone shares a plan, idea, decision, interpretation, or work product and might be seeking reassurance instead of honest assessment. Trigger on any of: "what do you think," "does this make sense," "is this a good…
manojsurapaneni/manufacturing-ops-skills
Skill Claude CodeCodex
Generates a Toyota-style A3 problem-solving report from a problem statement. Use this skill when the user mentions A3 reports, root cause analysis, 5-Whys, fishbone diagrams, Ishikawa, lean problem solving, DMAIC, manufacturing issues, quality escapes, production downtime, scrap reduction, yield problems, or asks to…
Skill Claude CodeCodex
Check whether the user's request has enough information to do the task well before producing output, instead of silently inventing missing details or asking generic clarifying questions. Use this whenever a task is underspecified in ways that would change the actual output — building a website, writing a contract…
batterfried-philosophy172/Agent-Startup-Skills
Skill Claude CodeCodex
Master orchestrator skill that coordinates a full multi-agent startup pipeline. Triggers on: build SaaS, launch startup, startup accelerator, build product, create MVP, SaaS builder, million dollar startup, build me a business, or using the Startup Factory. Coordinates 8 specialized sub-skills in a gated…
Plugin Claude Code
Bundles 2 skills · 333 tokens together
A plugin containing two workflows: one drafts a visual specification from an unclear request, and the other checks code against that specification.
Skill Claude CodeCodex
Cross-domain bridge thinking for stuck founders, creators, and builders. Finds pattern bridges from unrelated fields — biology, game design, physics, jazz, architecture, logistics — and maps them to your situation with explicit reasoning, pros/cons, and a first experiment. Use when stuck, plateaued, can't get…
LionHuang/triumvirate-strategy
Skill Claude CodeCodex
Multi-perspective business strategy debate using three AI advisors (Creative Strategist, Market Skeptic, Financial Realist). Use this skill when the user asks for business strategy analysis, wants to evaluate a business plan, needs to stress-test a business idea, asks for multi-angle feedback on a proposal, mentions…
Skill Claude CodeCodex needs its repo
Triggers when: user mentions "PRD", "requirements", "break down requirements", "split PRD", or provides a long feature document. Use this skill to first clarify ambiguous requirements, confirm business logic and boundaries, and then decompose the finalized PRD into atomic frontend tasks focusing purely on BUSINESS…
pamiray-m/product-completion-wrap
Skill Claude Code
Apply a vendor-neutral post-build completion standard to an existing product repository. Use when explicitly asked to finish, harden, package, validate, prepare, or launch a substantially completed product. Covers functional closure, engineering, security, branding, legal drafts, UI, website, SEO, payments, email…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: