Skip to content
Back to skills

Init

ASecurity

Enable the AI-native SDLC in the current repository - creates sdlc.config.json, the CLAUDE.md SDLC section, REVIEW.md and docs/sdlc/. Use when the user asks to set up, enable or install the SDLC workflow in a project.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 13, 2026
ai-agentsgoswiftgit

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned October 13, 2026

npx -y skills add Sennjen/claude-sdlc --skill init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Init?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sennjen-init/badge)](https://www.skillsdirectory.com/skills/sennjen-init)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: init
description: Enable the AI-native SDLC in the current repository - creates sdlc.config.json, the CLAUDE.md SDLC section, REVIEW.md and docs/sdlc/. Use when the user asks to set up, enable or install the SDLC workflow in a project.
disable-model-invocation: true
---

# Enable the SDLC in this repository

The plugin's hooks stay inert until `sdlc.config.json` exists at the repo root, so write
that file **last** (after it exists, CLAUDE.md and REVIEW.md become protected paths).

1. **Detect the verification commands.** Inspect `package.json` scripts, `Makefile`,
   `pyproject.toml`, `build.gradle`, `Package.swift`, `Cargo.toml`, CI workflows. Find the
   single commands for test, lint/format check, type check and build. Prefer fast,
   non-interactive, non-watch variants (e.g. `npm test -- --watch=false`, `CI=1`).
   Show the list to the user and confirm it before continuing.
2. **CLAUDE.md.** Merge the section from [claude-md-snippet.md](claude-md-snippet.md) into
   the repo-root `CLAUDE.md` (create it if missing, keep existing content). Fill in the real
   commands. Keep the whole file under roughly one page: commands, conventions,
   architecture, common mistakes. If an architecture overview is missing, add 3-6 lines.
3. **REVIEW.md.** If absent, create it from [review-template.md](review-template.md) and
   adapt the categories to the stack (for example add accessibility for UI apps).
4. **Git hygiene.** Add `.sdlc/` to `.gitignore` (local session state, audit log). The
   `docs/sdlc/**` artifacts, including `approvals.json`, **are** committed: they are the
   audit trail.
5. **Config (last).** Write `sdlc.config.json` from
   [config-template.json](config-template.json) with the confirmed `verify` commands.
   Adjust `test_paths` and `gated_commands` to the stack: add its own release and deploy
   commands, and remove entries that do not apply.
6. **Report to the user** in a short summary:
   - what was created;
   - the user-only chat commands: `sdlc approve intent|spec|plan`, `sdlc skip spec <reason>`,
     `sdlc trivial [reason|off]`, `sdlc unlock tests`, `sdlc feature <slug>`, `sdlc done`,
     `sdlc status`;
   - recommended repo settings outside Claude: branch protection with required human
     review, CODEOWNERS for critical paths, Claude PR review (the managed Code Review
     service or `anthropics/claude-code-action` driven by REVIEW.md);
   - that they should commit the new files.

Files in this skill

  • SKILL.md2.4 KB
  • claude-md-snippet.md1.1 KB
  • config-template.json1.1 KB
  • review-template.md1.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.