ai-dlc-skills

Plugin ai-dlc-skills from marketplace ai-dlc in queen-of-code/AI-DLC. Commands read from the repo's manifest — yesterday.

Skills (33)

• agent-devops-review

  DevOps review pass for PRs — CI/CD, containers, workflows, rollout, rollback, monitoring vs Tech Spec. Used by the /review orchestrator for the DevOps dimension.

• agent-explorer

  Maps a codebase or directory structure and returns a structural summary. Identifies key entry points, dependencies, patterns, and areas of complexity without making changes.

• agent-grounding-reviewer

  The skeptic. Reviews a feature spec against the project's actual technical context and existing features. Flags contradictions, impossible claims, and overlaps with severity (blocking or advisory). Does not rewrite the spec.

• agent-issue-tracker-setup

  Onboards AIDLC issue-tracker choice for a consumer repo: fills AGENTS.md Issue tracker (AIDLC) table, checklists for GitHub vs Linear vs Jira paths, and links to ISSUE-TRACKER-PORTABILITY docs. Does not run external APIs; guides humans through wiring.

• agent-learn

  Captures learnings after a feature or incident completes. Updates PROJECT.md, writes or updates ADRs, adds retrospective notes to Tech Specs, and updates repo documentation so future agents start with current context.

• agent-monitor

  Watches a defined condition on a schedule or continuous basis and emits a structured event record when the condition triggers. Used for health checks, metric thresholds, and scheduled audits.

• agent-planner

  Breaks a task or feature into a phased, ordered implementation plan with clear dependencies, success criteria per step, and a recommended agent composition for execution.

• agent-product-manager

  Writes feature spec drafts using the product template. Takes a research brief and seed blurb as input. Outputs a structured spec to the scratchpad and writes unanswerable questions to pm_questions for the orchestrator to surface.

• agent-product-marketer

  Reviews a feature spec draft from the customer and market perspective. Adds or refines user impact statements, product positioning, and competitive context. Does not rewrite the spec — augments and challenges it.

• agent-researcher

  Explores a codebase, documentation set, brain-mcp collection, or external sources to answer a specific question. When used in the Plan phase, produces a structured research brief for feature spec writing. Returns structured findings with source references and a confidence level.

• agent-reviewer

  Review Orchestrator. Runs CI checks, traces implementation against Tech Spec sections, and generates a structured review report for human sign-off before Validate.

• agent-security-review

  Lightweight security review pass for PRs — secrets, auth/access, dependencies, web/data safety, config. Used by the /review orchestrator for the Security dimension.

• agent-spec-clarity-reviewer

  Reviews a Product Spec for internal contradictions, undefined terms, untestable or unmapped success criteria, missing roles and unhappy paths, and gaps around existing data and work in flight. Applies the Plan exit test (two readers would build the same thing). Does not rewrite the spec.

• agent-synthesizer

  Combines outputs from multiple agents or sources into a single coherent result. Resolves conflicts, eliminates duplication, and produces a merged structured output with a clear provenance trail.

• agent-writer

  Produces a document, spec, or structured text output given a clear brief. Covers technical docs, product specs, ADRs, incident summaries, READMEs, and similar structured writing.

• architecture

  Apply software architecture best practices and design patterns. Use when designing systems, refactoring code, making architectural decisions, or reviewing code structure.

• backend-saas

  SaaS backend development patterns including API design, multi-tenancy, authentication, and scalability. Use when building backend services, APIs, SaaS infrastructure, or designing system architecture.

• blog-writing

  Write blog posts in Melissa Benua's voice and style, saved to external-brain/blog-posts. Use when the user wants to write, draft, brainstorm, or edit a blog post, article, or written content for publication.

• design

  AIDLC Design phase — Tech Spec on the Feature work item (default), review passes, human gate before /build. Requires an approved Product Spec (run /plan first or confirm approval in-thread).

• frontend-web

  Modern web development patterns for React, Vue, and vanilla JS including component architecture, state management, and performance. Use when building web UIs, optimizing frontend performance, or implementing accessibility.

• gdoc-to-markdown

  Download Google Docs as markdown files to external-brain folder. Use when the user provides a Google Doc URL and wants to save it locally, archive documentation, or import Google Docs content.

• git-workflow

  Git workflow standards including commit messages, branch management, and success criteria. Use when committing code, creating branches, or preparing changes for review.

• greeting

  Personal greeting preference that addresses the user appropriately at the start of conversations. This skill applies automatically to all interactions.

• learn

  AIDLC Learn orchestrator. Run after Validate phase PASS — ADRs, docs, retrospective notes. Not combined with /ship in headless automation.

• mobile-apple

  iOS and macOS development patterns using Swift, SwiftUI, and UIKit including app architecture, data persistence, and platform conventions. Use when building Apple platform apps or following Human Interface Guidelines.

• plan

  AIDLC Plan phase — Product Spec on the Feature work item (default), conversation-first, human approval. Different owner may run /design for Tech Spec next. Not for quick bugfixes.

• report-bug

  Bug triage and structured report orchestrator — collects environment, reproduction steps, exact errors, observability evidence; conversation-first; never assumes.

• review

  AIDLC Test gate + Review — six review passes (spec, tests, DevOps, UI via Chrome DevTools MCP, security, architectural soundness) plus an every-PR literal-match check; post PR comments; hand off to /build.

• ship

  AIDLC Validate phase orchestrator (/ship). Scorecard vs Product Spec, deploy gates, UI validation when applicable. Learn is separate — run /learn after PASS.

• spec-management

  Create, organize, and maintain feature specifications following standardized templates. Use when creating specs, updating documentation, planning features, or organizing project documentation.

• testing

  Apply comprehensive testing best practices including unit, integration, and e2e tests. Use when writing tests, reviewing test coverage, designing testable code, or setting up test infrastructure.

• validate-deployed

  Validate a PR's change on a deployed copy before merge, against its spec — numbered checks written first, the deployed commit confirmed, each check exercised in the browser, API or a script, a screenshot per browser check, observability for the deploy window, and one PR comment with the results tabl

• work-tracking

  Structure work using parent-feature and child-work-item hierarchy compatible with Linear and GitHub. Use when planning features, breaking down work, creating issues, or organizing tasks.

Similar plugins