textum
Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
About this skill
Textum is an AI agent skill designed to systematize the software development lifecycle for AI coding agents. It breaks down the complex process into distinct, self-contained stages, progressing from Product Requirement Document (PRD) creation and validation, through global context scaffolding, to the generation and execution of individual code stories. The skill enforces 'hard constraints' such as ensuring low-noise outputs to prevent context pollution and maintaining multi-window separation, where each stage's output is independent of previous or future stages. Users leverage Textum to manage AI-driven coding projects with high fidelity and built-in quality assurance. It automates critical checks at various stages (e.g., PRD Check, Scaffold Check, Story Checks), making it invaluable for ensuring consistency, adherence to requirements, and structural integrity of AI-generated code. This structured approach helps in maintaining control and predictability in projects heavily reliant on AI for code generation. By providing a robust framework for an AI agent to navigate the entire development process, Textum significantly enhances the reliability and quality of AI-assisted software delivery. It's particularly useful for translating high-level product requirements into actionable, verifiable code components, mitigating common issues like scope creep or inconsistent outputs from less guided AI agents.
Best use case
The primary use case for Textum is to guide an AI agent through a complete software development lifecycle, from initial product requirements to finalized code stories. This skill benefits developers, product managers, and project leads who utilize AI agents for coding, providing a standardized, quality-controlled process for AI-generated artifacts.
Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
A complete set of validated product requirements, a comprehensive global context scaffold, and executable code stories, all systematically generated, checked, and managed by an AI agent through a defined workflow.
Practical example
Example input
Generate the Product Requirements Document (PRD) for our new user authentication module, covering key user flows.
Example output
PRD for user authentication module generated, outlining flows, data storage, and error handling. Saved to `references/prd-render.md`. Next step: `PRD Check`.
When to use this skill
- When using an AI agent to transform a high-level PRD into actionable coding tasks and executable stories.
- When a structured, multi-stage workflow is essential for AI-driven software development projects.
- When low-noise outputs, clear stage progression, and robust gate checks are critical for AI-generated code.
- When breaking down complex software features into manageable, verifiable stages for an AI agent.
When not to use this skill
- For simple, single-step coding tasks that do not require a full development workflow.
- When rapid prototyping or speed is the sole priority over structured checks and low-noise output.
- When human oversight and manual intervention are preferred at every micro-step rather than automated checks.
- If the project's development process does not align with the PRD→Scaffold→Story paradigm.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/textum/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How textum Compares
| Feature / Agent | textum | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Textum Hard constraints: - Low-noise is non-negotiable (avoid attention/context pollution). - Multi-window: each stage is self-contained; do not narrate upstream/downstream flow. - Output “next step” as a stage name only. Prereq (runtime): - `uv` installed. - Run `uv sync --project .claude/skills/textum/scripts` once (creates `.claude/skills/textum/scripts/.venv`). Supported stages: - PRD Plan → `references/prd-plan.md` - PRD Check → `references/prd-check.md` - PRD Render → `references/prd-render.md` - PRD Slice → `references/prd-slice.md` - Scaffold Plan → `references/scaffold-plan.md` - Scaffold Render → `references/scaffold.md` - Scaffold Check → `references/scaffold-check.md` - Split Plan → `references/split-plan.md` - Split Generate → `references/split.md` - Split Check1 → `references/split-check1.md` - Split Check2 → `references/split-check2.md` - Split Checkout → `references/split-checkout.md` - Story Check → `references/story-check.md` - Story Pack → `references/story-pack.md` - Story Exec → `references/story.md` - Story Full Exec (experimental) → `references/story-full-exec.md` Routing: - CN intent examples: - `PRD Plan`: 需求澄清 / 澄清需求 / PRD 计划 - `PRD Render`: 生成PRD / 渲染PRD / 输出PRD - `PRD Check`: 校验PRD / 检查PRD / 门禁 - `PRD Slice`: PRD 切片 / 切片 / 低噪切片 / slice - `Scaffold Plan`: 上下文提取 / 全局上下文 / Scaffold 计划 - `Scaffold Render`: 生成GLOBAL-CONTEXT / 渲染GLOBAL-CONTEXT / 输出GLOBAL-CONTEXT - `Scaffold Check`: 校验GLOBAL-CONTEXT / 检查GLOBAL-CONTEXT / GC 门禁 - `Split Plan`: Story 拆分规划 / Split Plan / 拆分计划 - `Split Generate`: 生成Story / Split Generate / 拆分生成 - `Split Check1`: Split 校验1 / 拆分校验1 / 结构阈值校验 - `Split Check2`: Split 校验2 / 拆分校验2 / 引用一致性校验 - `Split Checkout`: Split Checkout / 依赖图 / 导出依赖图 - `Story Check`: Story 校验 / Story Check / 单 Story 门禁 - `Story Pack`: Story 执行包生成 / Story Pack / 生成执行包 - `Story Exec`: Story 执行 / Story Exec / 单 Story 执行 - `Story Full Exec`: Story 批量执行 / Story Full Exec / 试验性全执行 - If intent is unclear, ask the user to pick one: `PRD Plan` / `PRD Check` / `PRD Render` / `PRD Slice` / `Scaffold Plan` / `Scaffold Render` / `Scaffold Check` / `Split Plan` / `Split Generate` / `Split Check1` / `Split Check2` / `Split Checkout` / `Story Check` / `Story Pack` / `Story Exec` / `Story Full Exec`. Always: - For every `FAIL` item (in diagnostics/replan packs): include `loc/problem/expected/impact/fix`, and `fix` must be a single action. - Keep chat output low-noise: prefer paths (`wrote: docs/*`) over pasting long `FAIL` lists.
Related Skills
ai-pair
AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others review (Codex + Gemini). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop
review
Daily and weekly review workflows. USE WHEN user says "morning routine", "evening routine", "weekly review", "start my day", "end of day".
Beads Issue Tracking Skill
> **Attribution**: [Beads](https://github.com/steveyegge/beads) by [Steve Yegge](https://github.com/steveyegge)
prd
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
Skill: Runs
## Purpose
Claude-Zeroclaw SKILL
## Overview
reprompter
Transform messy prompts into structured, effective prompts — single, multi-agent, or reverse-engineered from great outputs. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags, "reprompter teams", "repromptverse", "run with quality", "smart run", "smart agents", "campaign swarm", "engineering swarm", "ops swarm", "research swarm", multi-agent tasks, audits, parallel work, "reverse reprompt", "reprompt from example", "learn from this", "extract prompt from", "prompt dna", "prompt genome", reverse-engineering prompts from exemplar outputs. Don't use for simple Q&A, pure chat, or immediate execution-only tasks (see "Don't Use When" section). Outputs: structured XML/Markdown prompt, before/after quality score, optional team brief + per-agent sub-prompts, Agent Cards, Extraction Card (reverse mode). Target quality score: Single ≥ 7/10; Repromptverse per-agent ≥ 8/10; Reverse ≥ 7/10.
session-pack
세션 종료 시 Memory, Handoff를 자동 정리. /pack
execute
Main entry point for hierarchical task execution. Orchestrates layer-by-layer implementation of PRD tasks with parallel worktree execution.
sdd
This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit. Guide users through executable specification workflows for both new projects (greenfield) and existing codebases (brownfield). After any SDD command generates artifacts, automatically provide structured 10-point summaries with feature status tracking, enabling natural language feature management and keeping users engaged throughout the process.
nonstop
Enables an autonomous work mode for AI agents, allowing continuous operation without user interruption. It includes a pre-flight risk assessment and intelligent blocker handling to maximize productivity.
superbuild
Use when executing implementation plans phase-by-phase with strict enforcement of quality gates, tests, and Definition of Done. Triggers on "build this plan", "execute plan", "implement phases", or when user provides a plan document to execute.