Software Development AI agent skills

13,359 skills in the archive. Read a skill’s instructions or open its original repository.

• Checkpoint Management

  by @a5c-ai

  Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

• Cog Onboarding

  by @a5c-ai

  Personalize COG Second Brain workflow through role pack selection and vault initialization

• Cog Daily Intelligence

  by @a5c-ai

  Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy

• Cog Knowledge Consolidation

  by @a5c-ai

  Build structured knowledge frameworks from scattered vault notes with source attribution

• Cog Weekly Reflection

  by @a5c-ai

  Cross-domain pattern analysis with personal, professional, and project domain synthesis

• Cog Url Extraction

  by @a5c-ai

  Save URLs with auto-extracted insights, credibility scoring, and vault routing

• Cog Braindump Capture

  by @a5c-ai

  Capture raw thoughts with automatic domain classification and vault routing

• Modal Gpu

  by @benchflow-ai

  Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.

• Civ6lib

  by @benchflow-ai

  Civilization 6 district mechanics library. Use when working with district placement validation, adjacency bonus calculations, or understanding Civ6 game rules.

• Mesh Analysis

  by @benchflow-ai

  Analyzes 3D mesh files (STL) to calculate geometric properties (volume, components) and extract attribute data. Use this skill to process noisy 3D scan data and filter debris.

• Hex Grid Spatial

  by @benchflow-ai

  Hex grid spatial utilities for offset coordinate systems. Use when working with hexagonal grids, calculating distances, finding neighbors, or spatial queries on hex maps.

• Triangulated Fx Rates

  by @benchflow-ai

  Reference for multi-hop / triangulated currency conversion on batch rate tapes. When a rate row carries an explicit "via" currency, the row's rate is only one leg of the conversion, and the via currency may ITSELF be quoted…

• Speaker Clustering Methods

  by @benchflow-ai

  Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative…

• Geospatial Routing Data

  by @benchflow-ai

  Geospatial routing data handling for depot and station coordinates, route node IDs, internal index mappings, great-circle distance matrices, and route-distance reconstruction. Use when optimization or reporting tasks involve…

• Ebcdic Overpunch Decoding

  by @benchflow-ai

  Reference for the EBCDIC "overpunch" / zoned-decimal sign convention where the units position of a numeric field is replaced with a letter that encodes both a digit and a sign. Useful when reading mainframe-style fixed-length…

• Comp3 Packed Decimal

  by @benchflow-ai

  Reference for COBOL COMP-3 (packed decimal / BCD) numeric storage -- layout on disk, declaring it in the FD, and pitfalls when carrying the decoded value through working storage and into later arithmetic. Useful when an input…

• Routing Subtour Elimination

  by @benchflow-ai

  Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles and the model needs MTZ constraints, flow-based…

• Gh Cli

  by @benchflow-ai

  The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. When needs to interact with GitHub repositories, issues, pull requests, and more, use this skill.

• Pid Controller

  by @benchflow-ai

  Use this skill when implementing PID control loops for adaptive cruise control, vehicle speed regulation, throttle/brake management, or any feedback control system requiring proportional-integral-derivative control.

• Vehicle Dynamics

  by @benchflow-ai

  Use this skill when simulating vehicle motion, calculating safe following distances, time-to-collision, speed/position updates, or implementing vehicle state machines for cruise control modes.

• Gl Posting Codes

  by @benchflow-ai

  Background on general-ledger batch posting codes (HD/DR/CR/RV plus signed "other" rows). Reference only -- follow the task instruction for the exact rules, which may differ per account type.

• Simulation Metrics

  by @benchflow-ai

  Use this skill when calculating control system performance metrics such as rise time, overshoot percentage, steady-state error, or settling time for evaluating simulation results.

• Audiobook

  by @benchflow-ai

  Create audiobooks from web content or text files. Handles content fetching, text processing, and TTS conversion with automatic fallback between ElevenLabs, OpenAI TTS, and gTTS.

• Map Optimization Strategy

  by @benchflow-ai

  Strategy for solving constraint optimization problems on spatial maps. Use when you need to place items on a grid/map to maximize some objective while satisfying constraints.

• Sqlite Map Parser

  by @benchflow-ai

  Parse SQLite databases into structured JSON data. Use when exploring unknown database schemas, understanding table relationships, and extracting map data as JSON.

• Yaml Config

  by @benchflow-ai

  Use this skill when reading or writing YAML configuration files, loading vehicle parameters, or handling config file parsing with proper error handling.

• Gemini Count In Video

  by @benchflow-ai

  Analyze and count objects in videos using Google Gemini API (object counting, pedestrian detection, vehicle tracking, and surveillance video analysis).

• Gnucobol Mainframe Batch

  by @benchflow-ai

  GnuCOBOL toolchain pointers for mainframe-style batch programs (LINE/RECORD SEQUENTIAL files, PIC clauses, cobc build flags).

• Video Frame Extraction

  by @benchflow-ai

  Extract frames from video files and save them as images using OpenCV

• Verify

  by @ai4s-research

  Verify apps/desktop frontend changes visually without launching the Tauri app or a live model

• Ctf Pwn

  by @wgpsec

  CTF 二进制漏洞利用(Pwn)技术。当挑战提供 ELF/PE 可执行文件并开放 nc 端口、存在栈溢出/堆溢出/格式化字符串/UAF 漏洞时使用。覆盖 ROP 链构造、堆利用(tcache/House of Orange/Spirit)、内核利用、seccomp 沙箱逃逸、pwntools 自动化利用脚本编写

• Ctf Web Methodology

  by @wgpsec

  CTF Web 挑战的总体方法论。当面对 CTF 靶场、xbow benchmark、Web 安全挑战赛时使用。包含挑战类型快速识别、攻击策略选择决策树、常见出题模式、何时切换方向的判断标准。与 exploit/ 下的具体漏洞技能配合使用

• Ctf Reverse

  by @wgpsec

  CTF 逆向工程技术。当挑战提供未知二进制文件需要分析算法逻辑、游戏客户端需要破解验证、混淆代码需要还原、自定义 VM 需要解释执行时使用。覆盖 Ghidra/IDA 静态分析、GDB/Frida 动态调试、反调试绕过、WASM/.NET/APK/Python 字节码/Go/Rust 多平台逆向

• C2 Evasion Methodology

  by @wgpsec

  C2框架免杀方法论：分析 C2 源码、搜索检测规则(YARA/Sigma/Snort)、逐规则分析、修改源码绕过检测。当遇到 YARA/Sigma/Snort 规则触发告警、beacon/implant 被杀软检测到时使用。第一步：确认 implant/beacon 语言和架构；第二步：搜索对应检测规则并逐规则分析修改

• Shellcode Loader Generate

  by @wgpsec

  Shellcode Loader 组合生成：从知识库选择 storage/allocator/copier/executor 四类组件组合生成 C/C++/Rust Loader。当已获 shellcode、需要生成可在目标环境运行的 Loader 二进制时使用。先读 references/loader-scenarios.json 确认不存在重复场景，再选择 4 组件组合生成

• Binary Exploitation Methodology

  by @wgpsec

  二进制漏洞利用基础方法论。涵盖漏洞识别（栈溢出/堆溢出/格式化字符串/UAF）、保护机制分析（ASLR/NX/Stack Canary/PIE/RELRO）、利用策略选择（ret2win/ret2shellcode/ROP/ret2libc）、调试与利用开发流程。当 Agent 需要分析二进制程序漏洞、选择利用策略、或理解保护机制绕过方法时触发。区别于 CTF pwn 技巧，侧重实战方法论。

• Evasion Technique Integrate

  by @wgpsec

  免杀技术整合：将免杀技术（API 混淆、字符串加密、Syscall、反调试、AMSI 绕过等）植入已有 Loader 代码。当需要向已有 Loader 添加新加载技术、或现有 Loader 被检测到需要替换组件时使用。先读 references/evasion-techniques-db.json 确认组件库中有你需要的技术，再执行集成

• Jwt Attack Methodology

  by @wgpsec

  JWT Token 攻击方法论。当响应头/Cookie 中出现 eyJ 开头的字符串（三段式 base64，Header.Payload.Signature）、Authorization: Bearer token、API 返回 token/access_token 字段时使用。包含 alg:none 绕过、弱密钥爆破（hashcat/john/c-jwt-cracker/jwt_tool 完整工具链）、Claims 篡改提权、RS256->HS256…

• 401 403 Bypass

  by @wgpsec

  401/403 访问拒绝绕过与 Spring MVC .do 鉴权绕过方法论。当遇到管理后台、API 端点返回 401/403 Forbidden、Spring MVC .do 接口鉴权绕过、302 登录跳转（login_tologin.do）、越权注册（registersysuser、goedituser）等场景时使用。覆盖路径操纵、HTTP 方法篡改、Header 注入、协议降级、.do 后缀鉴权绕过、302 跳转绕过、组合攻击

• Crypto Web Attack

  by @wgpsec

  Web 应用中的密码学攻击。当发现 Padding Oracle 错误信息、CBC 模式加密的 Token、可预测的随机数/Token、哈希长度扩展攻击机会时使用。覆盖 Padding Oracle（含 PadBuster 完整用法）、CBC bit-flip、弱随机数、哈希长度扩展、ECB 块重排。注意：JWT 攻击请使用 jwt-attack-methodology，Cookie 分析请使用 cookie-analysis

• Ctf Source Audit

  by @wgpsec

  CTF 挑战中的源码审计方法。当发现 .git 目录、.bak/.zip 备份、/proc/self/environ 泄露源码时使用。与真实代码审计不同——CTF 源码中的漏洞是故意设置的，通常只有 1-2 个关键点。先找危险函数（sink），再追溯输入（source）到该函数的路径。覆盖 PHP/Python/Node.js/Java 四种语言的危险函数和漏洞模式

• Evasion Research

  by @wgpsec

  GitHub 安全研究方法论：搜索 GitHub 上的免杀/Loader/C2 技术仓库，分析代码模式，提取新技术入库。当知识库中没有针对当前检测环境的免杀技术时使用——先搜索 GitHub 高星仓库，分析代码后写入 evasion-techniques-db.json 或 loader-components-db.json 入库

• Race Condition Exploit

  by @wgpsec

  竞态条件漏洞利用方法论。当目标有余额/积分操作、优惠券兑换、限量库存、频率限制、多步骤工作流（注册/密码重置/MFA）时使用。核心技术：HTTP/2 单包攻击（Single-Packet Attack）、Turbo Intruder、Last-Byte Sync

• Http Smuggling Advanced

  by @wgpsec

  HTTP 请求走私高级利用方法论。扩展 cache-poisoning-smuggling 的走私部分。当已确认存在 CL.TE/TE.CL/TE.TE/H2.CL 走私时使用。覆盖链式利用（窃取凭据、绕过 ACL、投毒 Web 缓存、XSS 其他用户）和 HTTP/2 降级走私

• Ot Ics Attack

  by @wgpsec

  OT/ICS 工控系统攻击方法论。当目标涉及 SCADA/DCS/PLC 系统、发现 Modbus/DNP3/OPC UA/EtherNet-IP 等工控协议、或需要评估关键基础设施安全时使用。覆盖工控协议利用、PLC 攻击、HMI 渗透、IT/OT 边界突破

• Supply Chain Attack

  by @wgpsec

  软件供应链攻击方法论。当目标使用 npm/PyPI/Maven 等包管理器、有私有仓库、使用 CI/CD Pipeline 时使用。覆盖 Dependency Confusion、Typosquatting、恶意包发布、CI/CD 投毒、构建服务器攻击

• Ctf Web Recon

  by @wgpsec

  CTF Web 挑战专用侦察方法。当面对 CTF 靶场目标需要快速发现攻击入口时使用。与真实渗透的 recon 不同——CTF 是单个应用、有意留线索、侦察应在 2-3 轮内完成。覆盖源码泄露、备份文件、隐藏路径、页面线索提取

• Disk Forensics Evasion

  by @wgpsec

  磁盘取证与反磁盘取证方法论。理解蓝队如何从磁盘恢复删除文件、提取时间线、分析文件系统 artifact，以及红队如何进行反取证（安全删除、时间戳篡改、痕迹清除）。当需要规避磁盘取证或进行磁盘分析时使用

• Binary Exploitation Tools

  by @wgpsec

  二进制漏洞利用工具集参考。涵盖调试工具（GDB/GEF/pwndbg/r2）、利用开发框架（pwntools/ROPgadget/one_gadget）、反编译工具（Ghidra/IDA/Binary Ninja）、动态分析工具（ltrace/strace/valgrind）。当 Agent 需要选择合适的二进制分析工具、了解工具使用方法、或搭建利用开发环境时触发。

• Emergency Response

  by @wgpsec

  应急响应方法论。当目标主机疑似被入侵、需要排查后门/木马/异常进程/异常账户、或需要进行安全事件溯源分析时使用。覆盖 Linux 和 Windows 双平台的账户审计、进程排查、网络连接分析、启动项/计划任务检查、日志分析、Rootkit 检测

• Ci Pipeline Synthesizer

  by @kajisho5

  Generate GitHub Actions CI/CD pipeline configurations for automated building and testing of library and package projects. Use when creating or updating CI workflows for npm packages, Python packages, Go modules, Rust crates, or…

• Reviewing Ffmpeg Skill Changes

  by @kajisho5

  Review a change to the ffmpeg-skill repository for the failures its own contract makes possible — a claim in a result document that is true at one layer and false at the layer a caller reads, a new flag that reaches the code but…

• Shipping Across Surfaces

  by @kajisho5

  Land a change everywhere the same fact is stated — enumerating the full surface inventory (landing copy, docs, machine-readable summaries, changelog badges repeated across every page, sitemap, README, descriptions embedded in…

• Concurrent Branches

  by @kajisho5

  Resolve conflicts and merges when several branches are open against one repo at the same time — the hotspot files every change must touch (registry manifests, a single version field, shared tool config, one aggregated test…

• Writing Defect Reports

  by @kajisho5

  Establish a finding before you publish it, and correct it after — headlines that overstate what actually reproduces at the layer a user sees, reporting code that no entry point can reach or that is already dead, filing a caveat…

• Verifying External Behavior

  by @kajisho5

  Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments…

• Guarding Destructive Operations

  by @kajisho5

  Add and review preconditions on operations that delete, overwrite, rewrite history, or resolve a caller-supplied name to a filesystem path — refusing instead of warning, placing the guard ahead of the first mutation, structural…

• Reproducing Ci Locally

  by @kajisho5

  Run the CI gate on your machine so it agrees with the runner — deriving the exact command, paths, markers, and env from the workflow file instead of the Makefile, unblocking gate steps that short-circuit and hide the next…

• Shipping Build Artifacts

  by @kajisho5

  Make the build step a real gate on what you actually distribute — build scripts that warn and exit 0 on a missing input, size checks with only an upper bound, hand-maintained file lists that drift from the entrypoints they must…

• Running Github Actions Efficiently

  by @kajisho5

  Cut GitHub Actions minutes and wall-clock time without losing coverage — the OS billing multiplier (macOS 10x / Windows 2x / Linux 1x), trigger hygiene that stops push+pull_request double-firing, concurrency that cancels…

• Keeping Git Repos Clean

  by @kajisho5

  Prevents, detects, and remediates files that should never be committed — secrets (.env, API tokens, hardcoded credentials) and dev artifacts (build output, scratch databases, editor/OS files). Covers .gitignore (and why it does…

• Building Python Mcp Servers

  by @kajisho5

  Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and…

• Managing Python Releases

  by @kajisho5

  Manages Python library releases including semantic versioning, changelog maintenance (Keep a Changelog format), release automation with GitHub Actions, and deprecation workflows. Use when planning releases, writing changelogs,…

• Agent Device

  by @gronxb

  Automates interactions for iOS simulators/devices and Android emulators/devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, or extracting UI info on mobile targets.

• E2e

  by @gronxb

  Agentic end-to-end tests with e2e, the e2e runner. Covers scaffolding e2e.config.ts, picking the Playwright browser engine or the agent-device mobile engine, starting the app under test from the config, driving flows with…

• Unity Pico Design

  by @Besty0728

  Doc-anchored design rules for PICO Unity Integration SDK v3.4.0 — XR/MR/platform services, version diffs 2.x-3.4, hallucination shields

• Unity Netcode Design

  by @Besty0728

  Source-anchored design rules for Netcode for GameObjects 2.x

• Unity Dotween Design

  by @Besty0728

  Source-anchored design rules for DOTween 1.3.015

• Unity Material

  by @Besty0728

  Edit material and shader properties across Built-in/URP/HDRP

• Unity Profiler

  by @Besty0728

  Capture read-only Unity runtime performance snapshots

• Unity Sample

  by @Besty0728

  Sample and demo skills for API connectivity testing

• Unity Architecture

  by @Besty0728

  Advise on Unity gameplay and system architecture

• Unity Debug

  by @Besty0728

  Inspect debug, diagnostics and compile state

• Unity Package

  by @Besty0728

  Manage Unity Package Manager (UPM) packages

• Unity Console

  by @Besty0728

  Capture and query the Unity Editor console

• Unity Batch

  by @Besty0728

  Unified batch and async-job orchestration

• Unity Hybridclr

  by @Besty0728

  Automate HybridCLR C# hot-update prebuild

• Unity Patterns

  by @Besty0728

  Advise on choosing Unity design patterns

• Unity Inspector

  by @Besty0728

  Advise on Unity Inspector authoring UX

• Unity Asset

  by @Besty0728

  Manage Unity AssetDatabase operations

• Unity Performance

  by @Besty0728

  Advise on Unity performance red flags

• Unity Cleaner

  by @Besty0728

  Clean up and audit a Unity project

• Interactive Dashboard

  by @ginlix-ai

  Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors, served via preview URL

• Pdf

  by @ginlix-ai

  Read, fill and build PDFs: inspect structure and fonts, extract text and tables with pdfplumber and poppler, fill and flatten AcroForms with pypdf, create with reportlab, merge, split and encrypt with qpdf, and verify by…

• Dcf Model

  by @ginlix-ai

  Build a DCF valuation in Excel: FCF projections, WACC, terminal value, scenarios, sensitivity grids, reverse DCF. Triggers on build a DCF, what is it worth, intrinsic value, fair value, price target from cash flows.

• Sector Overview

  by @ginlix-ai

  Sector and industry landscape report, built on the sector's own archetypes, metrics and valuation lenses. Triggers on sector overview, industry landscape, industry primer, sector deep dive, market map.

• X Api

  by @ginlix-ai

  Search X (Twitter) posts, pull user profiles, fetch specific tweets, and read reply threads for sentiment, news, and event research. Triggers on 'X', 'Twitter', 'tweets about', 'sentiment on', 'what are people saying about',…

• Web Scraping

  by @ginlix-ai

  Web scraping: scrape_page / scrape_pages MCP tools for fetching pages as markdown, HTML, or text (fast HTTP, browser rendering, anti-bot stealth), plus the direct Scrapling Python API for selectors, sessions, and spiders

• User Profile

  by @ginlix-ai

  Manage user profile including watchlists, portfolio, and preferences.

• Run Workflow

  by @ginlix-ai

  Orchestrate parallel subagent pipelines from a JavaScript workflow script. Fan out work across many items (tickers, filings, findings) then synthesize, or run a saved workflow by name. Unlocks the RunWorkflow tool.

• Html Report

  by @ginlix-ai

  Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS

• Self Improve

  by @ginlix-ai

  Report issues and propose fixes to improve your own capabilities when you encounter errors or limitations

• Onboarding

  by @ginlix-ai

  First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.

• Mex Relay

  by @mex-memory

  Prepare and manage durable MEX team handoffs in git-native project memory. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create a MEX Relay, take…

• Mex Inbox

  by @mex-memory

  Draft and review contributions to existing MEX project knowledge in the repo wiki. Use when the user wants to capture a team decision, convention, or architecture note, propose an addition or correction for team review, or…

• Mex Relay

  by @mex-memory

  Prepare and manage durable MEX team handoffs. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create a MEX Relay, take or close a Relay, or…

• Mex Inbox

  by @mex-memory

  Draft and review contributions to existing MEX project knowledge. Use when the user asks to capture a discussion or decision in project knowledge, propose an addition or correction for team review, or explicitly invokes…

• Test Skill

  by @NeoLabHQ

  Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to…

• Write Tests

  by @NeoLabHQ

  Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or…

• Tree Of Thoughts

  by @NeoLabHQ

  Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation