superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Seven-phase AI-driven SDLC: phase agents, slash commands, document templates, mandatory approvals and logging. .NET, Playwright, optional Codex review.
Plugin sdlc from marketplace sdlc-workflow in palakornims/sdlc-workflow-ai-driven-development. Commands read from the repo's manifest — 1 month ago.
breakdownPhase 3 Breakdown. Decompose an approved design into tiered TASK- tickets, delivery plan, and execution-ordered backlog via the project-manager agent.
codexTurn the optional OpenAI Codex second review on or off for this project, or show its current state and whether the Codex CLI, login, and plugin are ready.
designPhase 2 Design. Produce architecture, ADRs, contracts, data model, threat model (OWASP Top 10), and gap analysis from an approved plan via the solution-architect agent.
doctorDiagnose the sdlc workflow environment - MCP tool-name mismatches, stale or duplicate Playwright MCP server processes, port conflicts, missing tools, and status drift between task tickets and the backlog. Reports findings and the exact command to fix each one.
implementPhase 4 Implement. Implement one approved TASK- ticket on its own branch via the dotnet-developer agent, then run /codex:rescue on the result when Codex review is on.
initScaffold the AI-driven SDLC workflow into the current project - docs folders, templates, logs, WORKFLOW.md, CLAUDE.md section, settings, sdlc.config.json (Codex review on/off), Codex and Playwright config, setup script. Idempotent; never overwrites existing files.
logAppend a human action to the correct workflow log (review, test, validation, or task ticket) so the mandatory logging rule is satisfied for approvals, Codex runs, dismissals, and sign-offs.
planPhase 1 Plan. Turn a feature idea into an approved PRD, REQ- requirements with Given/When/Then scenarios, and STORY- tickets via the product-owner agent.
reviewPhase 5 Code Review. Review a task's PR with the code-reviewer agent plus a second independent reviewer - Codex (/codex:rescue and the human-only Codex commands) when Codex review is on, otherwise a Sonnet second-opinion review.
statusShow where every feature sits in the workflow (approvals, tasks, open findings, defects, validation) and the next command to run.
triagePhase 5 triage-and-fix loop. Register code-reviewer, Codex (when on), or human review findings, get solution-architect and dotnet-developer decisions, fix agreed findings one commit each, and re-review, logging every step.
validatePhase 7 Validation. The product-owner agent walks every acceptance scenario on the running system, builds traceability, routes VAL- findings, and stops for release sign-off.
code-reviewerCode Reviewer for the Code Review phase. Use after the dotnet-developer has opened a PR (or after any code change) to review the diff for correctness, Clean Architecture conformance, .NET/C# best practice, OWASP Top 10 (2025) controls, and test adequacy, consolidate second-reviewer findings the main
dotnet-developer.NET / C# Developer for the Implement phase. Use to implement one approved TASK- ticket at a time on its own branch, following Clean Architecture, the dotnet-skills plugin practices, .NET and C# best practice, and the OWASP Top 10 (2025) controls from the threat model, then opening a PR and stopping
product-ownerProduct Owner for the Plan phase and the Validation phase. Plan mode - use when a new feature, idea, or requirement arrives and needs to be analysed, turned into a PRD with numbered requirements and Given/When/Then acceptance criteria, and broken into story tickets ready for the Design phase. Valida
project-managerProject Manager for the Breakdown phase. Use after the Design documents are approved to decompose the design into an ordered work breakdown of TASK- tickets and sub-tasks under docs/03-tasks/, core structure and main feature first, then components, with dependencies, milestones, and sizing. Follows
qa-engineerPrincipal QA Engineer for the Test phase. Use after a task or story is merged to define the test strategy, drive the Playwright test agents (planner, generator, healer) from the Given/When/Then acceptance criteria, review generated tests, run the full suite (.NET unit/integration plus Playwright end
solution-architectPrincipal Solution Architect for the Design phase. Use after the Plan documents are approved to produce the architecture, ADRs, API contracts, data model, threat model, and gap analysis under docs/02-design/. Applies Clean Architecture, the current OWASP Top 10 (2025), and software engineering best
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.