- Home
- Skills
- Business & Operations
- Praxis — SDLC Expert Team
Works with the AI Agents you already use
Praxis — SDLC Expert Team
13 SDLC expert skills (architect, developer, QA, DevOps, security, UX, data, ML…) plus a skill factory and memory ledger.
$9
Praxis — SDLC Expert Team
Example session with this skill installed
One idea in, a full delivery plan out
/new-feature Let returning customers save a payment method at checkout and reuse it next time.
- Read your context and instructions
- Compiled the praxis
Result (BA → Product Owner → Architect → Developer → QA → DevOps)
SCOPE (BA) Authenticated customers only; tokenized storage; guests out of scope.
SLICES (PO) 1) Save a card at checkout ⬅ sprint goal 2) Pay with saved card
3) Manage saved methods. DoD: behind a flag, tests green, audit log live.
DESIGN (Arch) ADR-0007 tokens only → SAQ-A. Top risk: IDOR on the pay path.
BUILD (Dev) Migration → Stripe.js tokenize → owner-scoped POST /payment-methods.
TESTS (QA) User A can't charge user B's card (404) · expired card · duplicate save.
RELEASE (DevOps) Feature flag, 5% canary → 100%, alert on charge-error spike,
rollback = flag off (additive migration).
OPEN QUESTIONS Max saved methods per account? Expired cards: prune or prompt?
Six experts, one consolidated plan — with the open questions surfaced instead of guessed.
Connects securely to your tools. The creator never sees your data.
About this skill
Praxis turns Claude Code into a full software-delivery team. Each skill is a role expert that applies best practices the same way, on every project.
WHAT'S INCLUDED (31 skills)
- 13 SDLC experts: Business Analyst, Product Owner, Software Architect,
Developer, QA Engineer, DevOps Engineer, Security Engineer, Cybersecurity Architect, UX/UI Engineer, Frontend Architect, Frontend Engineer, Data Engineer, ML/AI Engineer
- skill-creator: the meta-skill for scaffolding, reviewing, tiering and
validating new SKILL.md skills
- skill-learner: captures your team's conventions as durable skill knowledge
- memory: a versioned ledger of plans, decisions and implementations
(pending → accepted / rejected / rolled-back)
- validation-orchestrator, docs and diagram utilities
- StartupOS: 12 startup-strategy personas (CEO, CTO, VC partner, market
analyst, GTM, financial analyst…) for validating a business idea before you build it
Who it's for
Developers and teams who want Claude to write requirements, design architectures, review code, plan tests and pipelines, and threat-model features with consistent, senior-level rigor.
How to use
Unzip into .claude/skills/ (project) or ~/.claude/skills/ (user-wide). Claude Code discovers the skills automatically. Describe your task ("design an ADR for…", "write test cases for…") or ask for a role by name.
Every skill is self-contained (shared references are bundled), passes a deterministic structure validator, and contains no secrets. Its helper scripts only use Python's standard library and never install packages.
Does not generate UI wireframes, code, or market research. Focuses exclusively on requirements, process logic, and stakeholder artifacts.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Requires