agentleFS
fapariciorfaparicior/sdlc-skills/skills/core/sdlc-guide/SKILL.md

sdlc-guide

Skill2 starsChanged 7 days agoMITView on GitHub

Wayfinder and router skill for the SDLC workflow. LOAD THIS SKILL when user mentions: what skill should I use, sdlc guide, how do I start, help with sdlc, what is the next step, or ask-sdlc.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before ending your turn, verify every item below with concrete evidence (not just a checkmark).

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PROTOCOL: SDLC-GUIDE (EXECUTION LEVEL 3)

<state_machine> CURRENT_STEP -> REQUIRED_TOOL -> REQUIRED_OUTPUT -> MANDATORY_HALT Step 1: Classify Goal -> match user intent against Flow Router (Categories A-F)-> Recommended /skill-name command + rationale -> 🛑 HALT TURN (Or read target SKILL.md if executing) </state_machine>

<execution_invariants>

  1. WORKFLOW IMMUTABILITY: You may reason freely INSIDE Step 1 to understand the user's project stage and goal, but the routing contract is fixed (workflow structure = immutable | step reasoning = flexible).
  2. ROUTER-ONLY INVARIANT: sdlc-guide is a wayfinder and router skill. Never improvise or execute a downstream workflow (such as drafting an ADR, flow doc, proposal, or entity lifecycle) from memory inside sdlc-guide.
  3. DELEGATION LOCK: If the user wants you to execute the recommended skill immediately, you MUST call read_file on that skill's SKILL.md and follow its <state_machine> and <output_contract>.
  4. ESCAPE HATCH: If the user's goal does not fit any branch in the Flow Router, do not silently improvise and do not force-fit: declare the deviation in one line and ask. </execution_invariants>

<output_contract>

  • OUTPUT_TYPE: Exact skill recommendation (/skill-name) mapped from the Flow Router tree (A through F) with a brief explanation of why it fits the user's current stage.
  • ESCAPE_HATCH: If the request spans multiple stages, list the ordered sequence of /skill-name commands and ask the user which stage to start with. </output_contract>

SDLC Skills Guide & Wayfinder

I help you choose the right skill for your current task within the Spec-Driven, DDD & TDD Software Development Life Cycle.

🧭 Flow Router

What is your immediate goal?
│
├── 🟢 A. I'm starting a brand new product / initiative from scratch
│   ├── Want an 8-step product vision & MVP canvas?   ──> /inception-workshop
│   ├── Want to break down stories & release waves?   ──> /user-story-mapping
│   └── Want a formal Product Requirements Document?  ──> /prd-workshop
│
├── 🔵 B. I have user stories/journeys and need technical specifications
│   ├── End-to-end user journeys & Mermaid flows      ──> /create-flow-documentation
│   ├── Slicing journeys into vertical feature specs  ──> /create-features
│   └── Domain model (Entities, VOs, Rules, Invariants) ─> /create-entity-lifecycle
│
├── 🟣 C. My specs and domain models are ready, time to code
│   ├── Scaffold a new Bounded Context package        ──> /create-module
│   └── Implement feature step-by-step with TDD/DDD   ──> /implement-flow
│
├── 🟠 D. I need to modify an existing, already-documented flow
│   ├── Triage tier (Light / Standard / Full)         ──> /modify-flow
│   └── Brownfield/Legacy code needs specs extracted   ──> /reverse-engineer-domain
│
├── 🏛️ E. I need to make or evolve an architectural decision
│   ├── Record a new Architectural Decision Record    ──> /adr-create
│   ├── Amend an existing ADR non-destructively       ──> /adr-amend
│   ├── Benchmark technology stack & 2026 standards   ──> /adr-review-alternatives
│   └── Score ADR quality and compliance              ──> /adr-validate
│
└── 🔍 F. I need to explore the system or audit documentation health
    ├── Query flows, business rules, or events        ──> /explore-domain
    ├── Check if code has drifted from living docs     ──> /audit-docs
    └── Audit and maintain agent instructions/rules   ──> /agents-maintainer

How to interact

Tell me what you are working on or what stage of development you are in, and I will recommend the exact skill command and parameters to invoke.


<self_validation_gate> Before ending your turn, verify every item below with concrete evidence (not just a checkmark). If any item cannot be cited with real evidence from this turn, DO NOT produce your final response — fix the violation first:

  • Router Discipline Evidence: State the matched Flow Router branch (A–F) and recommended /skill-name command: <branch -> /skill>
  • Delegation Lock Evidence (if executing): Exact target skills/<category>/<skill>/SKILL.md path passed to read_file before executing any downstream step: <path or Router-Only> </self_validation_gate>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.