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

setup-sdlc

Skill2 starsChanged 6 days agoMITView on GitHub

Interactive onboarding skill to configure a repository for the SDLC workflow. LOAD THIS SKILL when user mentions: setup sdlc, init sdlc, configure sdlc, install sdlc skills, or bootstrap sdlc.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check if the repository is a Monorepo (pnpm/turborepo/npm workspaces) or Single App.

    line 37
  2. Very specific:

    Check for existing ADRs (docs/adr/) and architecture guidelines.

    line 39
  3. Very specific:

    Documentation root: Default is docs/.

    line 43
  4. Very specific:

    ADR directory: Default is docs/adr/.

    line 45
  5. Very specific:

    Product Specifications directory: Default is docs/product/bounded-contexts/.

    line 46
  6. Very specific:

    Working Proposals directory: Default is docs/product/working-on/.

    line 47
  7. Distinctive:

    Create directories if they do not exist:

    line 65
  8. Distinctive:

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

    line 88

≈ “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: SETUP-SDLC (EXECUTION LEVEL 3)

<state_machine> CURRENT_STEP -> REQUIRED_TOOL -> REQUIRED_OUTPUT -> MANDATORY_HALT Step 1: Detect Env -> ls / read_file (workspace layout, existing docs) -> Detected directory defaults -> Continue to Step 2 Step 2: Configure -> ask_question / prompt developer -> Confirmed paths for .sdlc/config.json -> 🛑 HALT TURN (Wait for user answers) Step 3-5: Initialize -> write_file / mkdir / cp guidelines -> .sdlc/config.json + directory tree + guidelines -> END </state_machine>

<execution_invariants>

  1. WORKFLOW IMMUTABILITY: You may reason freely INSIDE each step to inspect the repository's real workspace layout (monorepo vs single-app, existing doc folders, architecture style), but you must execute the onboarding steps in order (workflow structure = immutable | step reasoning = flexible).
  2. INTERACTIVE CONFIRMATION: Confirm the 5 directory paths with the developer before writing .sdlc/config.json (unless the user explicitly requested default/unattended initialization in their prompt).
  3. GUIDELINE COPY RULE: Copy business-rules-vs-invariants.md, flow-documentation-structure.md, and adr-naming-conventions.md into the target guidelinesDir, but NEVER copy traceability.md or execution-protocol.md (they remain in the skills pack).
  4. ESCAPE HATCH: If the repository's structure does not fit the standard SDLC layout, do not silently improvise and do not force-fit: declare the deviation in one line and ask. </execution_invariants>

<output_contract>

  • TARGET_CONFIG: .sdlc/config.json conforming to schemas/sdlc-config.schema.json
  • TARGET_DIRECTORIES: docs/inception/, docs/user-story-mapping/, docs/product/bounded-contexts/, docs/product/guidelines/, docs/product/working-on/active/, docs/product/working-on/grace-period/, docs/adr/ (or user-configured equivalents)
  • ESCAPE_HATCH: If any target directory already exists with files, preserve existing files untouched and report them in the summary. </output_contract>

Configure your repository to use the full Spec-Driven, DDD & TDD Software Development Life Cycle (SDLC).

Workflow

  1. Detect Project Environment:
    • Check if the repository is a Monorepo (pnpm/turborepo/npm workspaces) or Single App.
    • Inspect existing documentation directories (docs/, doc/, etc.).
    • Check for existing ADRs (docs/adr/) and architecture guidelines.
  2. Interactive Configuration: Ask the developer:
    • Documentation root: Default is docs/.
    • Bounded Contexts / Modules location: e.g., packages/modules/ (Monorepo), src/modules/, or apps/.
    • ADR directory: Default is docs/adr/.
    • Product Specifications directory: Default is docs/product/bounded-contexts/.
    • Working Proposals directory: Default is docs/product/working-on/.
  3. Generate Configuration: Save settings to .sdlc/config.json:
    {
      "$schema": "https://raw.githubusercontent.com/faparicior/sdlc-skills/main/schemas/sdlc-config.schema.json",
      "version": "1.0.0",
      "docsRoot": "docs",
      "adrDir": "docs/adr",
      "productDocsDir": "docs/product",
      "modulesDir": "packages/modules",
      "guidelinesDir": "docs/product/guidelines",
      "architectureStyle": "ddd"
    }
  4. Initialize Directory Structure & Guidelines:
    • Create directories if they do not exist:
      • docs/inception/
      • docs/user-story-mapping/
      • docs/product/bounded-contexts/
      • docs/product/guidelines/
      • docs/product/working-on/active/
      • docs/product/working-on/grace-period/
      • docs/adr/
    • Copy canonical guidelines from this skill package into docs/product/guidelines/:
      • business-rules-vs-invariants.md
      • flow-documentation-structure.md
      • adr-naming-conventions.md
    • Do not copy traceability.md: it stays in the skills pack (../guidelines/traceability.md) as the single source of the convention; product docs carry the sections it defines but never link to it.
  5. Confirm Ready: Provide the developer with a summary and suggest the next step:
    • For a brand new project: Run /inception-workshop or /user-story-mapping.
    • For an existing project needing documentation: Run /reverse-engineer-domain.
    • For a general overview: Run /sdlc-guide.

<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:

  • User Confirmation Evidence: Confirm developer approved the 5 paths (or halted at Step 2 waiting for answers): <status>
  • Config & Directories Evidence: Exact .sdlc/config.json path written and list of directories created: <paths>
  • Guideline Copy Evidence: List the 3 guideline files copied to guidelinesDir and confirm traceability.md & execution-protocol.md were excluded: <3 files copied> </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.