ai-coding-assistant commands

370 tagged ai-coding-assistant, measured the same way as everything else here.

Browse within: code-quality 164ai-assistant 154agentic-ai 116ai-development 93agentic-workflow 78claude-code-plugin 69ai-coding 67cli-tool 55ai-project-manager 53claude-compatible 53claude-ai 51aider 40agents 39ai-assisted-development 38

PackmindHub/packmind

Command Claude Code needs its repo

Implement a standardized repository with soft delete functionality and comprehensive tests to ensure maintainable code and reliable data access patterns in the Packmind codebase.

not rated 319 +1 today A 5 tokens original Apache-2.0

work

03

fockus/skill-memory-bank

Command Claude Code

A command that runs an existing Memory Bank workflow for planning, implementing, checking, reviewing, and completing development work. The workflow can use project plans or specification tasks.

not rated 26 changed 8d ago A 55 tokens original MIT

staleness-check

04

jonathanmr22/pact

Command Claude Code

Check what governance artifacts went stale based on what was edited this session.

not rated 15 4mo ago A 0 tokens original MIT

ai-do

05

lebsral/DSPy-Programming-not-prompting-LMs-skills

Command Claude Code

You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.

not rated 12 +1 3mo ago A 0 tokens

snek.fill

07

4tyone/snek

Command Claude Code

You are processing @@snek blocks - regions in source code where the developer has written specifications for code that needs to be generated or modified.

not rated 10 10mo ago A 0 tokens original Apache-2.0

discover

08

lx-wnk/Agent-Context

Command Claude Code

Build or refresh the on-demand discovery map (concept graph + per-node notes).

not rated 7 changed 15d ago A 16 tokens original MIT

review-decide

09

gosha70/code-copilot-team

Command Claude Code

Resolve a circuit breaker in the review loop. Accepts exactly one argument: approve, reject, or retry.

not rated 7 16d ago A 0 tokens original MIT

align

10

ApexIQ/skillsmith

Command Claude Code

Command "align" from ApexIQ/skillsmith, covering command: /align, goal, resources and execution plan.

not rated 5 6mo ago A 0 tokens original MIT

cut-release

11

rajdeepratan/SlashForge

Command Claude Code

Prepare a release — bump the version, finalize the changelog, and open the release PR that publishes on merge.

not rated 5 2d ago A 25 tokens original MIT

gate

14

Oreo-Mcflurry/claude-gate

Command Claude Code

You are the Gate System controller. Execute quality gate reviews based on the user's request.

not rated 3 4mo ago A 0 tokens original MIT

neural-patterns

15

airmcp-com/mcp-standards

Command Claude Code

Continuously improve coordination through neural network learning.

not rated 3 10mo ago A 0 tokens copy · 92% MIT archived

blueprint

16

AcKeskin/contexture

Command Claude Code

Author a concrete blueprint for a slug — what we wanted (intent) + what we're building now (classes, interfaces, dependencies, module relationships, build order) with Mermaid UML. Optional, after /draft-plan. Presents the draft for accept/edit/reject, then writes to .claude/docs/ /v .md and the Obsidian vault.

not rated 2 2mo ago A 73 tokens original MIT

README

17

afaizalam2003/Master-claude-skill

Command Claude Code

Git workflow and quality assurance commands for the claude-skills repository.

not rated 2 6mo ago A 0 tokens copy · 100% MIT

start-feature

18

zahardev/aicontext

Command Claude CodeOpenCode

Run a structured discovery interview before starting a new feature — explores the codebase, asks one question at a time, presents decision packages with options + recommendation, then creates a spec and task file.

not rated 2 17d ago A 38 tokens original MIT

bmad-init

19

miounet11/ccjk

Command Claude Code

This command initializes or updates BMad-Method (V6) in your project.

not rated 1 yesterday A 0 tokens original MIT

trw-reflect

20

wallter/trw-mcp

Command Claude Code

Run the end-of-session reflection: turn this session's friction into routed improvements (quick-fixes, PRDs, learnings, backlog) with a follow-through ledger.

not rated 0 yesterday A 0 tokens

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: