agentskills.codes
TE

textum

by snakeyingCodingSource

Manages a structured workflow for moving from PRD to code scaffolding and story generation.

Project ManagementCode Generation

Install

mkdir -p .claude/skills/textum && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9552" && unzip -o skill.zip -d .claude/skills/textum && rm skill.zip

Installs to .claude/skills/textum

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
84 charsno explicit “when” trigger
Advanced

Key capabilities

  • →Generate PRD plans and renders
  • →Scaffold global project context
  • →Split stories into executable units
  • →Validate stages with automated gates
  • →Maintain low-noise output

How it works

The skill executes a multi-stage workflow where each stage is self-contained and validated against specific check gates.

Inputs & outputs

You give it
Stage name intent
You get back
Generated artifact file

When to use textum

  • →Generating PRDs
  • →Scaffolding global context
  • →Splitting stories
  • →Executing story generation

About this skill

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 .codex/skills/textum/scripts once (creates .codex/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.

When not to use it

  • →Narrating upstream or downstream flow
  • →Verbose diagnostic output

Prerequisites

uvuv sync --project .codex/skills/textum/scripts

Limitations

  • →Requires specific stage names for routing
  • →Strictly avoids context pollution

How it compares

It uses a structured, low-noise pipeline for PRD and scaffold generation instead of manual documentation and file creation.

Compared to similar skills

textum side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
textum (this skill)06moReviewAdvanced
code-implementer06moNo flagsAdvanced
start-work06moNo flagsIntermediate
smith-new02moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

code-implementer

galz10

Pickle Rick's "God Mode" Implementation Skill. Executes technical plans with rigorous verification. Use when you are ready to write code, run tests, and iterate through implementation phases.No Jerry-work allowed.

01

start-work

elenatanasoiu

Start new work on an issue with discovery, worktree/branch setup, TDD workflow, and draft PR creation. Use when beginning work on a GitHub issue.

00

smith-new

ATTCKDigital

Start a new feature from scratch or from conversation context. Conversational requirements gathering, planning, questions gate, then fully autonomous build.

00

rein-go

jstxn

Run one task through the full REIN flow from clarification through implementation, cleanup, review, and verification

00

spec-workflow

TencentCloudBase

Standard software engineering workflow for requirement analysis, technical design, and task planning. Use this skill when developing new features, complex architecture designs, multi-module integrations, or projects involving database/UI design.

1091

executing-plans

obra

Use when you have a written implementation plan to execute in a separate session with review checkpoints

643

Search skills

Search the agent skills registry