agentic-coding skills

4,576 tagged agentic-coding, measured the same way as everything else here.

Browse within: agentic-workflow 203ai-skills 113agentic 85software-engineering 83Autonomous Agents 73coding-agents 69ai-workflows 60agentic-workflows 59ai-governance 58code-quality 58spec-driven-development 58ai-testing 57ai-coding-agent 52context-engineering 51

t

49

Yeachan-Heo/oh-my-claudecode

MCP server Claude CodeCodexCursor +2

MCP server "t" as configured in Yeachan-Heo/oh-my-claudecode. Runs ${CLAUDE_PLUGIN_ROOT}/bridge/mcp-server.cjs with node.

39k +39 yesterday A tokens not measured original MIT

Yeachan-Heo/oh-my-claudecode

Instructions file CodexOpenCode

AGENTS.md instructions for Yeachan-Heo/oh-my-claudecode, covering oh-my-claudecode - intelligent multi-agent orchestration, working agreements, setup and review guidelines.

39k +39 changed today A 5,140 tokens original MIT

Yeachan-Heo/oh-my-claudecode

Instructions file

Claude Code instructions for Yeachan-Heo/oh-my-claudecode, covering oh-my-claudecode - intelligent multi-agent orchestration and setup.

39k +39 changed today A 1,515 tokens original MIT

ask

55

Yeachan-Heo/oh-my-claudecode

Command

This compatibility command keeps /oh-my-claudecode:ask available without loading the full ask skill description in every Claude Code session.

39k +39 yesterday A 0 tokens original MIT

trace

57

Yeachan-Heo/oh-my-claudecode

Command

This compatibility command keeps /oh-my-claudecode:trace available without loading the full trace skill description in every Claude Code session.

39k +39 yesterday A 0 tokens original MIT

UserPromptSubmit

58

Yeachan-Heo/oh-my-claudecode

Hook

Runs when you submit a prompt, before the agent sees it, executing run.cjs via node (2 commands). From Yeachan-Heo/oh-my-claudecode.

39k +39 yesterday A tokens not measured original MIT

SessionStart

59

Yeachan-Heo/oh-my-claudecode

Hook

Runs when a session starts on init and maintenance, executing run.cjs via node (5 commands). From Yeachan-Heo/oh-my-claudecode.

39k +39 yesterday A tokens not measured original MIT

SessionEnd

60

Yeachan-Heo/oh-my-claudecode

Hook

Runs when a session ends, executing run.cjs via node (2 commands). From Yeachan-Heo/oh-my-claudecode.

39k +39 yesterday A tokens not measured original MIT

drydock

63

Yeachan-Heo/oh-my-claudecode

Skill Claude CodeCodex

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check…

39k +39 yesterday A 84 tokens original MIT

mcp-builder

64

HKUDS/DeepCode

Skill Claude CodeCodex

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

16k +14 5d ago A 61 tokens original MIT

HKUDS/DeepCode

Skill Claude CodeCodex

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…

16k +14 5d ago A 99 tokens original MIT

webapp-testing

66

HKUDS/DeepCode

Skill Claude CodeCodex

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

16k +14 5d ago A 35 tokens original MIT

mindfold-ai/Trellis

Skill Claude CodeCodex

A structured way to examine a problem from its basic assumptions upward. It encourages questioning why a design exists and whether a different approach would be better.

14k +56 6d ago A 164 tokens AGPL-3.0

python-design

68

mindfold-ai/Trellis

Skill Claude CodeCodex

Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .trellis/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding…

14k +56 6d ago A 73 tokens AGPL-3.0

ts-sdk-author

69

mindfold-ai/Trellis

Skill Claude CodeCodex

Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo. Covers workspace layout, public API and module boundaries, plugin extension points, branded types and library-tuned tsconfig, tsdown bundling (vs tsup/tsc-only/unbuild), package.json exports with dual ESM+CJS…

14k +56 6d ago A 219 tokens AGPL-3.0

trellis-check

70

mindfold-ai/Trellis

Agent Claude Code

Code quality check expert. Reviews code changes against specs and self-fixes issues.

14k +56 6d ago A 20 tokens AGPL-3.0

create-manifest

71

mindfold-ai/Trellis

Command Claude Code

Create a migration manifest for a new patch, beta, rc, or minor release based on commits since the previous release.

14k +56 6d ago A 0 tokens AGPL-3.0

finish-work

72

mindfold-ai/Trellis

Command Claude Code

Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.

14k +56 6d ago A 0 tokens AGPL-3.0

At most 3 mods per repository are shown here — the rest are on their repository pages: