INTERNAL sub-agent for blind 9-dim rubric scoring. NOT a user-facing skill — do NOT invoke from main conversation. Called via Task tool by cheat-score / cheat-predict / cheat-bump to get a context-isolated score on a script. Receives ONLY scriptpath + rubricnotespath; refuses any other input. Outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. Hard refuses to Read .cheat-state.json, predictions/, retro 段, or anything that could leak post-publish data. This is channel B in the 3-channel calibration model (A=main, B=blind sub, C=cross-model).
EnglishExpert document creation specialist who generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data…
EnglishExpert in Git workflows, branching strategies, and version control best practices including conventional commits, rebasing, worktrees, and CI-friendly branch management.
EnglishDeploy external AI agent/personality collections (like agency-agents, nature-skills, or custom role sets) into Hermes Agent as auto-triggering skills. Use when the user wants to install agent packs, role libraries, or personality collections from GitHub repos and make them activate automatically based on task content.
EnglishDiagnose MATLAB errors and unexpected behavior. Breakpoints, workspace inspection, try-catch diagnostics, and common error patterns. Use when debugging functions, tracing errors, inspecting variables, or diagnosing runtime failures.
EnglishDesign and validate digital filters in MATLAB. Use when cleaning up noisy signals, removing interference, filtering signals, designing FIR/IIR filters (lowpass/highpass/bandpass/bandstop/notch), or comparing filters in Filter Analyzer.
EnglishCreate MATLAB plain text Live Scripts (.m files) following specific formatting rules. Use when generating MATLAB scripts, educational MATLAB content, Live Scripts, or when the user requests .m files with rich text formatting.
EnglishModernize deprecated MATLAB functions and patterns. Use when checkmatlabcode or checkcode reports "not recommended" or "to be removed" warnings, when migrating legacy code, or when replacing deprecated APIs (trainNetwork, csvread, xlsread, datenum, eval, subplot, guide, optimset, wavread, svmtrain, uicontrol) with current equivalents.
EnglishRead BEFORE optimizing any MATLAB code for speed. Without this workflow, agents commonly optimize the wrong target, fabricate speedup claims without measurement, or introduce regressions. Guides the 7-step workflow: baseline, profile, identify, optimize, measure, verify, report.
EnglishReview MATLAB code for quality, performance, maintainability, and adherence to MathWorks coding standards. Uses checkmatlabcode and matlabcodingguidelines. Use when reviewing code, checking style, finding code smells, assessing quality, or preparing code for handoff or publication.
EnglishCreate comprehensive MATLAB unit tests using the MATLAB Testing Framework. Use when generating test files, test cases, unit tests, test suites, or when the user requests testing for MATLAB code, functions, or classes.
EnglishGenerate and run MATLAB unit tests using matlab.unittest and matlab.uitest. Parameterized tests, fixtures, mocking, coverage analysis, CI/CD with buildtool, app testing with gestures. Use when creating tests, writing test classes, running test suites, checking coverage, testing apps, or validating MATLAB code.
EnglishBeautifully render AI-generated markdown text in WeChat mini-programs — WXS parser, section cards, inline bold.
EnglishBuild standalone AI Agents with LLM direct-connect, tool calling, agentic loop, real-time status bar, permission system, and multi-provider support. Based on MUNDO Agent architecture (28 AI models, 6 tools, approval system).
EnglishExpert performance testing and optimization specialist focused on measuring, analyzing, and improving system performance across all applications and…
EnglishDesign pixel art characters from reference images and render them as HTML Canvas grids and terminal ASCII block art.
EnglishStops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production…
EnglishPremium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js…
EnglishExpert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prioritization frameworks.
EnglishExpert WeChat Mini Program developer specializing in 小程序 development with WXML/WXSS/WXS, WeChat API integration, payment systems, subscription messaging, and the full WeChat ecosystem.
EnglishWorkflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.
English同步 Hermes skills 到 CC Switch(macOS AI 模型选择工具)。 触发词:更新 cc switch、同步 skill 到 cc switch、cc switch 更新、 把 skill 更新到 cc switch、cc-switch。 自动检测需要更新的 skills,增量同步 SKILL.md 和…
Chinese提议并执行 rubric 或 bucket 升级。两种模式:完整 rubric bump(最高风险动作,5 步强制 + 跨模型审核)和 --bucket-only 轻量重校(只换 bucket 边界,不动 rubric 公式)。Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分——不接受 self-scored fallback。触发词:"升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate…
Chinese从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / scriptpatterns.md / rubricnotes.md。这是工具最早期信号的来源——cold-start 用户没自己历史时全靠对标,发过历史的用户也建议至少 1 个对标做 sanity check。触发词:"学这个账号"/"拆这几个对标视频"/"learn…
Chinese
AGENT SKILLS ATLASIncludes Cheat Score Blind, Document Generator, Git Workflow Master, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Cheat Score Blind
INTERNAL sub-agent for blind 9-dim rubric scoring. NOT a user-facing skill — do NOT invoke from main conversation. Called via Task tool by cheat-score / cheat-predict / cheat-bump to get a context-isolated score on a script. Receives ONLY scriptpath + rubricnotespath; refuses any other input. Outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. Hard refuses to Read .cheat-state.json, predictions/, retro 段, or anything that could leak post-publish data. This is channel B in the 3-channel calibration model (A=main, B=blind sub, C=cross-model).
Document Generator
Expert document creation specialist who generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data visual
Git Workflow Master
Expert in Git workflows, branching strategies, and version control best practices including conventional commits, rebasing, worktrees, and CI-friendly branch management.
Hermes Agent Collection Deployer
Deploy external AI agent/personality collections (like agency-agents, nature-skills, or custom role sets) into Hermes Agent as auto-triggering skills. Use when the user wants to install agent packs, role libraries, or personality collections from GitHub repos and make them activate automatically based on task content.
Matlab Debugging
Diagnose MATLAB errors and unexpected behavior. Breakpoints, workspace inspection, try-catch diagnostics, and common error patterns. Use when debugging functions, tracing errors, inspecting variables, or diagnosing runtime failures.
Matlab Design Digital Filter
Design and validate digital filters in MATLAB. Use when cleaning up noisy signals, removing interference, filtering signals, designing FIR/IIR filters (lowpass/highpass/bandpass/bandstop/notch), or comparing filters in Filter Analyzer.
Matlab Live Script
Create MATLAB plain text Live Scripts (.m files) following specific formatting rules. Use when generating MATLAB scripts, educational MATLAB content, Live Scripts, or when the user requests .m files with rich text formatting.
Matlab Modernize Code
Modernize deprecated MATLAB functions and patterns. Use when checkmatlabcode or checkcode reports "not recommended" or "to be removed" warnings, when migrating legacy code, or when replacing deprecated APIs (trainNetwork, csvread, xlsread, datenum, eval, subplot, guide, optimset, wavread, svmtrain, uicontrol) with current equivalents.
Matlab Optimize Performance
Read BEFORE optimizing any MATLAB code for speed. Without this workflow, agents commonly optimize the wrong target, fabricate speedup claims without measurement, or introduce regressions. Guides the 7-step workflow: baseline, profile, identify, optimize, measure, verify, report.
Matlab Review Code
Review MATLAB code for quality, performance, maintainability, and adherence to MathWorks coding standards. Uses checkmatlabcode and matlabcodingguidelines. Use when reviewing code, checking style, finding code smells, assessing quality, or preparing code for handoff or publication.
Matlab Test Generator
Create comprehensive MATLAB unit tests using the MATLAB Testing Framework. Use when generating test files, test cases, unit tests, test suites, or when the user requests testing for MATLAB code, functions, or classes.
Matlab Testing
Generate and run MATLAB unit tests using matlab.unittest and matlab.uitest. Parameterized tests, fixtures, mocking, coverage analysis, CI/CD with buildtool, app testing with gestures. Use when creating tests, writing test classes, running test suites, checking coverage, testing apps, or validating MATLAB code.
Miniprogram AI Display
Beautifully render AI-generated markdown text in WeChat mini-programs — WXS parser, section cards, inline bold.
Mundo Agent Builder
Build standalone AI Agents with LLM direct-connect, tool calling, agentic loop, real-time status bar, permission system, and multi-provider support. Based on MUNDO Agent architecture (28 AI models, 6 tools, approval system).
Performance Benchmarker
Expert performance testing and optimization specialist focused on measuring, analyzing, and improving system performance across all applications and infrastructure
Pixel Character Design
Design pixel art characters from reference images and render them as HTML Canvas grids and terminal ASCII block art.
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness
Senior Developer
Premium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js integration
Sprint Prioritizer
Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prioritization frameworks.
We Chat Mini Program Developer
Expert WeChat Mini Program developer specializing in 小程序 development with WXML/WXSS/WXS, WeChat API integration, payment systems, subscription messaging, and the full WeChat ecosystem.
Workflow Architect
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.
Cc Switch Sync
同步 Hermes skills 到 CC Switch(macOS AI 模型选择工具)。 触发词:更新 cc switch、同步 skill 到 cc switch、cc switch 更新、 把 skill 更新到 cc switch、cc-switch。 自动检测需要更新的 skills,增量同步 SKILL.md 和 references/。
Cheat Bump
提议并执行 rubric 或 bucket 升级。两种模式:完整 rubric bump(最高风险动作,5 步强制 + 跨模型审核)和 --bucket-only 轻量重校(只换 bucket 边界,不动 rubric 公式)。Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分——不接受 self-scored fallback。触发词:"升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。
Cheat Learn from
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / scriptpatterns.md / rubricnotes.md。这是工具最早期信号的来源——cold-start 用户没自己历史时全靠对标,发过历史的用户也建议至少 1 个对标做 sanity check。触发词:"学这个账号"/"拆这几个对标视频"/"learn from"/"导入对标账号"/"找对标"。
Showing 24 of 45 skills. Use the list’s page controls above to explore the rest.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Cheat Score Blind skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.