How this skill is triggered — by the user, by Claude, or both
Slash command
/operant:sdlc-skillThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- #core -->
A structured software development lifecycle where specifications drive implementation. Human writes intent; Claude produces design documents, implementation specs, code, and tests—with review gates at each phase.
Intent & Constraints (human)
↓
High-Level Design (Claude) ←→ Human Review
↓
ADR-Lite (Claude) ←→ Human Review
↓
Revised HLD (Claude)
↓
Executable Implementation Spec (Claude) ←→ Human Review
↓
Code Generation (Claude)
↓
Validation Tests (Claude)
Owner: Human
Output: docs/intent-and-constraints.md
Human provides:
Owner: Claude
Input: Intent and constraints document
Output: docs/high-level-design.md
Template: See hld-template.md
Generate HLD covering:
Wait for human review and agreement before proceeding.
Owner: Claude
Input: Approved HLD + human feedback
Output: docs/adr-lite.md
Template: See adr-template.md
For each significant decision, document:
Each ADR entry must explicitly reference:
Wait for human review and agreement before proceeding.
Owner: Claude
Input: Approved ADR-Lite
Output: Updated docs/high-level-design.md
Revise HLD to:
Owner: Claude
Input: Revised HLD + ADR-Lite
Output: docs/implementation-spec.md
Template: See eis-template.md
Specify implementation details:
Wait for human review and agreement before proceeding.
Owner: Claude
Input: Approved EIS
Output: Source code in src/
Implement code that:
Owner: Claude
Input: Implementation + Intent document
Output: Tests in tests/
Generate comprehensive tests:
Tests should trace back to original intents and constraints.
Never proceed to the next phase without explicit human approval. At each gate:
When user provides existing artifacts and wants to continue from a specific phase:
Determine which phase to start from based on what artifacts exist:
Before generating the next artifact, review provided documents for:
If gaps or inconsistencies found:
"I reviewed [artifact]. Before proceeding to [next phase], I noticed:
- [Gap or inconsistency]
Would you like me to address this first, or proceed with assumptions?"
When entering mid-workflow, explicitly map existing artifacts:
After assessment, continue with standard phase sequence and review gates.
project/
├── docs/
│ ├── intent-and-constraints.md
│ ├── high-level-design.md
│ ├── adr-lite.md
│ └── implementation-spec.md
├── src/
│ └── [implementation files]
└── tests/
└── [test files]
The pipeline hooks automatically detect when you write SDLC artifacts and trigger review calls. After writing each artifact:
Use /status to check the current pipeline state if uncertain about where things stand.
npx claudepluginhub esxr/operant --plugin operantProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.