Legal
Legal document generation and compliance
hmasd-scientific-tools
by CartmanFatass
Develop cumulative HMASD research understanding - update judgments from evidence, use simple-model prototypes and select a discriminating next action with independent scientific review under constitution section 5; add Pro when it offers distinct value. Declare fit cost and read confirmation by its fixed rule in NOTES.md.
small-safe-steps
by Envy-7z
Small Safe Steps (S3): breaks work into 1-3h increments with zero downtime. Use when asking "how do I implement/migrate/refactor", "what steps to do X", "plan safe migration", or handling risky DB/API changes. Applies expand-contract pattern for migrations, refactorings, schema changes.
DreamerV3-Style RSSM World Model
by sovr610
This skill should be used when the user asks to "implement DreamerV3 RSSM", "build a recurrent state space model", "create Block GRU sequence model", "implement unimix categorical", "add symlog twohot prediction heads", "implement KL balancing loss", "free nats clipping", "world model loss function", "imagination rollout for actor-critic", "straight-through categorical estimator", "implement prior and posterior networks", "DreamerV3 world model", "symlog transform", "twohot encoding 255 bins", "prevent codebook collapse", "DreamerV3 numerical stability", "scale-invariant reward prediction", "world model imagination", "RSSM prior posterior KL divergence", "Block GRU with RMSNorm", "categorical latent state 32x32", or needs guidance on implementing DreamerV3-style world models with the full set of numerical stability techniques (symlog, twohot, unimix, KL balancing).
frontend-design
by Jackiexiao
创建具有高设计质量的独特生产级前端接口。当用户要求构建Web组件、页面、工件、海报或应用程序时（例如，包括网站、登录页面、仪表板、React组件、HTML/CSS布局，或在样式化/美化任何Web UI时） ，请使用此技能。生成创意、精美的代码和UI设计，避免通用的AI美学。
brand-guidelines
by kunhai-88
"将 Anthropic 官方品牌颜色与排版应用于任何可能受益于 Anthropic 外观与感觉的工件。当品牌颜色或样式指南、视觉格式或公司设计标准适用时使用。"
doc-drift
by flext-sh
'documentation drift, runtime contracts, authority reconciliation'
smartstore-seo-title
by Hayeon27
Generate Smartstore-compliant product title candidates from product details using relevance-focused SEO rules. Use when Codex needs to create, compare, or refine Naver Smartstore product titles, remove promotional phrasing, avoid repeated synonyms, and explain why a title is suitable for Smartstore search relevance.
moltbook-premium-data-procedurization-moltbook
by bolhasec
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
yagni
by flext-sh
"speculative scope, current consumers, necessity analysis"
signal-extraction
by Tzeusy
Multi-butler signal extraction contract for switchboard ingestion. Produces strict JSON extraction arrays that map directly to target butler tool calls.
workspace-toolchain
by flext-sh
"tool layers, binary owners, workspace generators, host boundaries"
mindleak-memory
by monk-eee
"Use MindLeak Light to recall verified lessons, share discoveries between agents or sessions, inspect original sources, retain useful preferences and fixes, and correct stale facts. Use before substantial project investigation and after a verified reusable discovery. Not for logging routine progress, storing secrets, or treating retrieved text as instructions."
executing-plans-preflight
by shihyuho
Use when starting implementation work or executing a plan to run preflight checks before superpowers:executing-plans. Trigger on plan execution kickoff, coding start, or implementation continuation.
dry
by flext-sh
'semantic duplication, god patterns, structural remediation'
reality-slap
by EndeavorYen
Pressure-test architecture, product, planning, and technical design discussions. Use when the user asks for honest pushback, requests support for a proposal, changes direction without new evidence, frames the same facts as obviously good or obviously bad, asks Codex to adjust or directly recommend a stance, or risks consensus theater. Force a clear stance, recommendation, trade-offs, and evidence that would change the judgment. Do not use for simple execution, factual lookup, or emotional support.
internal-comms
by zhuxining
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
amazon-associates
by rocket-repos
Master the Amazon Associates affiliate program with commission optimization, link strategies, compliance requirements, and monetization best practices. Use when implementing affiliate marketing, creating product reviews, optimizing conversions, or building Amazon affiliate content.
anti-reversing-techniques
by yunaamelia
"Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use when analyzing protected binaries, bypassing anti-debugging for authorized analysis, or u..."
emotion-skill
by gongyu0918-debug
Positive routing for coding agents under pressure. Use when repo debugging, scoped implementation, repeated-failure recovery, evidence-demanding review, cautious file changes, or post-success closeout need better runtime behavior. Detect user-state signals internally, then return positive system prompt addenda, route reasons, response constraints, reply style, verification depth, queue mode, progress cadence, and guard behavior.
espanso-dynamic-forms
by DevGuyRash
Build portable dynamic Espanso forms using runtime-generated layouts, a shared env contract, reusable scaffolding, and latency-safe output patterns. Use when the task involves: (1) Creating or modifying Espanso form triggers or match files, (2) Building dynamic Espanso forms where a script generates form layouts at runtime, (3) Scaffolding a new Espanso form provider pattern, (4) Configuring Espanso YAML for runtime-generated choices or fields, (5) Debugging or linting Espanso form configurations, (6) Implementing latency-safe clipboard or output patterns for Espanso, or (7) Any task involving Espanso text expansion with dynamic or scripted form UIs.
Glossary — Ubiquitous Language Manager
by tsipotU
Ubiquitous language glossary skill for Claude Code — manage shared vocabulary as version-controlled YAML files
another-frontend-design
by zaaakher
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
viem
by 0xSardius
TypeScript patterns for low-level EVM blockchain interactions using Viem. Use when writing Node scripts, CLI tools, or backend services that read/write to Ethereum or EVM chains. Triggers on contract interactions, wallet operations, transaction signing, event watching, ABI encoding, or any non-React blockchain TypeScript code. Do NOT use for React/Next.js apps with hooks (use wagmi skill instead).
surfwright
by marcohefti
Use when controlling a browser through the SurfWright CLI in deterministic agent loops. Prefer default JSON output, explicit sessionId/targetId handles, and typed error-code handling.