claude

claude-sdlc-team

Agentic SDLC team (requirements → design → implementation → testing → review → security → release → docs) with per-feature auto-merge to development, sprint close promoting to staging for UAT, a separate production release to main with semantic versioning + tagging, CI/CD pipeline scan-and-fix, and optional per-project Jira-Scrum Notion sync — per-project hub pages, backlog, sprint planning (Definition of Ready), and a scrum-master skill. All stage promotions are PR/MR-based with non-protected branch cleanup. A Playwright E2E layer records a per-feature review video — with a visible mouse cursor, never screenshots — that gates the merge to development.

2 on GitHubby Danniel Liborv1.9.0MITupdated 19 days ago
/

Plugin claude-sdlc-team from marketplace danniel-claude-plugins in danniel-isiah-libor/danniel-claude-plugins. Commands read from the repo's manifest — 18 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (26)

  • capability-discovery

    Inventory the capabilities already available in the current session so the SDLC team can reuse them. Use at pipeline start (Phase 0) to discover project-local agents and skills (.claude/agents, .claude/skills), agents/skills from other installed plugins, and connected MCP servers, plus the repo's CL

  • cicd-failure-diagnosis

    Diagnose a failing CI/CD run — retrieve the failed-step logs, classify the root cause (config | code/test | infra/transient), and route or fix. Use when a CI run is red, e.g. by the ci-doctor agent and the /sdlc-fix-ci loop. Forge-aware; reuses the cicd-pipeline-audit fix catalog.

  • cicd-pipeline-audit

    Audit CI/CD pipeline config (CI workflows + Dockerfiles) for security, correctness, reliability/cost, and plugin-convention issues. Use when reviewing or generating pipeline config — by the pipeline-reviewer (Phase 4) and the release-engineer (Phase 5). Prefers real linters, falls back to a checklis

  • clean-code-standards

    Apply pragmatic clean-code standards — DRY, YAGNI, KISS, separation of concerns, naming, small functions, low complexity. Use when writing or reviewing code to keep it readable and maintainable. Cited by the implementer, QA, and code reviewer as a shared rubric.

  • database-design

    Design and review relational schemas, MySQL-focused. Use when the design or implementation involves data modeling — tables, keys, relationships, normalization, indexing, constraints, migrations, and query/EXPLAIN optimization. Used by the architect (data model) and implementer (schema/migrations).

  • devops-gcp

    Containerize and ship apps with Docker, CI/CD pipelines that deploy on a MANUAL trigger, and Google Cloud Platform. Use when setting up build/deploy, writing Dockerfiles or CI workflows, or planning a release. Primary skill of the release-engineer.

  • end-to-end-testing

    Drive a running web app end-to-end as a real user (mouse + keyboard) with Playwright and record a screen video — with a visible mouse pointer — for review. Use in the review phase (the e2e-tester agent and /sdlc-e2e) to produce a per-feature recording the user approves before merge. No-ops when ther

  • framework-expertise

    Framework- and architecture-specific implementation guidance. Use when building or reviewing code in a known stack (Laravel, Filament, Vue, React, Next, Electron, Ionic, shadcn, Tailwind) or when choosing between microservice and monolithic architectures. A router — load only the reference file(s) m

  • git-conventions

    Apply Conventional Commits and Conventional Branch naming, the three-tier branch model, the per-task branch workflow, and the promotion policy (every stage merge goes through a PR/MR; merged non-protected branches are deleted, the protected main/staging/development are not). Use when committing, cre

  • notion-sync

    Mirror the SDLC pipeline to a Notion workspace as a Jira-Scrum board — a shared Projects registry plus, per project, a hub page holding its own Tickets and Sprints databases with backlog and active-sprint views, plus sprint-planning Ready sign-off. Use when syncing artifacts/status to Notion (the /s

  • performance-and-cost

    Keep the whole application performant and cost-effective. Use when designing, implementing, or reviewing for latency, throughput, resource use, and cloud cost. Covers N+1 queries, caching, async/queues, payload size, and right-sizing. Used by the architect, implementer, and code-reviewer.

  • project-memory

    Conventions for the repo-local, committed agent-memory store at .claude/agent-memory/. Use whenever reading project memory at the start of an SDLC run, forwarding it to subagents, or persisting a durable project fact. Defines the MEMORY.md index + per-fact file layout, what is worth remembering, and

  • release-management

    Manage versioning and release communication. Use when cutting a release — semantic-versioning decisions, changelog entries, and release notes. Used by the release-engineer.

  • requirements-engineering

    Turn a raw request into clear, testable requirements. Use when writing 01-requirements.md — eliciting user stories, INVEST-quality criteria, Given/When/Then acceptance criteria, scope boundaries, and assumptions. Primary skill of the requirements-analyst.

  • scrum-master

    Agile/Scrum methodology expert — the orchestrator's scrum master. Facilitates the sprint lifecycle: backlog refinement, Definition of Ready/Done, sprint planning, scope discipline, and sprint review/retro. Use when planning or running sprints (the /sdlc-plan and /sdlc-sprint commands and the orchest

  • sdlc-artifacts

    Conventions for SDLC pipeline artifacts and handoffs. Use whenever creating, reading, or updating files under docs/sdlc/<slug>/, writing the 00-manifest.md, or applying the QUESTIONS FOR USER / NO QUESTIONS clarification protocol. Defines the artifact layout, manifest schema, feature slug rules, and

  • sdlc-gates

    Flow-control primitives for the SDLC pipeline — GATE (human approval), LOOP-GUARD (N tries then ask), and PRECONDITION (state guard). Apply whenever presenting an approval gate, running a fix/repair loop, or refusing an action based on sprint state. Used by the orchestrator (skills/sdlc) and the /sd

  • sdlc

    Orchestrate the SDLC pipeline end to end. Use when the user runs /sdlc with a request, or asks to "run the SDLC pipeline", "build this feature properly", or take a feature/fix from requirements through design and implementation. Routes work to the requirements-analyst, solution-architect, and implem

  • software-architecture

    Turn requirements into a technical design. Use when writing 02-design.md — decomposition into components with clear boundaries, interfaces/contracts, data flow, a file-level build sequence, trade-off analysis, and a test strategy outline. Primary skill of the solution-architect.

  • solid-principles

    Apply and review against the five SOLID object-oriented design principles. Use when designing components, writing classes/modules, or reviewing code for maintainability and coupling. Language-neutral guidance with review heuristics for the architect, implementer, and code reviewer.

  • stack-detection

    Detect and adapt to any repository's tech stack and conventions. Use as the FIRST step of every SDLC agent, before doing phase work, to identify language, framework, package manager, test runner, build/lint tooling, and the repo's own conventions (including its CLAUDE.md). Ensures the team follows e

  • technical-writing

    Write clear technical documentation. Use when producing or updating a README, API docs, usage guides, or changelogs. Audience-first structure and conventions. Primary skill of the tech-writer.

  • test-engineering

    Design test cases — UAT (stakeholder-readable acceptance scenarios) and automated tests adapted to the project's stack. Use when planning or writing tests, verifying acceptance criteria, or deciding coverage. Primary skill of the qa-tester; also used by the implementer.

  • threat-modeling

    Design-time security risk analysis. Use when reviewing a design or change for what could go wrong — assets, trust boundaries, attack surface, and STRIDE categories. Used by the security-reviewer and consulted by the architect.

  • ui-ux-design

    Apply modern UI/UX design language. Use when designing or building user interfaces — layout, visual hierarchy, accessibility, responsive/cross-platform (web/mobile/desktop), and Tailwind as a design system. Used by the architect and implementer.

  • vulnerability-scanning

    Find and prevent concrete code-level security vulnerabilities. Use when writing or reviewing code that handles input, auth, data access, files, or external requests. Covers XSS, SQL injection, CSRF, SSRF, IDOR, command injection, insecure deserialization, auth/session flaws, secrets exposure, and de

Slash commands (14)

  • /claude-sdlc-team:sdlc-backlog

    Capture a new requirement into the project's Notion Backlog as a ticket (no sprint, no pipeline run). Non-blocking; no-ops if Notion is disabled.

  • /claude-sdlc-team:sdlc-design

    Run or re-run the Design phase for a feature — dispatches the solution-architect to produce 02-design.md.

  • /claude-sdlc-team:sdlc-docs

    Run the optional Docs phase — dispatches the tech-writer to update README/API docs/changelog and write 06-docs.md.

  • /claude-sdlc-team:sdlc-e2e

    Run the end-to-end test layer on demand — drive the running app as a user via Playwright and record a review video (with a visible mouse pointer, never screenshots) to docs/sdlc/<slug>/e2e-recordings/. No-ops without a web UI; asks before installing Playwright.

  • /claude-sdlc-team:sdlc-fix-ci

    Diagnose a failing CI/CD run and, if the cause is pipeline config, patch + re-run until green (gated). Routes code/test failures to /sdlc-implement; infra failures to a re-run.

  • /claude-sdlc-team:sdlc-implement

    Run or re-run the Implementation phase for a feature — dispatches the implementer to build the approved design with tests and produce 03-implementation.md.

  • /claude-sdlc-team:sdlc-init

    Bootstrap a project — set up the three-tier git branch model (main/staging/development) and optionally enable Notion sync (register the project + ensure the Kanban board).

  • /claude-sdlc-team:sdlc-inspect

    Run the parallel inspection quintet (QA + code review + security + CI/CD pipeline + E2E video) on the current feature's changes and merge findings into one issue list.

  • /claude-sdlc-team:sdlc-plan

    Sprint planning — collaboratively refine each candidate ticket in a Planned sprint to the Definition of Ready (scope, acceptance, type, priority, estimate), write the agreed details to Notion, and mark each Ready. Gates /sdlc-sprint start. Non-blocking; no-ops if Notion is disabled.

  • /claude-sdlc-team:sdlc-release

    Run the production-release step — promote staging → main after UAT, dispatch the release-engineer for versioning + changelog + prod deploy config, tag, and deploy (Gate ④). Refuses while a sprint is Active.

  • /claude-sdlc-team:sdlc-requirements

    Run or re-run the Requirements phase for a feature — dispatches the requirements-analyst to produce 01-requirements.md.

  • /claude-sdlc-team:sdlc-sprint

    Manage Notion sprints like Jira Scrum — create a sprint, move backlog tickets into it, plan it (refine to Ready via /sdlc-plan), start it (commence → active Kanban board; gated on planning), or close it (review/retro + promote the sprint's Done features to staging for UAT). Non-blocking; no-ops if N

  • /claude-sdlc-team:sdlc-status

    Show SDLC progress — prints the manifest(s) under docs/sdlc/ (current phase, gate status, open questions) and the Notion ticket link if enabled.

  • /claude-sdlc-team:sdlc-sync

    Sync the current feature's artifacts and status to Notion (Projects registry + the project's own Tickets/Sprints DBs + doc pages). Idempotent and non-blocking; no-ops if Notion is disabled for the project.

Subagents (11)

  • ci-doctor

    Use to diagnose a single failing CI/CD run. Given the failed-step logs + the repo's pipeline config, classifies the root cause (config | code/test | infra/transient) and, if it's config, prescribes a concrete patch. Diagnoses and prescribes only — never edits, pushes, re-runs, or deploys. <example>

  • code-reviewer

    Use to review an implementation's code quality (part of the parallel inspection phase). Checks bugs, conventions, SOLID/clean-code, performance, and known vulnerability classes; writes 04b-code-review.md with file:line findings. White-box perspective. <example> Context: Implementation done; orchestr

  • e2e-tester

    Use to end-to-end test an implementation by driving the running app as a real user via Playwright and recording a review video (part of the parallel inspection phase). Detects a web UI, emulates mouse/keyboard, writes 04e-e2e.md with the recording path, and no-ops when there's no web UI. Black-box p

  • implementer

    Use to implement an approved design in code with tests (Phase 3 of the SDLC pipeline). Writes the code and tests, runs the build/tests, and produces 03-implementation.md (files changed, decisions, test results). <example> Context: Design approved at Gate 2; orchestrator starts Phase 3. user: "(appro

  • pipeline-reviewer

    Use during Phase 4 inspection to audit the repo's CI/CD pipeline config (CI workflows + Dockerfiles) for security, correctness, reliability/cost, and plugin-convention issues. Reports findings; never fixes or deploys. No-ops cleanly when no pipeline config exists. <example> Context: Phase 4 parallel

  • qa-tester

    Use to QA-test an implementation against its acceptance criteria (part of the parallel inspection phase). Verifies behavior, designs UAT cases, finds edge cases, and writes 04a-qa.md. Black-box/behavioral perspective. <example> Context: Implementation done; orchestrator runs the inspection trio. use

  • release-engineer

    Use to prepare a release after review passes (Phase 5). Authors Docker/CI-CD config with a MANUAL deploy trigger targeting GCP, versions the release, and writes 05-release.md. Nothing outward-facing happens without explicit confirmation. <example> Context: Review passed (Gate 3); the user opts to pr

  • requirements-analyst

    Use to turn a raw feature/fix request into clear, testable requirements at the start of the SDLC pipeline. Produces 01-requirements.md (user stories, Given/When/Then acceptance criteria, scope, assumptions). <example> Context: The orchestrator begins Phase 1 for a new feature. user: "Build password

  • security-reviewer

    Use to security-audit an implementation (part of the parallel inspection phase). Combines design-time threat modeling with code-time vulnerability scanning; writes 04c-security.md. Attacker perspective. <example> Context: Implementation done; orchestrator runs the inspection trio. user: "(02-design.

  • solution-architect

    Use to turn approved requirements into a technical design (Phase 2 of the SDLC pipeline). Produces 02-design.md: components, data model, interfaces, build sequence, trade-offs, and a test strategy. <example> Context: Requirements approved at Gate 1; orchestrator starts Phase 2. user: "(approved 01-r

  • tech-writer

    Use to document a shipped feature (Phase 6). Updates the README/API docs/changelog and writes 06-docs.md. Reader-clarity perspective. <example> Context: Feature built and reviewed; the user opts to document it. user: "(reviewed feature)" assistant: "I'll use the tech-writer agent to update the docs

MCP servers (1)

  • notion

    connects to: https://mcp.notion.com/mcp

Hooks (1)

  • SessionStart

    bash "$CLAUDE_PLUGIN_ROOT/hooks/load-agent-memory.sh"

View source on GitHub

More from danniel-isiah-libor/danniel-claude-plugins

All 3 plugins →

A summonable dream team of senior expert agents — a DevOps engineer (Docker, industry-standard CI/CD with mandatory manual-approval gates and semver tags/releases for UAT & prod, GCP infra), a fullstack developer (SOLID/clean code, security-first, cross-platform UI/UX, database design), a QA engineer (unit, Playwright E2E, VAPT, code review), a security analyst (read-only CVE triage via OSV/NVD with EPSS + CISA KEV, reachability checks, routed fixes), and a technical writer (user guides, how-to/feature docs, FAQs, release notes for clients/stakeholders). Includes focused skills (project-adaptation, gcp-devops, senior-development, qa-testing, git-conventions, documentation) and a /dream-team-review command that routes QA findings to the dev/devops agents and re-verifies. Stack-agnostic; composes with each project's CLAUDE.md, skills, and agents.

6 skills · 1 command · 5 agents

2

An active Obsidian vault steward: the vault-keeper agent maintains your vault to best practices through the Obsidian MCP (CLI or filesystem fallback) — captures and files notes into PARA, builds and refreshes MOC index notes, fixes broken [[links]] and finds orphans, normalizes frontmatter, safely dedupes/renames, and runs the archive lifecycle. Includes three skills — obsidian-vault (the official Obsidian style guide, PARA organization, MCP-aware maintenance workflows, Dataview/Templates), vault-conventions (this vault's own house rules: the folder map, where each incoming note goes, and capture-vs-reference for daily and meeting notes with on-demand promotion), and project-context (the employer-scoped repo ↔ vault bridge: coding sessions read the matching project note's business rules before changing domain logic, stay within that employer's folder plus its daily/meeting captures, and write discoveries back) — plus /vault-checkup (read-only health sweep) and /vault-wire (scaffold and wire a repo's project note) commands. Complements the required official obsidian plugin (by Steph Ango/kepano) — it owns vault stewardship and defers Obsidian authoring syntax (Markdown, Bases, Canvas) to that plugin's skills.

3 skills · 2 commands · 1 agent

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain claude-sdlc-team?

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.

claude & codex plugins3 plugins