Best software development skills, page 25

A skill your agent uses to generate well-branded interfaces and assets for fast-agent, either for production or throwaway prototypes/mocks/etc.

evalstate/fast-agent

Automate git worktree creation and copy private files (not tracked in git) to new workdirs.

k8zdev/k8z

A skill your agent uses when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release…

Prism-Shadow/penguin-harness

Drive Chrome via the DevTools Protocol from JavaScript. An agent skill from browser-use/browser-harness-js.

browser-use/browser-harness-js

Cut a new RocketPy release: prepare the version-bump branch, update the changelog and all version references, and guide the PR-to-master + PyPI flow.

RocketPy-Team/RocketPy

Runs the full release of the remotion-bits package: version bump, changelog, registry build, release commit, GitHub release, docs deploy and npm publish.

av/remotion-bits

Build, review, and troubleshoot STDF Svelte 5 applications using exact component APIs, themes, icons, localization, and scaffolding.

any-tdf/any-tdf

使用 bm.md 写作、改写、排版或渲染 Markdown；生成 Mermaid 与 AntV Infographic，设置图片尺寸、高亮重点，以及执行 HTML/纯文本转换和 Markdown lint

miantiao-me/bm.md

Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.

Devin-AXIS/iPolloWork

Guide for implementing, configuring, and debugging React Joyride v3 guided tours.

cadence-workflow/cadence-web

SVG diagramming conventions blending a technical look with CJK-friendly typography.

bybit-exchange/svg-diagram

Simplifies code for clarity. An agent skill from sanity-io/sanity.

sanity-io/sanity

Python development guidance with code quality standards, error handling, testing practices, and environment management.

databricks-solutions/ai-dev-kit

Conducts multi-axis code review. An agent skill from sanity-io/sanity.

sanity-io/sanity

Runs a hostile review of the Caffeine Java caching library with parallel subagents that get no design docs, then challenges and consolidates their findings.

ben-manes/caffeine

Firmware crash analysis, stack trace decoder, and register dump interpreter for ESP32/ARM/AVR platforms.

FastLED/FastLED

Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

NVIDIA/Megatron-LM

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

udecode/plate-playground-template

Cascade-merge the maintained Symfony UX branches from oldest to newest (2.x - 3.x), resolve conflicts, run the affected packages' tests and prepare the push.

symfony/ux

Run the current worktree as a production-shaped local dev instance with web, Slack, or both, on a real LLM + Postgres.

yc-software/qm

Generate a changelog entry for the current Git branch by inspecting changed files, classifying the domain and type, writing a short public-friendly message, and running just changelog add after the…

baserow/baserow

Automates a version release with changesets: analyzes code changes, writes a bilingual CHANGELOG, bumps the version and commits through a release branch and pull request.

UfoMiao/zcf

Run Ethereum multi-client devnets using Kurtosis and the ethpandaops/ethereum-package.

ethpandaops/ethereum-package

Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength.

Zhen-Bo/smell-check

Generate Excalidraw diagrams from text content. An agent skill from Gerstep/cybos.

Gerstep/cybos

Create one well-formed tracker issue from a brief without implementing it — dedupes against existing issues and PRs, links a covering spec (authoring one via om-auto-write-spec on a design-only PR…

go-musicfox/go-musicfox

Bumps the verygoodanalysis package to a new version. An agent skill from VeryGoodOpenSource/very_good_analysis.

VeryGoodOpenSource/very_good_analysis

Run, interpret, or modify Skylos safely. An agent skill from duriantaco/skylos.

duriantaco/skylos

Semantic code analysis via LSP. An agent skill from lsp-client/lsp-skill.

lsp-client/lsp-skill

Publishes a GitHub PR for the checked-out branch with a Conventional Commits style title, a description backed by commands run, and screenshots when the UI changed.

antfu/skills

Utilities for browser extensions - proxy services for cross-context RPC, type-safe messaging, URL match patterns, fake browser for testing, job scheduling, and shadow DOM isolation.

mengxi-ream/read-frog

Create and validate Beachball change files. An agent skill from microsoft/beachball.

microsoft/beachball

Reconcile the SDK against the Mollie API spec — checks and optionally fixes types, JSDoc, enums, deprecations, endpoint coverage, and helper wiring.

mollie/mollie-api-node

A skill your agent uses when researching React APIs or concepts for documentation.

reactjs/ar.react.dev

Syncs or audits ccLoad's CLIProxyAPI protocol-conversion core and registered provider adapters against one pinned upstream commit, then verifies the result.

caidaoli/ccLoad

Generates, edits and validates draw.io files with correct mxGraph XML, covering flowcharts, architecture, sequence, ER and UML class diagrams.

github/awesome-copilot

Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

bgauryy/octocode

Creates, edits, reviews, and regenerates C4 architecture diagrams written with goa.design/model and the mdl CLI.

goadesign/model

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch).

karanhudia/borg-ui

Converts MLIR lit test files to bazel run commands. An agent skill from google/heir.

google/heir

Runs one improvement mission as a bounded loop: each round makes a change, runs a strict JSON evaluator, logs the decision in markdown and continues until a max runtime is hit.

Yeachan-Heo/gajae-code

Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering.

shapeshift/web

Audit App-Store-Connect-CLI pull requests end to end and fix concrete defects when authorized.

rorkai/App-Store-Connect-CLI

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings.

umputun/revdiff

A skill your agent uses when editing .lean files, debugging Lean 4 builds (type mismatch, sorry, failed to synthesize instance, axiom warnings, lake build errors), searching mathlib for lemmas…

cameronfreer/lean4-skills

CCW command help system. An agent skill from catlog22/Claude-Code-Workflow.

catlog22/Claude-Code-Workflow

A skill your agent uses when a change may need a .changes note, the Release note gate fails, or deciding whether type: internal or no-release-note applies.

4gray/iptvnator

Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.

backnotprop/plannotator