spec-builder

Solid

Build a complete BA specification set (13-section structure under docs/specs/) for any project from raw input - an idea, meeting notes, a transcript, an existing PRD, or legacy docs. Use when the user asks to "build specs", "tạo specs", "viết tài liệu phân tích yêu cầu", "chuẩn hóa tài liệu BA", or wants requirement docs scaffolded for a new or existing project.

AI & Automation 5 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Spec builder Produces the requirements contract for a project: thirteen linked sections under `docs/specs/`, traceable from user story to feasibility row, with no invented requirements in them. **The thirteen sections are real files, not prose to retype.** They live in `assets/specs/` and are installed by `scripts/scaffold.py` with their headings, tables, column headers, Mermaid scaffolds, and inline authoring notes intact. Your job is the content and the judgment - the elicitation, the FR list, the priorities, the security posture, the feasibility call. Do not regenerate the shape. ## The rule that governs everything **Never invent a requirement.** Anything not stated by a stakeholder and not clearly implied by the source material goes to `11-assumptions-constraints.md` as an assumption (AS-nn) or an open issue (OI-nn), with an owner, and is flagged to the user in the final summary. A missing requirement stalls and gets asked about. A plausible invented one gets estimated, built, and discovered in UAT - every document downstream treats it as settled. It is the most expensive error available here, and the one a language model is most prone to. ## Procedure **1. Elicit.** [`reference/elicitation.md`](reference/elicitation.md). Establish the system name and one-line purpose, the problem, the candidate feature list, the roles, the known constraints, and the output language - from whatever the user brought (a line, a transcript, a PRD, a codebase). Ask only what cannot b...

Details

Author
nguyenhx2
Repository
nguyenhx2/agent-harness-bootstrap
Created
1 weeks ago
Last Updated
4 days ago
Language
HTML
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

spec

Define requirements before planning. Use when starting a new feature, when requirements are ambiguous, or when the user says 'write a spec' or 'define requirements'.

14 Updated 1 weeks ago
domengabrovsek
AI & Automation Listed

spec-interviewer

Turn a vague software idea into a complete, build-ready specification set through a deep structured interview, then hand it to an AI coding agent. Use this whenever someone describes an app, product, system, or feature they want to build but hasn't nailed down the details — including phrasings like "I want to build X", "help me plan an app", "I have an idea for a system", "help me think through the features", "write a PRD/spec/requirements doc", or when they hand over a rough one-paragraph description and expect something buildable back. Also use it to extend an existing spec set with new modules, or to audit a spec that a coding agent keeps misinterpreting. The skill interviews module by module (roles, flows, rules, data, states, contracts, edge cases, UI), pushes back on gaps and scope creep, and emits numbered module specs plus a foundations doc, decision log, and progress tracker written specifically so Claude Code can build from them without guessing.

0 Updated today
chowjustin
AI & Automation Listed

spec-writer

Generate structured software specifications for features, bug fixes, and products. Use when the user wants to create a spec, PRD, feature brief, requirements document, or when starting any new implementation that needs a specification first. Invoke via /spec-writer or when the user says "write a spec", "spec this out", "create a spec", "I need a spec for...", or describes a feature they want to build. Produces adaptive-complexity specs with Job Stories, Gherkin acceptance criteria, and three-tier boundaries. Output is a markdown file ready for agent execution or human review.

1 Updated yesterday
jaydenluckertjes-ai