Claude Code and Codex plugins their authors filed under "workflow". All categories.
An AI-powered product development team covering discovery, UX, architecture, implementation, code review, and QA — with human approval gates at every critical decision. Pilot project is a Notes/Reminders Android app.
8 skills · 9 agents · hooks
Eight-stage spec-driven workflow (Questions, Research, Design, Structure, Slices, Plan, Implement, PR) on top of OpenSpec. Includes /qrspi:* commands, seven stage subagents, and supporting skills.
18 skills
Seven-phase AI-driven SDLC: phase agents, slash commands, document templates, mandatory approvals and logging. .NET, Playwright, optional Codex review.
12 skills · 6 agents
오케스트레이터 + PM, 플래너, 개발, QA, 마케팅 에이전트 팀으로 단일 제품의 개발과 마케팅을 통합 관리
8 skills · 9 agents · hooks
Kernpaket: Session-Start und -Uebergabe, Ideenpruefung, Machbarkeit, Aufgabenzerlegung, Sicherheits-Check mit Commit-Sperre, Freigabepruefung, Token-Sparmodus, Hilfe aus der Ferne.
17 skills · hooks
Bead-driven phase orchestration for ATM agent teams: atm-beads, atm-bd-orchestration and sprint-report skills plus the dev-sanity agents they name.
8 skills · 10 agents
Plan, build, check, prove, remember. From idea to MVP to finished build, with a stop at every segment's exit test.
11 skills · 6 agents · hooks
Plan execution framework with checkpoint-based session management, context loading, and orchestrated task dispatch
5 skills · 9 commands · 3 agents
Carries one piece of work from a remark in a session to merged: file the issue, do the work, review it and open the pull request, land it. Every step stops for a person, and the same gates cover READMEs. Needs `gh` or `glab`, authenticated.
17 skills
需求→開發→驗收→合併收尾的 14 個 skill、PR 證據閘門 hooks 與 Issue/PR 模板。
16 skills · hooks
Triage + orchestrator agents, pipeline skills (/task, /worktree, /commit, /review, /pr, /ship, /sync-docs) and enforcement hooks.
13 skills · 3 agents · hooks
Context-reconciled workflows for research, specs, in-repo design execution with opt-in designer commissions, accepted-evidence design contracts, integration-reality plans, verification, and handoffs.
17 skills
Always-on skills: code explanation, conventional commits, codebase visualization, code quality, git, and Vue/TypeScript frontend work
14 skills · 3 commands
Skills for trustable code: spec, design, slice, build, prove it works, and ship a feature with evidence.
17 skills
Kata Flight — kata and roborev workflow skills with optional RDR binding. Run /kata-flight-init once in a consumer project, then /kata-flight or /kata-ship to drain work.
16 skills
Idea → plan → architecture + design system → walking skeleton → verified tracer-bullet slices → release. Skills, subagents and guard hook for Claude Code.
11 skills · 4 agents · hooks
Portable orchestrator: generic agents, skills, guard hooks, and /og:orchestrate + /og:orchestrate-init slash commands for any repo.
8 skills · 7 agents · hooks
Spec, freeze, stories, build, judge, ship, retro. The human decides three times; a program checks the rest.
10 skills · 5 agents · hooks
Full SDD toolkit: foundation commands (/sdd:constitution, /sdd:context, /sdd:claude-md, /sdd:adr), the loop (/sdd:spec, /sdd:task, /sdd:review, /sdd:commit, /sdd:verify-ui), skills (brainstorm, grill-me, grill-with-docs, discovery, browser-verify, sdd-loop), templates, AND a PreToolUse guardrail hook that blocks force-push, catastrophic rm -rf, and writes to protected paths. Aligns before acting, chains each step, reminds you to verify.
6 skills · 9 commands · hooks
Enforced read-only conformance gate with whole-repo audit, CI enforcement, and an explicit local-container pentest skill using OWASP ZAP plus nuclei.
4 skills · 11 agents · hooks
Vendored copy of obra/superpowers (MIT) — brainstorming, planning, TDD, systematic debugging, subagent-driven development, and code-review workflows. Kept in-repo so Codex (via AGENTS.md) and other non-Claude harnesses can read these skills directly.
15 skills · hooks
The AI-native SDLC as a change pipeline: numbered intent/spec/plan artifacts under work/, tier-sized overhead, and a human gate at every stage that writes. Repo-agnostic mechanism; each repo supplies its own policy, commands and templates through .sdlc/config.toml.
15 skills · 1 agent
obra/superpowers — TDD, debugging, planning, code review, worktree workflows. Referenced upstream (always latest).
15 skills · hooks
Stack-agnostic AI dev workflow — thirteen slash commands, a focused reviewer agent, and hooks that layer with your project's .flow/ config
13 commands · 1 agent · hooks
The saas-skills kit in one plugin: the code-standard, tdd, not-overengineering and communication skills, the deterministic write guard and docs hooks, /saas-skills:setup and :upgrade to install and update the project-local half, and Linear-driven delivery — /spec and /implement plus the six agents that review, approve and ship a pull request.
4 skills · 4 commands · 6 agents · hooks
Superpowers 6.4.2, vendored from upstream as V2's engineering method.
14 skills · hooks
Unified workflow system with Stage A/B/C complexity routing (Spec → Dev → Exec)
14 skills · 1 agent
Always-on multi-persona code-review pipeline: parallel distinct-angle reviewer panels → a Code Review Master → a second adversarial panel → Master 2 → an opt-in Executor & Fixer. No token optimization; every panelist is always spun up. Opt-in.
1 skill · 1 command · 13 agents
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
14 skills · hooks
Skill that enforces a doc-first per-phase workflow: brainstorm with research gate, planned execution with per-task cadence, dual-track smoke (manual + Playwright), phase delivery handoff, and milestone-done gate. Designed to be the same workflow across all your projects.
1 skill · 14 commands