ai-dlc

Plugin ai-dlc from marketplace ai-dlc-agent-workflow in rafsanulhasan/ai-dlc-agent-workflow-plugin. Commands read from the repo's manifest — 19 days ago.

Skills (73)

• agent-invocation

  Authoritative skill for spawning or invoking another agent with proper context. Use PROACTIVELY before any agent calls another agent — covers Claude `Agent(...)` / `SendMessage` and Copilot/VS Code `agent` tool invocation forms, routing rules to orchestrator / product-manager / agent-manager / resea

• agent-management

  Creates, updates, and deprecates agent definitions for both Claude Code (.claude/agents/*.md) and GitHub Copilot/VS Code (.github/agents/*.agent.md). Invoked exclusively by the agent-manager agent.

• ai-dlc

  AI-DLC lifecycle router and operating model. Defines the full AI-DLC lifecycle — idea to release through every gate (Plan → G1 → Architect & Design → G2 → Breakdown → G3 → Build · Test · Review → G4 → Release) — the default for feature work, plus eight named lifecycles that are its segments (PDLC, A

• architecture-design

  Structured architectural design skill for the project. Use when translating requirements into architectural decisions, producing component designs, or documenting architectural trade-offs. Invoked by the software-architect agent to apply a consistent, systematic design process.

• architecture-narrative

  Turn an architecture solution into a story stakeholders can follow — business problem first, then constraints and trade-offs, then the proposed design, ADRs and risks. Use when presenting, documenting or reviewing an architecture for product owners, business stakeholders or review boards, or when so

• architecture-review

  Structured architectural review skill for the project. Use when reviewing implemented code for architectural integrity, design flaws, convention compliance, and long-term risk, or when asked to scan a codebase or area for architectural improvement — finding shallow modules, leaky seams and other dee

• bunit-blazor-testing

  Comprehensive guidance for writing Blazor component tests using bUnit with TUnit as the test runner. Covers in-memory rendering, component parameters, cascading values, service mocking, event testing, semantic HTML assertions, and snapshot testing.

• cache-keepalive-configure

  Shows or changes keep-alive's settings in .ai-dlc/cache-keepalive.json (Claude Code only). With no arguments it lists each value, its source and any problem; with plain words it previews the change and writes it after you confirm.

• cache-keepalive-install

  Creates .ai-dlc/cache-keepalive.json with every key at its default, and its schema, on first use; an existing file is left alone (use /ai-dlc:cache-keepalive-merge). Claude Code only.

• cache-keepalive-merge

  Brings .ai-dlc/cache-keepalive.json up to date after a plugin upgrade, or repairs it (Claude Code only). It adds new keys, rewrites null and legacy values to their defaults, removes retired keys and keeps every value set; without a file, use /ai-dlc:cache-keepalive-install.

• cache-keepalive

  Pings the prompt cache now, or sets how long keep-alive keeps it warm while background tasks run, on the 1h track, the 5m track or both (Claude Code only). /ai-dlc:cache-keepalive [<n>m|<n>h|<n>d|clear] [--track 1h|5m|both] [--session|--machine].

• command-management

  Create, modify, and delete GitHub Copilot prompt files (.github/prompts/*.prompt.md) and Claude command files (.claude/commands/*.md) safely using a discovery-first, non-destructive workflow. Invoked by agent-manager whenever a command or prompt needs to be created, modified, or deleted.

• configure-auto-handoff

  Shows and changes the automatic session handoff's settings (Claude Code only) in the repository's .ai-dlc/auto-handoff.json, with the source of each value, and checks whether this Claude Code can rename sessions.

• csharp-architecture-testing

  Comprehensive guidance for writing C# architecture tests using NetArchTest.Rules, TUnit, and TUnit.Assertions.Should to enforce layer dependencies, namespace rules, and naming conventions

• csharp-integration-testing

  Comprehensive guidance for writing C# integration tests using TUnit, TestWebApplicationFactory, Testcontainers, Bogus, and TUnit.Assertions.Should — real infrastructure, no mocks of your own code

• csharp-mutation-testing

  Runs and interprets Stryker.NET mutation testing for C# projects — installing the tool, configuring stryker-config.json, running full, incremental (--since) and baseline runs, and triaging surviving mutants into real test gaps vs equivalent mutants. The sqa-engineer's exclusive quality gate in FDLC,

• csharp-unit-testing

  Comprehensive guidance for writing C# unit tests using TUnit, TUnit.Mocks, Bogus, and TUnit.Assertions.Should with project conventions

• design-test-cases

  Structured test case design skill for software projects. Takes an implementation (and acceptance criteria if available) and produces a complete test plan specifying what to test, how, and why — ready to hand off to the write-tests skill. Invoked by the sqa-engineer agent before any test code is writ

• docs-rules

  Installs the AI-DLC documentation rule (docs-status) into the current repository, for every stack. The rule binds every agent in every lifecycle and workflow: who writes documentation, what counts as documentation, how other agents ask for a docs update, and how the status markers are worked out; it

• dotnet-rules

  Installs the AI-DLC .NET rules into the current repository: C# coding style, the GlobalUsings convention and the dotnet test / dotnet stryker testing gates, as Claude rules (.claude/rules) with identical GitHub Copilot instruction twins (.github/instructions). Called by init when it detects a .NET p

• dotnet-test-gate

  Installs the AI-DLC .NET test gate into the current repository: a Claude Code Stop hook and a GitHub Copilot agentStop hook that block the agent from finishing while `dotnet test` fails after runtime changes. Called by init when it detects a .NET project; run it directly to add, repair or remove the

• fix-bug

  Structured bug investigation workflow for software projects. Use for root-cause analysis followed by a minimal targeted fix, including hard, intermittent or flaky bugs and performance regressions: build a red-capable feedback loop, reproduce and minimise, test ranked hypotheses, then fix at the narr

• github-cd-automation

  Structured workflow for designing GitHub Actions continuous deployment for .NET and JavaScript/TypeScript projects. Covers release workflows triggered by tags or manual dispatch, environments and environment secrets, approval gates, package deployment (NuGet to nuget.org; npm with provenance and OID

• github-ci-automation

  Structured workflow for designing and maintaining GitHub Actions continuous integration for .NET and JavaScript/TypeScript projects. Covers workflow file structure, push/pull_request triggers, build matrix, caching, stack-specific build/lint/typecheck/test/mutation steps (dotnet build/test/stryker;

• handoff

  Records and verifies every hand-off in an AI-DLC run and keeps its run state. Use before any spawn, loop round or hand-off between agents (AAW included), whenever an agent returns its report, at every gate, and at session start to resume an unfinished run after a crash or lost context. Also use mid-

• harness-sync

  Runs the two-way Claude Code ↔ GitHub Copilot harness sync, `node .claude/scripts/sync-harness.mjs`, so every agent, skill, command ↔ prompt, rule ↔ instruction and hook made or edited on one platform exists on the other. `--check` only reports; `--prefer`, `--only` and `--name` pass through to the

• hook-management

  Create, modify, and delete Claude Code hooks and GitHub Copilot hook integrations safely using a discovery-first, non-destructive workflow.

• implement-feature

  Structured feature implementation workflow for software projects. Use when architecture/system design is ready and code must be implemented safely, from a design, spec or work item, in small verified steps (test-first when failing tests are supplied), without overbuilding: reuse what the repository

• init

  Bootstraps a repository for the AI-DLC agent team: scaffolds AGENTS.md (the orchestrator persona with all its skills, plus the project's gates and workspace folders, free of stack-specific commands), CLAUDE.md (an @AGENTS.md import, the project's build / test / mutation commands and the Claude Code

• k6-docker

  Invoke this skill when the question is **how to run k6 tests via Docker** — for either local development or CI automation. This skill is the execution-infrastructure complement to the k6 scripting skills

• k6-load-testing

  Invoke this skill when the task is to validate that the system sustains its SLOs at **realistic production throughput over time** — including endurance (soak) testing for memory leaks, connection pool exhaustion, and GC pressure.

• k6-performance-testing

  Invoke this skill when the task is to validate that a system meets its SLOs under **normal operating conditions** — expected concurrency and throughput levels.

• k6-stress-testing

  Invoke this skill when the task is to validate system behaviour **beyond normal capacity** — to observe how it degrades and whether it recovers. This skill answers: 'What happens when load exceeds the normal operating point?'

• lens-configure

  Shows the lens settings, each with its value, where it comes from and its env name, or sets or unsets one in .ai-dlc/lens.json (needs the ai-dlc-lens plugin). /ai-dlc:lens-configure [<key> [<value>|--unset]].

• lens-gate

  Lens anomaly detection (blocked runs and steps, gates waiting or rejected, loops out of rounds, failed or stuck agents, failed hand-backs): on|off turns it on or off; bare, it lists them (needs the ai-dlc-lens plugin).

• lens-init

  Writes the lens settings file .ai-dlc/lens.json with every default, and its schema .ai-dlc/lens.schema.json (needs the ai-dlc-lens plugin). An existing file is kept unless --force is given. /ai-dlc:lens-init [--force].

• lens-keepalive

  Shows or hides the lens's Cache keep-alive section (how long keep-alive kept the cache warm per track, what cache reads saved), then reports those figures (needs the ai-dlc-lens plugin; on by default). /ai-dlc:lens-keepalive [on|off].

• lens-kit

  Opens the lens kit pane: the manual checks K1 to K5 of the lens (resize across the dock boundary, Svg animation, pane buttons, transcript cards; K5 superseded: see /ai-dlc:lens-gate) (needs the ai-dlc-lens plugin). /ai-dlc:lens-kit.

• lens

  Opens or brings forward the AI-DLC Lens view, a live view of every run: one panel per workflow, its step charts of agents, and the avatar and hand-off panels (needs the ai-dlc-lens plugin). /ai-dlc:lens.

• manage-memory

  Manages persistent file-based memory for all agents in .claude/agent-memory/<folder>/ (ai-dlc-<agent> for plugin agents), committed with the repository. Supports load, save, refresh, prune, audit, and compress (shrink a memory or instruction file that loads every session, to save input tokens, keepi

• model-metadata

  Installs the AI-DLC model metadata hook into the current repository: .ai-dlc/model-metadata.json with its schema, holding every Anthropic model's prices (input, output, 5-minute and 1-hour cache writes, cache reads, batch, fast mode, long-prompt tier) and limits (context window, max input and output

• node-rules

  Installs the AI-DLC JavaScript / TypeScript rules into the current repository: coding style (strict TypeScript, no any, ESM, naming), module and import boundaries, async and error handling, and the test / Stryker testing gates, as Claude rules (.claude/rules) with identical GitHub Copilot instructio

• node-test-gate

  Installs the AI-DLC JavaScript / TypeScript test gate into the current repository: a Claude Code Stop hook and a GitHub Copilot agentStop hook that block the agent from finishing while the repository's test command fails after runtime changes. Called by init when it detects a Node.js project; run it

• npm-package-deployment

  Structured workflow for publishing JavaScript/TypeScript packages to the npm registry. Covers SemVer with prerelease dist-tags (next, beta) vs latest, package.json metadata (name/scope, exports, types, files, engines, publishConfig), building the publishable output, npm pack dry-run inspection, npm

• nuget-package-deployment

  Structured workflow for publishing NuGet packages to nuget.org. Covers SemVer with preview/prerelease suffixes, dotnet pack, dotnet nuget push, secret-based API key handling, symbol packages (.snupkg), Source Link, package metadata in .csproj, and the difference between stable and preview release fl

• playwright-mcp-ui-testing

  AI-driven browser UI testing using the Playwright MCP server. Guides the sqa-engineer to perform autonomous browser interactions, assertions, and evidence capture through the Playwright MCP tools. Use ONLY when the change involves UI or frontend components.

• plugin-management

  Creates and maintains a plugin that ships the same agents and skills to Claude Code and GitHub Copilot (CLI and VS Code) from one source: the Claude plugin is the source of truth and a zero-dependency build projects it into the Copilot plugin. Covers repository layout, both marketplaces, manifests,

• presentation-authoring

  Authors and maintains PowerPoint (.pptx) decks: reading a deck, editing slide text in place without breaking the layout, building a new deck, rendering slides to images for visual QA, and keeping a deck in sync with its source of truth (for example a team roster or a product's architecture). Use whe

• product-planning

  Product backlog management and release planning skill. Invoked by the product-manager agent to add items, review backlog health, re-prioritize, plan releases, or update item status. Reads and writes docs/backlog/backlog.md as the persistent source of truth.

• request-routing

  The orchestrator's single routing skill. Classifies every incoming request, decides which AI-DLC workflow (lifecycle) each work item runs — the one the user explicitly asked for, otherwise chosen from the ai-dlc lifecycles — or which single agent it is handed to, assigns the agent chain, and picks t

• requirement-analysis

  Structured requirement elicitation for software projects. Use before architecture or implementation when scope is new, vague, or ambiguous, or when a plan, idea or design needs to be grilled and stress-tested. Runs a relentless one-question-at-a-time interview (each question with a recommended answe

• research

  Structured external-knowledge and codebase-exploration research skill for software projects. Invoked by the research-assistant agent to clarify the question, select authoritative sources (context7 for library docs, web search/fetch for general information, Grep/Glob/Read for codebase exploration), t

• review

  Structured code review workflow for software projects. Use to assess branch/PR/file changes, or everything since a given commit, branch or tag, and produce severity-ranked findings on two separate axes: Standards (correctness, documented conventions, coverage, design and code smells) and Spec (does

• rules-management

  Create, modify, delete, and sync Claude rules files (.claude/rules/*.md) and GitHub Copilot instruction files (.github/instructions/*.instructions.md) safely using a discovery-first, non-destructive workflow. Invoked by agent-manager whenever a rules or instructions file lifecycle operation is reque

• security-review

  Security-focused review workflow for software projects. Use for auth, data exposure, input validation, dependency risk, secrets and vulnerability checks on a change, a component, or a reported incident. Produces severity-ranked findings with remediation; P0 findings block release.

• skill-management

  Creates, updates, syncs, and lists skill files (.claude/skills/*/SKILL.md) and (.github/skills/*/SKILL.md) for the AI-DLC multi-agent system, and holds the writing guide and review checklist for any agent-facing document (skills, agent bodies, rules, AGENTS.md, CLAUDE.md). Invoked exclusively by the

• sonarqube-pr-quality-gate

  Structured workflow for enforcing SonarQube quality gate on pull requests for .NET and JavaScript/TypeScript projects. Covers sonar-project.properties configuration, the stack's scanner (SonarScanner for .NET; sonarqube-scan-action with lcov coverage for JS/TS), PR decoration, quality-gate-failure a

• spec-driven-development

  Manages the full lifecycle of a feature specification — from collaborative drafting (after a requirement-analysis session, or by synthesising a spec from requirements already discussed in the conversation, a product brief or an issue without re-interviewing) through agreed test seams and architect/s

• system-design

  Low-level design skill. Use PROACTIVELY to design and review code-level structure (classes, modules, interfaces), select design patterns, apply SOLID and functional constructs, design UI structure (component boundaries, UI patterns), and help software engineers implement design principles in code. A

• task-triage

  The product-manager's task and bug triage skill. Turns a classified request, plan or spec into a work breakdown — tracer-bullet work items with explicit blocking edges, parallel groups, priorities and execution waves — and triages bugs (verification, severity, regression, security escalation, duplic

• terse-output

  Terse response register: answer first, keep every technical fact, drop the filler, at three levels (lite, full, ultra). Use when the user asks for shorter, terser or lower-token answers or types /terse-output, and when a brief asks a spawned agent for a compressed report. Stays on until the user tur

• test-doubles

  Mock, stub, fake, spy or test double policy — the single rule for whether a test may replace part of the system and with what. Use when a test plan lists doubles, before writing any mock, stub, fake, spy, MSW handler, Playwright route or fake clock, when someone asks \"can I mock this?\", and when r

• ts-architecture-testing

  Comprehensive guidance for writing architecture tests in JavaScript/TypeScript projects (Node, TypeScript, plain JavaScript) using dependency-cruiser forbidden and required rules (layer dependencies, no circular dependencies, no orphans, not-to-dev-dependency, restricted imports, folder residency),

• ts-integration-testing

  Comprehensive guidance for writing integration tests in JavaScript/TypeScript projects (Node, TypeScript, plain JavaScript) using Vitest (or Jest when the repository already uses it), Testcontainers for Node for real databases, caches and brokers, supertest or the framework's own in-process request

• ts-mutation-testing

  Runs and interprets StrykerJS mutation testing for JavaScript/TypeScript projects (Node, TypeScript, plain JavaScript): installing @stryker-mutator/core with the vitest-runner or jest-runner, configuring stryker.config.json, running full, incremental and changed-files (--mutate) runs, thresholds and

• ts-playwright-ui-testing
• ts-unit-testing
• tunit-playwright-ui-testing
• workflow
• workspace-folders
• write-adr
• write-documentation
• write-tests

Subagents (15)

• agent-manager

  Single authority for creating, updating, syncing, and deprecating agent definitions across both Claude Code (.claude/agents/*.md) and GitHub Copilot/VS Code (.github/agents/*.agent.md) platforms. Addressed by name as Boris Cherny (default persona name; a name chosen at /ai-dlc:init takes precedence)

• brutal-critique

  Adversarial, read-only critic for every document the AI-DLC team produces — user stories, specs, ADRs, low-level designs, task plans, test plans, READMEs and handoff records. Addressed by name as Linus Torvalds (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as brut

• code-reviewer

  Use this agent to review code after the software-engineer completes a feature, bug fix, or refactor. Addressed by name as Robert C. Martin (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as code-reviewer / reviewer. Invoke PROACTIVELY after software-engineer finishe

• devops-engineer

  Use this agent for CI/CD pipelines, package deployment (NuGet for .NET, npm for JS / TS), GitHub Actions workflows, release automation, and quality-gate-on-PR enforcement. Addressed by name as Gene Kim (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as devops-engine

• documentation-writer

  Use this agent to write and maintain README.md files across the project's repository. Addressed by name as Daniele Procida (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as documentation-writer / technical writer. Invoke whenever a new component lands, an API chang

• orchestrator

  Use this agent as the FIRST point of contact for every human request. Addressed by name as Scott Hanselman (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as orchestrator / coordinator. The orchestrator receives the human's intent, clarifies it, classifies it, has p

• presentation-manager

  Use this agent to create, update and review PowerPoint (.pptx) presentations, and to keep existing decks in sync with the project — for example after the agent team, architecture, roadmap or release changes. Addressed by name as Nancy Duarte (default persona name; a name chosen at /ai-dlc:init takes

• product-manager

  Use this agent to break requests into work items and to plan, prioritize, and coordinate the delivery of features, bug fixes, security fixes, and releases for the current project. Addressed by name as James Montemagno (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role

• product-owner

  Use this agent as the owner of the AI-DLC Plan and Release phases. Addressed by name as James Montemagno (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as product-owner / PO. It turns the human's intent into a product brief (vision, outcomes, features, use cases),

• requirement-analyst

  Use this agent to analyze requirements through an interactive Q&A session with the user before any system design or implementation begins. Addressed by name as James Montemagno (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as requirement-analyst / analyst. Invoke

• research-assistant

  Use PROACTIVELY when any agent needs external knowledge — library/API/SDK documentation, current framework behavior, version-migration information, web information, comparisons of options, validation of assumptions before design or implementation, or non-trivial codebase-wide exploration. Addressed

• software-architect

  Use this agent when designing systems, reviewing architectures, or validating technical decisions. Addressed by name as Mark Richards (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as software-architect / architect. Invoke PROACTIVELY in the following scenarios:\\n

• software-engineer

  Use this agent to implement features, fix bugs, and refactor code after architecture and system design are complete. Addressed by name as David Fowler (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as software-engineer / developer. Invoke PROACTIVELY after the soft

• sqa-engineer

  Use this agent to design test cases and write the test suite for any component after the software-engineer finishes implementation. Addressed by name as Kent Beck (default persona name; a name chosen at /ai-dlc:init takes precedence) or by role as sqa-engineer / QA. Invoke PROACTIVELY after software

• system-engineer

  Use this agent when low-level system design decisions need to be made or validated, design patterns need to be selected or reviewed, SOLID/DRY/YAGNI/KISS principles need to be enforced, functional programming constructs (monads, discriminated unions) need to be designed or evaluated, UI design is ne

Similar plugins