Back to categories
Category

Agent Skills in category: Uncategorized

81818 skills match this category. Browse curated collections and explore related Agent Skills.

governance

Creates Architecture Decision Records (ADRs) and Change Requests (CRs) for project governance. Activates on keywords like "ADR", "architecture decision", "CR", "change request", "governance", "technical decision", or "requirement change". Use for documenting technology choices, architectural patterns, or scope modifications.

desek
desek
3

build-and-learn

ACTION REQUIRED - After completing ANY non-trivial task (writing code, creating content, building strategies, designing anything), Claude MUST immediately invoke this skill and offer learning modes to the user. Do not wait for user to ask. Say "Want to understand the thinking behind what we just built?" then offer Quick (1 min) / Standard (10 min) / Deep (30 min) modes. Also invoke when user types "/build-and-learn" or asks "why did you do it this way" or "what could go wrong".

moh4med
moh4med
0

changelog-generator

|

hiccup-za
hiccup-za
1

istqb-foundation

|

hiccup-za
hiccup-za
1

openbio

>

[biologyproteingenomicschemistry
openbio-ai
openbio-ai
31

prompt-design

|

mrchen-hero
mrchen-hero
344

moonkite-maliang

UMPF 结构化提示词生成大师 - 通过多轮深度对话引导用户打磨电影级画面方案。支持 8 种视觉引擎(摄影/印刷/3D/油画/像素/水墨/定格动画/Pantone编辑插画)。触发条件: (1) 用户说'生成提示词'、'画一个...'、'帮我设计画面' (2) 需要 Nano banana 提示词 (3) 用户想要专业艺术指导生成图片 (4) 提到 UMPF 或 moonkite-maliang (5) 指定 style pantone + 主题,直接进入 Pantone 流程

huzhicheng
huzhicheng
84

moonkite-wechat-hongbao

微信红包封面创意设计大师 - 专注于卡通、动漫、游戏CG、商业海报风格的红包封面设计。支持三种创作模式(手动/自动/脑暴),一次性输出多尺寸提示词套装。触发条件: (1) 用户说'设计红包封面'、'红包封面'、'春节红包' (2) 需要微信红包封面设计 (3) 提到 wechat-hongbao

huzhicheng
huzhicheng
84

best-java-structure

Java Layered Architecture Design Pattern — A complete implementation guide for the classic five-layer architecture using Spring Boot + MyBatis-Plus. Suitable for bootstrapping new Java projects, refactoring existing architectures, establishing team development standards,and database migration scenarios.

chasepassion
chasepassion
2

bug-fix

Used for locating, reproducing, validating, and fixing software defects. Applicable when the user asks to "fix a bug," "locate an error," "analyze and fix an error," "reproduce an issue," "find the root cause," and similar scenarios.

chasepassion
chasepassion
2

test-best-pratice

A general skill for writing high-quality automated tests. Use it to design and implement stable, maintainable, and diagnosable tests for functions, modules, APIs, components, pages, and critical business workflows.

chasepassion
chasepassion
2

x-bookmark-analysis

>

chasepassion
chasepassion
2

architecture-diagram-draw

Draw clear, audience-appropriate software architecture diagrams and their companion sequence diagrams that communicate scope, structure, interfaces, and relationships without mixing abstraction levels or mixing static structure with runtime flow.

chasepassion
chasepassion
2

express-improve

Helps users design, optimize, and review the structure and content of speeches, presentations, and persuasive communication in a wide range of high-stakes scenarios. Applicable situations include, but are not limited to: startup pitches and co-founder recruiting, research presentations and thesis defenses, job talks and academic interviews, product demos and investor pitches, lab meetings and progress updates, public speaking and TEDx-style talks, conference presentations and panel remarks, oral exams and qualifying defenses, expressing viewpoints and persuading others, upward reporting and performance reviews, and internal proposals and solution walkthroughs.

chasepassion
chasepassion
2

fastapi-structure-guide

Trigger when the user wants to create a new FastAPI project, add new features, refactor code, or asks about architectural best practices. This skill enforces 2026 clean architecture with SQLModel, Repository Pattern, full async, and production-ready workflow.

chasepassion
chasepassion
2

log-build

Add or refine sparse, structured, file-persisted application logs for non-trivial code changes. Use when Agent is proposing an implementation approach, writing a plan, or implementing or modifying complex business logic, critical state transitions, validation or parsing flows, boundary interactions (HTTP, DB, cache, queue, filesystem, subprocess), retries, fallbacks, async jobs, concurrency, or background tasks, because planning is the right time to decide log placement. Reuse the project's existing logging infrastructure whenever possible. Do not use for trivial edits, simple obvious CRUD, blanket "log everything" requests, or low-value noise.

chasepassion
chasepassion
2

orchestrate-multi-target-sdks

>-

speakeasy-api
speakeasy-api
186

configure-sdk-options

>-

speakeasy-api
speakeasy-api
186

customize-sdk-hooks

|

speakeasy-api
speakeasy-api
186

diagnose-generation-failure

Use when SDK generation failed or seeing errors. Triggers on "generation failed", "speakeasy run failed", "SDK build error", "workflow failed", "Step Failed", "why did generation fail"

speakeasy-api
speakeasy-api
186

extract-openapi-from-code

Use when extracting or generating an OpenAPI spec from existing API code. Triggers on "extract OpenAPI", "code first", "generate spec from code", "FastAPI OpenAPI", "Spring Boot OpenAPI", "NestJS swagger", "Django OpenAPI", "Flask OpenAPI", "Rails swagger", "Laravel OpenAPI", "existing API code"

speakeasy-api
speakeasy-api
186

generate-mcp-server

Use when generating an MCP server from an OpenAPI spec with Speakeasy. Triggers on "generate MCP server", "MCP server", "Model Context Protocol", "AI assistant tools", "Claude tools", "speakeasy MCP", "mcp-typescript"

speakeasy-api
speakeasy-api
186

generate-terraform-provider

>-

speakeasy-api
speakeasy-api
186

improve-sdk-naming

Use when you want AI-powered suggestions for SDK naming improvements via the `speakeasy suggest` command (not manual overlay creation). Triggers on "suggest improvements", "speakeasy suggest", "AI suggestions", "suggest operation-ids", "suggest error-types", "auto-improve naming", "get AI recommendations".

speakeasy-api
speakeasy-api
186

manage-openapi-overlays

Use when creating, applying, or validating overlay files including x-speakeasy extensions. Covers overlay syntax, JSONPath targeting, retries, pagination, naming, grouping, open enums, global headers, custom security. Triggers on "create overlay", "apply overlay", "overlay file", "x-speakeasy", "add extension", "configure retries", "add pagination", "overlay for retries".

speakeasy-api
speakeasy-api
186

orchestrate-multi-repo-sdks

>-

speakeasy-api
speakeasy-api
186

setup-sdk-testing

Use when setting up SDK testing, configuring contract tests, writing Arazzo test workflows, or running integration tests. Triggers on "SDK testing", "test SDK", "contract testing", "Arazzo tests", "integration tests", "speakeasy test", "mock server", "test generation", "ResponseValidationError"

speakeasy-api
speakeasy-api
186

speakeasy-context

Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI.

speakeasy-api
speakeasy-api
186

start-new-sdk-project

>-

speakeasy-api
speakeasy-api
186

writing-openapi-specs

Reference guide for OpenAPI specification best practices, naming conventions, and expressing complex REST API patterns like polymorphism, enums, file uploads, and server-sent events. Use when writing or improving OpenAPI specs to ensure they follow established conventions and generate quality SDKs.

speakeasy-api
speakeasy-api
186

template-skill

Replace with description of the skill and when Claude should use it.

shafran123
shafran123
1

scoutqa-test

>-

phatpham-katalon
phatpham-katalon
1

logging-sucks

Design or review structured application logging, canonical request events, correlation, redaction, and sampling. Use when changing logging instrumentation or auditing log quality, not for every debugging task.

Boris Tane
Boris Tane
20615

animated-sprites

Create, repair, and review custom characters for 2D animation, animated sprite sheets, and custom Codex or ChatGPT pets, with consistent identity, readable motion, and timing-faithful previews.

elithrar
elithrar
20615

anti-slop

Edit formulaic or AI-sounding prose while preserving the author's voice. Use for an anti-slop pass, editorial review, or requests to make writing sound more human; ordinary drafting does not require this skill.

elithrar
elithrar
20615

code-reviewer

Review a specified code change for actionable defects. Use for uncommitted changes, base-branch diffs, commits, PRs or MRs; review alone is read-only, and requested fixes follow the review. Not a repository-wide security or complexity audit.

elithrar
elithrar
20615

create-readme

Write or improve concise, reader-focused README.md files for open source projects. Use for new READMEs, README rewrites, installation and usage examples, or README reviews. Do not use for API references, tutorials, changelogs, contributing guides, or unrelated prose editing.

elithrar
elithrar
20615

cut-ready

Create, revise, or preflight fabrication files for 2D cutting, physical graphics, formed parts, CNC machining, and 3D printing. Use for CAD solids, cut paths, print meshes, slicer handoffs, fit, and production requirements; not standalone technical documentation, digital-only graphics, NC-program qualification, or machine operation.

elithrar
elithrar
20615

engineering-drawings

Create, revise, or rigorously review electrical termination and wiring diagrams, engineering BOMs, mechanical part and housing drawings, and 2D views of 3D models. Use for engineering drawing structure, symbols, connections, projections, dimensions, tolerances, and export review; not presentation graphics or fabrication-process qualification alone.

elithrar
elithrar
20615

motronic

Diagnose Porsche Carrera 3.2 Bosch Motronic faults and interpret DME ROMs or calibration changes. Use for 1984-1989 3.2 DME systems, including swaps into earlier cars; not generic 911, CIS, or other ECU advice.

elithrar
elithrar
20615

neo-industrial-design

Design or restyle web interfaces in the user's neo-industrial or editorial-brutalist style. Use when that visual direction is requested; not for generic dashboards, dark themes, or copywriting.

elithrar
elithrar
20615

prompt-engineer

Audit and revise system prompts, developer instructions, tool descriptions, and reusable LLM prompt templates. Use for behavioral failures such as over-searching, format drift, weak tool use, instruction conflicts, or unsupported claims. Use for prompt behavior, not ordinary prose editing or skill packaging alone.

elithrar
elithrar
20615

summarize-work

Summarize OpenCode session history into work recaps, commit messages, or PR descriptions. Use when a summary needs past sessions or cross-project history; ordinary commits and summaries fully supported by the current conversation do not need this skill.

elithrar
elithrar
20615

web-perf

Diagnose page-load and interaction performance using browser traces, network evidence, and source code. Use for site-speed, Lighthouse, Core Web Vitals, or layout-shift investigations; a general accessibility audit is separate.

elithrar
elithrar
20615

wow-addon-development

Build, improve, debug, port, or review World of Warcraft Retail and official Forever add-ons. Use for addon Lua/XML, packaging, settings, persistence, performance, and in-game UI. Not for gameplay advice, addon recommendations, or WoW-themed websites.

elithrar
elithrar
20615

agent-exec

Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.

geli2001
geli2001
1

ui-extractor

Analyze screen recordings and websites to extract implementation specs, design systems, and UI patterns.

alpex-ai
alpex-ai
0

creating-operational-skills

Create new Claude Code skills following best practices. Use when the user asks to create a new skill, make a skill, or automate a workflow as a skill.

daralthus
daralthus
0

spec-flow

Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.

echovic
echovic
347

personal-growth-skill

日/周闭环规划系统,配合 Obsidian 使用

kevinxft
kevinxft
0

Page 302 of 1637 · 81818 results