ai-coding-agent skills

529 tagged ai-coding-agent, measured the same way as everything else here.

Browse within: agent-plugins 194agentic-coding 183claude-ai 167anthropic-claude 142cli-tools 131coding-agent 91codex-cli 79opencode 72codex-plugin 67context-engineering 67coding-paradigm 66gemini 66claude-code-plugin 64cpaas 52

pytrio-skill

25

SwanHubX/pytrio-skill

Skill Claude CodeCodex

A Python software development kit for sending large-model training and inference work to the remote TRIO service. Your local code prepares data and controls the process while the service performs model calculations and saves weights.

not rated 17 24d ago A 191 tokens original MIT

design

26

OutlineDriven/odin-codex-plugin

Skill Claude CodeCodex

Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…

not rated 15 1mo ago A 151 tokens original Apache-2.0

bharat2808/codex-universal-proxy

Skill Claude CodeCodex

Install and manage the unofficial codex-universal-proxy local compatibility tool. Use when the user wants Codex to install it from npm, clone/download the repo, configure model routing, start/restart/inspect the proxy, switch the local experimental Ollama/proxy workflow on or off, or uninstall it.

not rated 15 12d ago A 69 tokens original MIT

sigil-preflight

28

Ju571nK/sigil

Skill Claude CodeCodex

Before running a risky shell command, check it with Sigil's assess and refuse anything Sigil would block. Use whenever you are about to execute a destructive, privileged, or unfamiliar command.

not rated 13 11d ago E 46 tokens original Apache-2.0

deliver

29

firatcand/forge

Skill Claude CodeCodex

Drive a whole phase or feature-set to "merged + Done" — themed batching over /drive, front-loaded architectural questions, phase-gate ceremonies, and lossless resume. The long-horizon recipe ABOVE /drive; pair with native /goal " delivered" for hands-off, multi-turn completion.

not rated 13 1mo ago A 64 tokens original MIT

loopflow

30

tickets-forge-dev/loop-lang

Skill Claude CodeCodex

Create and run Loop (.loop) flows — a natural-language DSL for loop engineering. Use when the user wants to author, write, run, or execute a self-correcting or human-gated AI coding loop, turn an epic into a pipeline, fix a bug "as a loop", build a feature or whole app "as a loop", learn what Loop is or how to use it…

not rated 11 1mo ago A 136 tokens

docs-sync

31

chriscox/agent-skills

Skill Claude CodeCodex

Keep project documentation in sync with code changes. Identifies which docs need updating after a PR merges or code changes, drafts the updates, and manages doc site structure (mkdocs, docusaurus, vitepress). Use when: (1) a PR just merged and docs may need updating, (2) the user says "update the docs" or "sync docs"…

not rated 10 5mo ago A 147 tokens original MIT

desktop-controller

32

24kchengYe/desktop-controller-skill

Skill Claude CodeCodex

Universal desktop application controller for Windows. Automate any desktop app — send messages, click buttons, type text, take screenshots, and interact with native Windows applications. Use this skill when the user asks to: "control my computer", "automate desktop", "send a message on [any chat app]", "click on…

not rated 10 5mo ago A 304 tokens original MIT

loop-build

33

muzafferkadir/nextjs-loop-engineering-starter

Skill Claude CodeCodex

(loop-engineering) Implements exactly one feature from the BACKLOG.md Backlog — syncs main, acquires the loop lock, creates a feature branch, implements all acceptance criteria with tests, visually inspects UI changes, passes the independent verifier, and opens a PR. Use for Build-mode loop runs, or when asked to…

not rated 10 2mo ago A 84 tokens original MIT

project-conventions

34

choi138/toki

Skill Claude CodeCodex

Apply this before changing Toki source, tests, app resources, XcodeGen configuration, SwiftFormat/SwiftLint settings, usage readers, security audit logic, SwiftUI feature screens, view models, or macOS app entry code.

not rated 10 3d ago A 53 tokens original MIT

sitemd

35

sitemd-cc/sitemd

Skill Claude CodeCodex

Manage this sitemd project — pages, settings, deploy, dev server, and content generation. All operations route through the sitemd CLI.

not rated 9 2mo ago A 34 tokens

orchestrate

36

KirschBluteX/agent-orchestration-gateway

Skill Claude CodeCodex

Plan and supervise user-approved software initiatives through Codex native tasks and bounded native subagents. Use when the user explicitly asks Agent Orchestration Gateway to clarify work, split it into non-overlapping modules, dispatch module tasks, or run an AOG module task.

not rated 7 18d ago A 57 tokens original MIT

engineer-software

37

KirschBluteX/engineer-software

Skill Claude CodeCodex

Route substantive software engineering work through the smallest evidence-driven workflow: close unclear requirements or plans, trace an unknown failure, run a disposable decision probe, deliver and verify a defined code change or refactor, inspect structural redundancy, or draft local work items. Use when software…

not rated 6 20d ago A 101 tokens original MIT

cloudml-eval-ops

38

MiaoDX/roboclaws

Skill Claude CodeCodex

Run frozen Roboclaws Eval Harness rows on CloudML with bounded parallelism, official cml lifecycle commands, executor-backed JuiceFS transfer, durable task receipts, verified collection, and explicit retry/preemption evidence. Use when a user asks to run, refresh, resume, monitor, collect, or debug a Roboclaws…

not rated 6 2d ago A 99 tokens original MIT

triage-issue

39

OutlineDriven/odin-gemini-cli-extension

Skill Claude CodeCodex

Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.

not rated 5 1mo ago A 54 tokens copy · 100% Apache-2.0

concise

41

Cpp1022/concise

Skill Claude CodeCodex

A writing rule for concise answers: lead with the conclusion, use one or two sentences, and avoid plans, tool commentary, repeated background, and unnecessary sections.

not rated 3 2mo ago A 0 tokens original MIT

public-release

42

eddmann/agent-toolkit

Skill Claude CodeCodex

Comprehensive pre-release audit for making a GitHub repository public.

not rated 2 4mo ago A 15 tokens

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Independently challenge a consequential proposed decision, design, architecture, or approach before acceptance. Use for non-obvious tradeoffs or a high cost of being wrong; do not use for routine low-risk choices, implementation, or general defect discovery in existing code.

not rated 2 14d ago A 58 tokens original MIT

memory

44

wufunc/nova

Skill Claude CodeCodex

Memory management across personal and project layers. Modes: (1) 'recall' — durable recall when session memory is needed, (2) 'remember' — explicit user-directed memory write with pre-write recall, (3) 'snapshot-recall' — explicit historical session recall, (4) 'update' — project memory evaluation before git commit…

not rated 2 4mo ago A 106 tokens original MIT

corral

45

x0c/corral

Skill Claude CodeCodex

Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…

not rated 2 yesterday A 80 tokens original MIT

hapi-ota-release

46

miuiadmin/hapi-hmos

Skill Claude CodeCodex

A guide for releasing and checking HAPI-HMOS over-the-air updates. OTA updates are software updates delivered directly to devices.

not rated 1 25d ago A 156 tokens AGPL-3.0

mnemex-skills

47

notsointresting/mnemex

Skill Claude CodeCodex

Use mnemex before implementing a significant code change. Mnemex is a local-first decision-integrity layer: it anchors a decision to code and reports whether that decision is still fresh.

not rated 1 1mo ago A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: