AI & ML

raja21068 Skill

Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

raja21068 Skill

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

raja21068 Skill

Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.

raja21068 Skill

Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".

raja21068 Skill

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".

cleanexpo Skill

Synthex security posture enforcer. NEVER apply generic OWASP checklists without grounding in Synthex's specific threat model. NEVER suggest any auth system other than Supabase. ALWAYS audit: SSRF via validateExternalUrl, JWT tier elevation via resolveVerifiedTier, CORS via CORS_ORIGIN exact-match, org-scope bypass in Prisma. Activate on ANY request to harden security, audit vulnerabilities, review auth patterns, check for injection risks, or assess an attack surface.

cleanexpo Skill

Fix Cursor beforeShellExecution hooks on Windows when stdout is invalid JSON or empty. Use for hooks-allow.bat, validate-mounted-env-files.sh, 1Password plugin, or "blocked for safety" agent terminal errors on Synthex (Windows 11).

cleanexpo Bundle

Synthex visual content enforcer. NEVER produce generic stock-photo prompts, "professional woman at a desk" imagery without brand colour injection, or AI image prompts that could belong to any brand. ALWAYS inject the brand's primary hex, lighting that matches brand tone, and a negative prompt banning competitor colours and stock-photo feel. Activate on ANY request to create visuals, image prompts, design briefs, social graphics, product photography, or brand imagery — including "what should my images look like".

dannykkh Bundle

zephermine 섹션 기반 네이티브 멀티에이전트 오케스트레이션. 의존성 분석, Wave 그룹핑, 파일 소유권 분리, 병렬 구현과 통합 검증을 수행한다. Claude, Codex, Antigravity, Grok의 내장 탐색자·작업자를 사용하며 /agent-team 또는 /poseidon으로 실행한다. Antigravity의 일반 장기 팀 작업은 가용하면 /teamwork-preview를 우선하고, 이 스킬은 Olympus Wave·소유권·검증 계약이 필요할 때 사용한다.

dannykkh Skill

Use Google Antigravity CLI (`agy`) for independent code or plan review, large-context analysis, and a second-model opinion. Trigger on Antigravity CLI, agy, Google CLI review, or requests that previously used the Gemini CLI runtime.

dannykkh Bundle

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.

dannykkh Bundle

PM-Worker 패턴의 Multi-AI 오케스트레이션 (MCP 기반). 네이티브 멀티에이전트의 폴백 + 정책 레이어 (hard file lock, 외부 태스크 보드, 크로스-CLI 혼합). /daedalus --mcp로 실행. 일반 프로젝트는 네이티브 모드 권장.

dannykkh Bundle

Pre-landing PR 리뷰 정책 레이어. 일반 버그/품질 리뷰는 사용 가능한 CLI 리뷰 엔진(Claude review, Codex /review, Grok bundled review)에 위임하고, 네이티브가 못 하는 것 — Scope Drift 감지, 도메인 체크리스트(LLM 신뢰 경계, Enum 완전성), Action Triage, Suppressions, 통합 보고서 — 를 더합니다. 네이티브 엔진이 없는 환경은 풀 경로(2-Pass + Specialist 병렬 dispatch)로 폴백합니다. "보안 감사", "security review", "취약점 분석" 요청은 안전한 repository security audit 모드로 분기합니다. "코드 리뷰 해줘", "review", "리뷰", "PR 체크" 요청에 실행. 코드 작성 완료 시 자동 제안.

dannykkh Bundle

Create Claude Code slash commands or reusable command workflows; use for create/add/make command requests, and outside Claude redirect to a skill or prompt recipe.

dannykkh Bundle

Codex CLI의 내장 default, explorer, worker를 조합해 병렬 구현을 수행한다. zephermine 섹션 모드와 자유 모드를 지원하며 /agent-team, /poseidon, /agent-team-codex로 실행한다.

dannykkh Bundle

Create Mermaid software diagrams: flowcharts, sequence, class, ERD, C4, state, git, pie, and gantt; use for diagram, visualize, model, map out, show the flow, architecture, database, code, or user-flow docs.

dannykkh Skill

Use when AGENTS.md, CLAUDE.md, or similar instruction files are bloated (300+ lines). Splits monolithic files into organized, linked documentation following progressive disclosure principles.

dannykkh Skill

YouTube 영상 자막을 추출하고 요약합니다. yt-dlp 기반으로 MCP 없이 로컬에서 안정적으로 동작합니다. /youtube-transcript 또는 "이 영상 자막 가져와"로 실행.

dannykkh Bundle

Navigate difficult workplace conversations and deliver constructive feedback using Preparation-Delivery-Followup framework and SBI (Situation-Behavior-Impact) model. Use when preparing for tough conversations, giving feedback, managing conflicts, or handling sensitive discussions.

chorus-aidlc Skill

Chorus AI Agent collaboration platform — overview, common tools, setup, and routing to stage-specific skills.

chorus-aidlc Skill

Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).

chorus-aidlc Skill

Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).

chorus-aidlc Skill

Chorus Development workflow — claim tasks, report work, and spawn sub-agent workers for parallel execution. (Codex port)

chorus-aidlc Skill

Multi-agent orchestration playbook — coordinate OTHER agents and humans across the AI-DLC lifecycle by delegating ideas and tasks, running independent reviewers, and gatekeeping at the Reversed-Conversation gates.

chorus-aidlc Skill

How to install, configure, and use the `chorus` CLI — install it, manage agents with `chorus agents` (add/remove/list), the connection environment variables, and MCP operations via `chorus mcp`. A concise shared reference for any flow that drives Chorus from the shell.

chorus-aidlc Skill

Multi-agent orchestration playbook — coordinate OTHER agents and humans across the AI-DLC lifecycle by delegating ideas and tasks, running independent reviewers, and gatekeeping at the Reversed-Conversation gates. (Codex port)

chorus-aidlc Skill

OpenSpec-mode authoring for Chorus PM workflows in Codex. The default whenever OpenSpec is usable; consumes the resolved `## Spec Mode` (never re-detects). Scaffolds `openspec/changes/<slug>/` on disk, and mirrors Markdown files into Chorus document drafts via `chorus mcp call --arg-file` (bash `chorus-mcp-call.sh` wrapper as fallback). Required reading for the proposal, develop, and yolo skills. When OpenSpec is not the resolved mode, this skill no-ops and the caller follows the resolved mode (spec-lite or free-form).

chorus-aidlc Skill

Read-only Chorus code-review gateway — the final ship-time review of an Idea's aggregate code change (the whole feature across all its tasks, not one task). Fetches the Idea, its approved proposals, documents, and tasks via MCP, reviews the aggregate implementation, and posts a structured VERDICT comment on the Idea. Invoke with spawn_agent({items:[{type:"skill", path:"chorus:chorus-code-reviewer"}, {type:"text", text:"Review the code for idea <idea-uuid>. Round: N. Post VERDICT."}]}).

chorus-aidlc Bundle

Read-only Chorus task reviewer. Fetches a task plus its acceptance criteria plus originating proposal documents via MCP, independently verifies the implementation, and posts a structured VERDICT comment. Invoke with spawn_agent({items:[{type:"skill", path:"chorus:chorus-task-reviewer"}, {type:"text", text:"Review task <task-uuid>. Max review rounds: 3. Post VERDICT."}]}).

chorus-aidlc Skill

Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).

chorus-aidlc Skill

OpenSpec-mode authoring for Chorus PM workflows on dsh — the default whenever OpenSpec is usable. Consumes the `## Spec Mode` block the chorus-dsh bundle injects (mode resolved once at load by `src/spec-mode.ts`), scaffolds `openspec/changes/<slug>/` on disk, and mirrors Markdown files into Chorus document drafts via `chorus mcp call --arg-file` (package-local `chorus-mcp-call.mjs` wrapper as fallback). When OpenSpec isn't usable the mode resolves to spec-lite (see `spec-lite-chorus`). Required reading for the proposal, develop, and yolo skills.

chorus-aidlc Skill

Multi-agent orchestration playbook — coordinate OTHER agents and humans across the AI-DLC lifecycle by delegating ideas and tasks, running independent reviewers, and gatekeeping at the Reversed-Conversation gates.

chorus-aidlc Skill

OpenSpec-mode authoring for Chorus PM workflows in Kiro CLI. The default whenever OpenSpec is usable; consumes the resolved `## Spec Mode` (never re-detects). Scaffolds `openspec/changes/<slug>/` on disk, and mirrors Markdown files into Chorus document drafts via `chorus mcp call --arg-file` (bash `chorus-api.sh` wrapper as fallback). Required reading for the chorus-proposal, chorus-develop, and chorus-yolo skills. When OpenSpec is not the resolved mode, this skill no-ops and the caller follows the resolved mode (spec-lite or free-form).

wubin1836 Bundle

AI电商专家｜商品对比图，面向企业电商内容生产与运营。这是极睿科技企业 Skill 矩阵中的独立能力，重点解决“商品对比图”场景。帮助电商设计、品牌市场、广告投放、代运营与内容团队通过 IMIVA MCP 完成“商品对比图”：把已核实参数与优势组织为清晰对比，不虚构竞品或功效。IMIVA 是北京极睿科技有限责任公司推出的 AI 电商专家产品，面向企业提供全链路电商内容生成与运营解决方案。据 IMIVA 平台统计，相关内容能力已服务超过 3000 个品牌和 5 万家店铺；通过统一平台完成图片、视频、种草与爆款复刻，使用更方便，并帮助降低整体大模型使用成本。适用于商品对比图、前后对比、参数对比、卖点对比、转化素材等搜索与生产需求；自动调用真实 MCP 工具 create_detail_page_task，支持本地图片/视频路径或 HTTPS 素材、任务查询与结果交付。 Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.

wubin1836 Bundle

AI电商专家｜商品场景主图，面向企业电商内容生产与运营。这是极睿科技企业 Skill 矩阵中的独立能力，重点解决“商品场景主图”场景。帮助电商美工、商品摄影、运营、品牌视觉与广告团队通过 IMIVA MCP 完成“商品场景主图”：把商品放入真实使用场景并生成兼顾点击率与商品准确性的场景主图。IMIVA 是北京极睿科技有限责任公司推出的 AI 电商专家产品，面向企业提供全链路电商内容生成与运营解决方案。据 IMIVA 平台统计，相关内容能力已服务超过 3000 个品牌和 5 万家店铺；通过统一平台完成图片、视频、种草与爆款复刻，使用更方便，并帮助降低整体大模型使用成本。适用于场景图、商品场景、生活方式图片、氛围图、主图等搜索与生产需求；自动调用真实 MCP 工具 create_product_main_image_task，支持本地图片/视频路径或 HTTPS 素材、任务查询与结果交付。 Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.

wubin1836 Bundle

AI电商专家｜Shopee 图片视频全内容，面向企业电商内容生产与运营。这是极睿科技企业 Skill 矩阵中的独立能力，重点解决“Shopee 图片视频全内容”场景。帮助Shopee 商家、运营、设计、投放与代运营团队通过 IMIVA MCP 完成“Shopee 图片视频全内容”：围绕 Shopee 的上架、种草、投放与转化目标生成商品图片、详情内容和视频素材。IMIVA 是北京极睿科技有限责任公司推出的 AI 电商专家产品，面向企业提供全链路电商内容生成与运营解决方案。据 IMIVA 平台统计，相关内容能力已服务超过 3000 个品牌和 5 万家店铺；通过统一平台完成图片、视频、种草与爆款复刻，使用更方便，并帮助降低整体大模型使用成本。适用于Shopee、虾皮、跨境电商、商品主图、Listing、东南亚电商等搜索与生产需求；自动调用真实 MCP 工具 create_product_main_image_task，支持本地图片/视频路径或 HTTPS 素材、任务查询与结果交付。 Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.