telivityai/haip/haip-spec-writer

Claude Code and agent skill by telivityai/haip

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use this skill whenever writing or revising a module specification for HAIP. Trigger on "write spec for", "spec out module", "define module", or whenever a phase from HAIP_BUILD_PLAN.md needs detailed specification before going to Claude Code. Every HAIP module must go through this template before build.

Install

npx vskill@latest install telivityai/haip/haip-spec-writer

SKILL.md

HAIP Module Spec Writer

When to Use

  • Before any Phase goes to Claude Code
  • When Dušan approves a new module or feature
  • When domain research reveals a module needs redesign

Spec Template

yaml
module:
name: [Module Name]
phase: [Phase number from build plan]
version: 0.1.0
status: DRAFT | REVIEW | APPROVED
purpose: |
[What this module does and why it exists]
domain_knowledge_source: |
[Which KB sections this module draws from]
inputs:
- name: [input name]
type: [TypeScript type]
required: true/false
description: [what this is]
outputs:
- name: [output name]
type: [TypeScript type]
description: [what this returns]
api_endpoints:
- method: GET/POST/PUT/DELETE
path: /api/v1/[resource]
description: [what it does]
auth: required/optional
request_body: [schema reference]
response: [schema reference]
database_tables:
- name: [table name]
columns:
- name: [column]
type: [pg type]
nullable: true/false
description: [what this stores]
events_emitted:
- name: [event.name]
payload: [TypeScript type]
description: [when this fires]
dependencies:
- [other HAIP modules this depends on]
compliance_requirements:
- [PCI/GDPR/tax/registration requirements for this module]
acceptance_criteria:
- [specific, testable criteria]
open_questions:
- [anything the KB doesn't answer]

Rules

  1. Every field in the template must be filled or explicitly marked N/A
  2. Domain knowledge MUST reference specific KB sections — no invented logic
  3. Open questions must be researched before spec is marked APPROVED
  4. Dušan reviews and approves before handoff to Claude Code

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
50
Repository forks
31
7-day trend score
25

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/telivityai/haip/haip-spec-writer/badge)](https://verified-skill.com/skills/telivityai/haip/haip-spec-writer)

Something wrong with this skill or its page? Tell us.