Updated 1d ago
by RBraga01
a-team
Universal multi-agent infrastructure for AI coding assistants. 26 specialist agents, 19 enforced workflow skills, and a lead orchestrator — for Claude Code, Codex CLI, Cursor, and OpenCode.
24 GitHub stars (24)
+3 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | +1 |
- 20 skills (20 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add RBraga01/a-team
Asks which skills and agents to install. Just one: npx skills add RBraga01/a-team --skill api-contract-first — add -g for every project.
Claude Code
git clone https://github.com/RBraga01/a-teamcp -r "a-team/skills/api-contract-first" ~/.claude/skills/
Copies the api-contract-first skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add RBraga01/a-team
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
api-contract-first
Hard gate before implementing any API endpoint or service interface. Requires a written, reviewed contract (OpenAPI 3.x, protobuf, or GraphQL schema) before any implementation code is written. Prevents breaking changes, misaligned clients, and undocumented behaviour.
skills/api-contract-first/SKILL.md on GitHub (opens in a new tab) -
architecture-audit
Systematic architecture review workflow. Use before major feature work on an unfamiliar or inherited codebase, before scaling milestones, or as a periodic health check. Maps the system as-built (not as-documented), dispatches parallel specialist reviews, and produces an evidence-backed findings report with severity verdicts.
skills/architecture-audit/SKILL.md on GitHub (opens in a new tab) -
brainstorming
Use BEFORE any creative work — creating features, building components, adding functionality. Explores user intent, requirements, and design before implementation. Hard-gated: no code until user approves the spec.
skills/brainstorming/SKILL.md on GitHub (opens in a new tab) -
data-migration
Hard gate before any database schema change or data transformation in production. Requires a written migration plan with rollback strategy, dry run, and verification steps before execution. Prevents data loss, downtime, and irreversible schema changes.
skills/data-migration/SKILL.md on GitHub (opens in a new tab) -
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatches one focused agent per problem domain, runs them concurrently, then integrates.
skills/dispatching-parallel-agents/SKILL.md on GitHub (opens in a new tab) -
executing-plans
Use when you have a written implementation plan to execute in the current session. Loads the plan, reviews critically, executes all tasks, and reports when complete.
skills/executing-plans/SKILL.md on GitHub (opens in a new tab) -
finishing-a-development-branch
Complete a development branch before merge — verify tests pass, update documentation, ensure quality gate passes, and prepare a clean PR.
skills/finishing-a-development-branch/SKILL.md on GitHub (opens in a new tab) -
five-whys
Root cause analysis using the Five Whys technique. Use when a bug persists despite surface fixes, a failure recurs, or a process keeps breaking. Ensures the fix targets the root, not the symptom.
skills/five-whys/SKILL.md on GitHub (opens in a new tab) -
incident-response
Production incident playbook. Use immediately when production is degraded or down. Five phases: detect, contain, diagnose, resolve, post-mortem. Prevents the chaos of uncoordinated response and ensures every incident produces lasting improvements.
skills/incident-response/SKILL.md on GitHub (opens in a new tab) -
performance-audit
Systematic performance investigation workflow. Use when performance regressions are suspected, before and after optimisation work, or as a pre-release gate for performance-critical features. Produces a baseline, identifies the real bottleneck, and validates improvement with hard numbers.
skills/performance-audit/SKILL.md on GitHub (opens in a new tab) -
skill-duplication-audit
No description in the SKILL.md.
skills/skill-duplication-audit/SKILL.md on GitHub (opens in a new tab) -
smart-init
Conversational onboarding for A Team. Detects ROADMAP.md, extracts context, generates INIT.md without requiring technical knowledge. Invoked automatically by the orchestrator when INIT.md is missing.
skills/smart-init/SKILL.md on GitHub (opens in a new tab) -
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session. Dispatches a fresh subagent per task with two-stage review (spec compliance, then code quality).
skills/subagent-driven-development/SKILL.md on GitHub (opens in a new tab) -
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. Enforces root-cause investigation before fixes. The Iron Law — no fixes without understanding why.
skills/systematic-debugging/SKILL.md on GitHub (opens in a new tab) -
test-driven-development
Enforce RED-GREEN-REFACTOR discipline for every implementation task. Use for all new features, bug fixes, and refactors. The core rule — if you didn't watch the test fail, you don't know if it tests the right thing.
skills/test-driven-development/SKILL.md on GitHub (opens in a new tab) -
using-a-team
The meta-skill. Loaded at every session start. Defines which A Team skills and agents MUST be used for which situations. If a skill or agent applies, you do not have a choice — you must use it.
skills/using-a-team/SKILL.md on GitHub (opens in a new tab) -
using-git-worktrees
Create or verify an isolated git worktree before starting any development work. Prevents main branch contamination, enables parallel feature development, and gives subagents a clean baseline. Use at the start of every feature branch.
skills/using-git-worktrees/SKILL.md on GitHub (opens in a new tab) -
verification-before-completion
Use before claiming ANY task is complete. Requires you to run actual verification commands, read real output, and confirm it matches expectations — before stating the task is done. Blocks "should work" rationalizations.
skills/verification-before-completion/SKILL.md on GitHub (opens in a new tab) -
writing-plans
Create a detailed, phased implementation plan from an approved spec. Use after brainstorming produces an approved spec. Produces a plan file that executing-plans or subagent-driven-development can consume.
skills/writing-plans/SKILL.md on GitHub (opens in a new tab) -
writing-skills
Create new A Team skills using TDD for documentation. Write a bad skill, watch agents fail at the gap, improve, iterate. Use when the team needs a new capability that no existing skill covers.
skills/writing-skills/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
oh-my-openagentby code-yeongyu OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
-
agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
-
MemOSby MemTensor Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savin…
-
hivemindby activeloopai Hivemind turns your traces into reusable skills across agents
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.