Software Development AI agent skills

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

• Typescript Best Practices

  by @michael-denyer

  TypeScript best practices. Use when reading or editing any .ts or .tsx file.

• Blast Radius

  by @michael-denyer

  Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break',…

• Figure It Out

  by @michael-denyer

  Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via…

• Automate Me

  by @michael-denyer

  Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via…

• Correct

  by @michael-denyer

  Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real…

• Principle Type System Discipline

  by @michael-denyer

  Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to…

• Principle Build The Lever

  by @michael-denyer

  Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool…

• Principle Sequence Verifiable Units

  by @michael-denyer

  Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the…

• Babysit

  by @michael-denyer

  Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd…

• Thermo Nuclear Code Quality Review

  by @michael-denyer

  Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially…

• Teach

  by @michael-denyer

  Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this…

• Technical Writing

  by @michael-denyer

  Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR…

• Arena

  by @michael-denyer

  Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the…

• Make Pr Easy To Review

  by @michael-denyer

  Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the…

• Benchmark Checklist

  by @michael-denyer

  Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.

• Principle Boundary Discipline

  by @michael-denyer

  Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

• Principle Foundational Thinking

  by @michael-denyer

  Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

• Principle Prove It Works

  by @michael-denyer

  Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

• Principle Separate Before Serializing Shared State

  by @michael-denyer

  Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

• Principle Make Operations Idempotent

  by @michael-denyer

  Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

• Principle Exhaust The Design Space

  by @michael-denyer

  Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

• Principle Laziness Protocol

  by @michael-denyer

  Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

• Principle Model The Domain

  by @michael-denyer

  Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

• Principle Migrate Callers Then Delete Legacy Apis

  by @michael-denyer

  Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

• Principle Fix Root Causes

  by @michael-denyer

  Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

• Principle Experience First

  by @michael-denyer

  Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

• Principle Subtract Before You Add

  by @michael-denyer

  Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

• Swarm

  by @michael-denyer

  Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

• E Commerce

  by @firecrawl

  Navigate e-commerce sites to extract products, pricing, categories, and inventory. Handles pagination, variants, and JS-heavy storefronts.

• Fix Merge Conflicts

  by @michael-denyer

  Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

• No Comments

  by @michael-denyer

  Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.

• Fix Ci

  by @michael-denyer

  Find failing PR checks, inspect logs or external check links, and apply focused fixes

• What Did I Get Done

  by @michael-denyer

  Summarize authored commits over a user-specified time period into a concise update

• Get Pr Comments

  by @michael-denyer

  Fetch and summarize review comments from the active pull request

• Deslop

  by @michael-denyer

  Remove AI-generated code slop and clean up code style

• Unslop

  by @michael-denyer

  Cut AI tells from any writing. Must always apply.

• Fizz

  by @pashov

  Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects. Trigger on "fizz", "generate fuzz suite", "build fuzz harness", "stateful fuzzing", "fuzzing harness", "property testing", and "invariant…

• X Ray

  by @pashov

  Generates an x-ray.md pre-audit report covering overview, enhanced threat model (protocol-type profiling, git-weighted attack surfaces, temporal risk analysis, composability dependency mapping), invariants, integrations, docs…

• Image

  by @axoviq-ai

  Extract text from images using a vision LLM

• Markdown

  by @axoviq-ai

  Ingest Markdown and plain text files

• Pohuy

  by @smixs

  Режим идиоматического русского мата. Агент отвечает как живой русский инженер, который двадцать лет чинит прод: «наебнулось», «хуйня вопрос», «заебись, работает». Техническая точность байт в байт, лексика аутентичная. Уровни:…

• Pr Lens

  by @coldteadotai

  WHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should…

• Eli5

  by @coldteadotai

  WHAT: Explains a codebase, a folder, a feature, a command or a pull request to someone who knows nothing about it, as a PR Lens canvas whose walkthrough builds the picture one part at a time. WHEN: /eli5 <thing>, or asked to…

• Shellm

  by @laude-institute

  Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

• Web Research

  by @laude-institute

  Research topics using the web via curl. Use when the user asks to look something up, find current information, or research a topic online.

• Opencode

  by @laude-institute

  Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

• Obsidian

  by @laude-institute

  Read, write, search, and manage notes in an Obsidian vault

• Simulink Control Motors

  by @matlab

  Build motor control solutions using Motor Control Blockset for PMSM, induction motors, BLDC, and SynRM. Implement field oriented control, sensorless FOC, six-step control, speed control, current control, and torque control.…

• Simulink Author Classic Autosar Swc

  by @matlab

  Use this skill when authoring, reworking, or validating a Classic AUTOSAR software component (SWC) in Simulink, including autosar.api mappings, runnables, timing events, sender-receiver ports, client-server operations, IRVs, BSW…

• Specifying Mbd Algorithms

  by @matlab

  Specify algorithms for Model-Based Design: system specs, architecture specs, implementation plans, test plans. Use when creating specifications for controllers, signal processing, diagnostics, estimators, or other algorithms…

• Specifying Plant Models

  by @matlab

  Specify plant models for closed-loop simulation: system specs, architecture, build plans, validation plans. Use when creating, updating, or reviewing plant model specifications, planning plant model architecture, or planning…

• Simulink Configure Code Interfaces

  by @matlab

  Use the skill to control and verify the code interface configuration of your model — how Simulink® model elements are represented in the generated C or C++ code. This includes — (1) specifying names, types (storage classes), and…

• Filing Bug Reports

  by @matlab

  Generate a standalone bug report that another developer can use to reproduce, investigate, and fix an issue. Use when the user says 'file a bug', 'write a bug report', 'report this issue', or asks to document a defect for handoff.

• Simulink Curating Library Kg

  by @matlab

  Use this skill when the user wants to curate the SATK library knowledge index for a Simulink project — mark commonly used blocks, correct auto-assigned block categories, or improve block descriptions so the model-building agent…

• Simulink Linearize

  by @matlab

  Linearize Simulink models. Use when obtaining linear time invariant or linear parameter varying models from Simulink models.

• Solomd

  by @zhitongblog

  Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11…

• Create Image Fal

  by @gooseworks-ai

  Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls must be public URLs (orchestrator hosts local product refs via MCP…

• Create Video Fal

  by @gooseworks-ai

  Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), ROUTED THROUGH THE GooseWorks fal-proxy so the call bills the Ads agent. The template recipe names the model + params; image_url inputs must be…

• Media Proxy

  by @gooseworks-ai

  Shared helper that routes ALL paid media generation (FAL image/video, ElevenLabs music) through the GooseWorks proxies so every call bills the Ads agent — never a provider SDK's default host. Host-swaps the FAL queue URLs, loads…

• Create Music Elevenlabs

  by @gooseworks-ai

  Generate an instrumental music bed via ElevenLabs Music, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Trims any sparse intro, loudnorm, fades the tail. Prompt + length from the template recipe. Use for the…

• Backend

  by @sipyourdrink-ltd

  Python server code, APIs, async, strict typing.

• Extract Source Sample

  by @gooseworks-ai

  Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a `source-sample.json` in the exact…

• Store Submit

  by @zhitongblog

  Publish a SoloMD release to the stores that have no usable submission API — Google Play Console and Microsoft Partner Center — by driving them through the local Unzoo Browser REST API. Covers upload, release notes, track and…

• Meta Ad Scraper

  by @gooseworks-ai

  Scrape competitor ads from Meta's Ad Library (Facebook, Instagram, Messenger, Threads, WhatsApp). Search by company name, Facebook Page URL, or keyword. Returns ad creatives, spend estimates, reach, impressions, and campaign…

• Vp

  by @sipyourdrink-ltd

  Cross-cell coordination - resolve conflicts, decide pivots.

• Manager

  by @sipyourdrink-ltd

  Planning - decompose goals, create tasks via task server.

• Architect

  by @sipyourdrink-ltd

  System design - module boundaries, API contracts, ADRs.

• Reviewer

  by @sipyourdrink-ltd

  Code review - correctness, tests, merge-readiness.

• Ml Engineer

  by @sipyourdrink-ltd

  ML - training, inference, embeddings, evaluation.

• Frontend

  by @sipyourdrink-ltd

  React / Next.js UI, state, accessibility.

• Bernstein Run

  by @sipyourdrink-ltd

  Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and…

• Bernstein Approve

  by @sipyourdrink-ltd

  Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.

• Bernstein Create Task

  by @sipyourdrink-ltd

  Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug fix, or queue up work for the orchestrator to handle.

• Resolver

  by @sipyourdrink-ltd

  Git merge conflicts - resolve without losing intent.

• Ci Fixer

  by @sipyourdrink-ltd

  CI failures - read error, minimal fix, verify.

• Skill Release Gate

  by @fancyboi999

  在发布前评估 Agent Skill bundle 的结构完整性、触发质量、产物改进、脚本正确性、安全性、已安装目录树完整性和目标宿主可移植性。

• Skill Safety Reviewer

  by @fancyboi999

  在不执行的前提下，依据显式沙箱策略审查 skill 请求的文件系统、命令、网络、secret 或破坏性操作。

• Skill Invocation Router

  by @fancyboi999

  为 Agent Skill 目录设计并测试显式人工、隐式模型或 agent、程序化应用、有界 skill 组合和 harness 激活策略。

• Skill Catalog Builder

  by @fancyboi999

  在明确的发现 scope 中构建受限的 Agent Skill 目录，并在加载指令正文前报告冲突。

• Migration Review

  by @fancyboi999

  当（when）变更新增或修改 migrations/ 下的路径时，审查 database migration 文件。合并前使用此 migration Skill 收集正向、回滚、锁定和数据安全证据。

• Claude Certification

  by @fancyboi999

  AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评，或通过 GitHub 上的 Claude Code、 Codex、ChatGPT、Cursor 或其他 agent 补强薄弱考试领域时。

• Mcpa Certification

  by @fancyboi999

  AI Engineering from Scratch 中文版中的 MCPA（Model Context Protocol Associate）AI 原生导师与入门流程。学习者需要备考 MCPA、继续认证路线、 交互式学习下一课、运行并验证实践实验、参加诊断或全真模拟、根据薄弱领域 补弱时使用。适用于 Claude Code、Codex、ChatGPT、Cursor 或其他 agent。

• Learn Mcp

  by @fancyboi999

  AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。 学习者想构建、保护、调试、验证或运行 MCP clients、servers、transports、gateways、 registries 或 conformance gates 时，开始或续学此路线。每次调用教学一课，并将 wire evidence 记录到 MCP-LEARNING.md。Start…

• Learn Agent Skills

  by @fancyboi999

  AI Engineering from Scratch 中 Agent Skills Engineering 路线的专注交互 tutor。 学习者想创建、发现、调用、保护、评估、打包或迁移 Agent Skills 时，开始或续学此路线。 每次调用教学一课，并将证据记录在 AGENT-SKILLS-LEARNING.md。 Start or resume this route when a learner wants to create,…

• Verify Language Switch

  by @reticlehq

  Prove a language switch translates what the user sees, keeps what they had already typed, and is still in force after a reload. Use when i18n, a locale picker, a language menu or translation files were added or changed, when a…

• Slides Grab Design

  by @NomaDamas

  Stage 2 design skill usable in Codex and Claude Code. Generate and iterate slide-XX.html files in the selected slides workspace.

• Systematic Debugging

  by @GanyuanRan

  Use when encountering a bug, test failure, or unexpected behavior, before proposing fixes

• Using Aegis

  by @GanyuanRan

  Use when starting a turn or checking Aegis skill routing.

• Subagent Driven Development

  by @GanyuanRan

  Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

• Brainstorming

  by @GanyuanRan

  Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the…

• Writing Plans

  by @GanyuanRan

  Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.

• Requesting Code Review

  by @GanyuanRan

  Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.

• Test Driven Development

  by @GanyuanRan

  Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.

• Verification Before Completion

  by @GanyuanRan

  Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

• Dispatching Parallel Agents

  by @GanyuanRan

  Use when facing 2+ independent tasks without a written plan, with no shared state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.

• Executing Plans

  by @GanyuanRan

  Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.

• Update Aegis

  by @GanyuanRan

  Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

• Finishing A Development Branch

  by @GanyuanRan

  Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.

• Goal Framing

  by @GanyuanRan

  Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

• Using Git Worktrees

  by @GanyuanRan

  Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.