twitter-publisher
通过 bird CLI 发布和管理 Twitter/X 内容。使用此 skill 当用户需要：(1) 发布推文或帖子，(2) 回复推文，(3) 读取或获取推文内容，(4) 搜索推文，(5) 查看 mentions/bookmarks/likes，(6) 附带图片或视频发推。触发词包括：发推、tweet、发帖、回复推文、读取推文、Twitter、X 平台。
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.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
adr-writing
Write and maintain ADRs under docs/adrs when architecture decisions are made
github-actions-workflows
Create and maintain GitHub Actions workflows in .github/workflows
github-actions-troubleshooting
Troubleshoot and fix GitHub Actions workflow failures
agentic-trust
Deterministic workflow for searching services in Agentic Trust, inspecting trust evidence, loading the active questionnaire, comparing with local review memory, and optionally submitting a valid structured review with integer answers (0..10).
version-manager
SEMO 패키지 시맨틱 버저닝 자동화. Use when (1) Agent/Skill/Command 변경 후 릴리스, (2) VERSION 및 CHANGELOG 업데이트, (3) Keep a Changelog 형식 버전 관리.
package-validator
SEMO 패키지 구조 및 Sub-Agent 최적화 규칙 검증. Use when (1) Agent/Skill 추가/수정/삭제 후 검증, (2) CLAUDE.md 업데이트 후 일관성 확인, (3) 버저닝 전 품질 게이트, (4) Sub-Agent 최적화 규칙 준수 감사.
skill-creator
|
write-portfolio
|
process-feedback
|
deploy-npm
|
package-sync
SEMO 패키지 소스와 .claude/ 동기화 자동화. Use when (1) Agent/Skill/Command 변경 후 동기화, (2) 서브모듈 업데이트 후 심볼릭 링크 동기화, (3) 버저닝 완료 후 배포 준비.
supabase
|
check-feedback
SEMO 패키지 피드백 이슈 수집 및 리스트업. Use when (1) "피드백 확인", "피드백 있는지", (2) "유저 피드백 체크", (3) SEMO 관련 open 이슈 조회.
package-deploy
SEMO 패키지를 외부 프로젝트에 배포. Use when (1) 새 프로젝트에 SEMO 설치, (2) 기존 프로젝트 SEMO 업데이트, (3) 브라운필드 프로젝트 SEMO 도입.
meta-workflow
|
test-permission
|
changelog-writer
|
remote-bridge
|
test-selection
|
audit-semo
전체 SEMO 패키지 통합 품질 감사. Use when (1) 전체 패키지 품질 점검, (2) Agent/Skill/Command 표준 준수 검토, (3) 비효율적 구조 탐지, (4) 정기 감사 수행.
app-icon-generation
Generate iOS and watchOS app icons and image assets from SVG sources using Inkscape and sips
adr-writing
Write and maintain Architecture Decision Records (ADRs) when meaningful technical or architecture decisions are made. Use when introducing dependencies, changing APIs, adopting patterns, or making hard-to-reverse decisions.
planning
Creates structured implementation plans before code changes. Use when starting features, refactors, or multi-step tasks. Analyzes requirements, decomposes work into steps, identifies dependencies, surfaces risks, and saves plans to ./plans/ for review and tracking.
backstage-upgrade
Upgrade Backstage to the latest stable or specific version. Use when user says "upgrade backstage", "update backstage", "bump backstage", "backstage versions", or when the backstage.json version is behind the latest stable release.
agent-skills-authoring
Create and maintain Agent Skills following the agentskills.io specification for AI agents
agents-md-authoring
Create and maintain AGENTS.md files following the open specification at agents.md. Use when setting up AI coding agent instructions for a project, updating project conventions for agents, or documenting build/test/deploy workflows for automated coding assistants.
swift-ios-teaching
Teach Swift and iOS 26 development to experienced developers
keymaps
Add or modify keymaps in dots.factory following the mnemonic keymap model. Use when adding a new app launcher, aerospace workspace binding, vicinae shortcut, nvim keymap, herdr binding, or any cross-layer keyboard mapping.
den
Use when writing den aspects, debugging den framework issues, or working with the aspect-oriented Nix configuration in this repo
open-spec
Open a spec-authoring session over the project/ workspace. Use when the user says open-spec, $open-spec, or "open the spec" — it scopes the session to project/*, loads the spec contracts, and shifts into discussing desired outcomes before any spec is written.
create-gather-build-verify-prompts
Explicit workflow for creating or regenerating the gather-build-verify build-loop prompts under project/loops. Use only when the user explicitly invokes this skill or clearly asks to create or regenerate the gather/build/verify loop prompts.
seal-spec
Explicit workflow for sealing a settled goal into the project/ spec in one automated pass — the closing move of an open-spec session. Use only when the user explicitly invokes seal-spec, says $seal-spec or "seal the spec", or clearly asks to write the settled goal into project/product, project/research, project/design, and project/plan.
grill-me
Explicit workflow for interrogating a proposed goal or plan one question at a time until shared understanding — the middle move of an open-spec session, before seal-spec writes the result. Use when the user explicitly says grill-me, invokes $grill-me, or asks to be grilled before writing a project/ spec change.
ikispec
The project/ spec contracts: authoritative output shapes of product, research, design, and plan; authority boundaries; and hard invariants every writer keeps. Loaded by $open-spec, $grill-me, $seal-spec, and the loop-prompt generator workflows — not spoken by the user directly; use whenever any of those read or write the project/ spec.
ralph
Orientation map of the ralph autonomous-build family: interactive authoring, unattended execution, the ralph executor, and pointers to the project-local skills and generated prompts. Use for orientation around ralph, project/ specs, open-spec, seal-spec, build loops, and audit loops.
create-audit-prompts
Explicit workflow for creating or regenerating the single-prompt audit loop under project/loops. Use only when the user explicitly invokes this skill or clearly asks to create or regenerate the coverage audit prompt.
fact-check-x-authoritative-verify
对单个知识点调用可信搜索取得官方证据，由当前运行载体裁决各平台主张，并生成权威证据核验报告与平台表现报告。支持多知识点独立并发、深知晓可信搜索锚点免重复检索，以及直接准确、间接准确、结果巧合、严重误导、凭空编造等分类。可用于 Fact-Check-X 完整流程，也可作为独立的权威证据核验能力使用。
fact-check-x-knowledge-compare
在本地把多个 AI 原始回答拆成原子知识点，区分直接答案与补充参考，对齐各平台主张、差异、所附依据和来源忠实性，并生成可视化中间报告。不调用可信搜索或任何外部模型 API，语义分析由当前运行载体完成。
fact-check-x-complete
面向真实业务决策的多平台事实核验 Skill。正式支持深知晓、深知晓（深度研究）、豆包、腾讯元宝、DeepSeek 和通义千问，按用户输入动态选择 N≥1 个平台。完整采集原回答、引用、截图与页面存证，拆解并对比关键事实，再按需使用可信搜索取得权威证据，交付四份独立报告和可追溯结论。基础采集与对比无需 API Key；可信搜索是权威核验阶段的可选增强。语义工作由 Codex、Claude Code、WorkBuddy 等当前运行载体完成，不调用外部大模型 API。
fact-check-x-unified
Fact-Check-X 流程编排能力，依次组织多平台原始答案与引用采集、知识点结构化对比、权威证据核验和平台表现评估，生成可打开、可审计、可迁移的阶段产物与完整报告包。
llm-answer-reference-compare
用 Playwright 从深知晓、深知晓（深度研究）、豆包、腾讯元宝、DeepSeek 和通义千问网页端无损采集完整回答、原始引用、引用标记和现场存证。用于 Fact-Check-X 的原始答案采集阶段，或任何需要比较多个 AI 网页回答与参考来源的任务。
botsargue
Create and run a BotsArgue evidence arena for your human’s coding agent and another person’s separately controlled coding agent. Use when those two agents reached conflicting conclusions, have different context, checkouts, models, or runtime evidence, and need to compare reproducible evidence and ratify one exact settlement. Also use when the user supplies a BotsArgue arena link. Do not use for ordinary uncertainty, generic multi-agent orchestration, or to make one person’s agent role-play or occupy both sides.
anti-ui-slop
Stop UI slop before it ships. Use when building or reviewing React, Next.js, web, and iOS interfaces that need product-specific hierarchy, states, responsive decisions, and a hard finish gate grounded in UIZZE's 800,000+ real screens. Trigger with "stop UI slop", "review this UI", or "make this interface product-specific".
route-github-agent-decisions
Diagnose why a GitHub Actions run failed and find its root cause; decide whether to retry that failed Action once; check or rank GitHub bounties; audit AGENTS.md readiness; detect MCP schema drift.
route-github-agent-decisions
Diagnose why a GitHub Actions run failed and find its root cause; decide whether to retry that failed Action once; check or rank GitHub bounties; audit AGENTS.md readiness; detect MCP schema drift.
sparkbtcbot-proxy
Use a Spark Bitcoin L2 wallet proxy for AI agents via HTTP API. Check balances, send payments, create invoices, pay L402 paywalls — all without holding the mnemonic. Use when user mentions "Spark proxy," "wallet API," "L402," "proxy payment," "bearer token auth," or wants secured Bitcoin capabilities for an agent.
sparkbtcbot-proxy-deploy
Deploy a serverless Spark Bitcoin L2 proxy on Vercel with spending limits, auth, and Redis logging. Use when user wants to set up a new proxy, configure env vars, deploy to Vercel, or manage the proxy infrastructure.
Page 1553 of 1700 · 84984 results
