Agent skill

To Prd

by udecode in udecode/kitcn

Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts.

Apache-2.0Auto-check passedProduct & Project Management

Install To Prd

skills CLI
$ npx skills add udecode/kitcn --skill to-prd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install udecode/kitcn to-prd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/udecode/kitcn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/to-prd .claude/skills/to-prd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
to-prd
GitHub stars
450
Token cost
~1.1k tokens
SKILL.md length
445 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
Apache-2.0

At a glance

Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts.

  • Works in 5 steps: Latest user direction. → VISION.md and the selected milestone map. → Existing PRDs, ADRs, research, plans,… → …
  • Tasks that involve PRD writing
  • SKILL.md covers Source Order, Scope Ambition, Required Decisions and Design Lane, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

To Prd is an agent skill from udecode/kitcn. Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering PRD writing and Project management. The repository describes itself as: Convex + Better Auth + tRPC + Drizzle + TanStack Query + shadcn. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve PRD writing
  • Tasks that involve Project management

Example prompts

  • “/to-prd”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Latest user direction.
  2. VISION.md and the selected milestone map.
  3. Existing PRDs, ADRs, research, plans, and docs.
  4. Public exports, runtime entry points, CLI/template owners, tests, fixtures,
  5. Proven OSS implementations from local clones when relevant.

What it can do on your machine

Read from SKILL.md and the folder at commit c6010f5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

To Prd loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from udecode/kitcn at commit c6010f5, republished under its Apache-2.0 licence (© udecode). 445 words, ~1,064 tokens.

Download SKILL.mdSave it as .claude/skills/to-prd/SKILL.md (or your agent's skills folder).
name
to-prd
description
Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts.
argument-hint
<source | milestone rung | capability>

To PRD

The PRD is the local source for a coherent capability. It must let auto full or task execute without inventing product, API, auth, or proof decisions.

Source Order

  1. Latest user direction.
  2. VISION.md and the selected milestone map.
  3. Existing PRDs, ADRs, research, plans, and docs.
  4. Public exports, runtime entry points, CLI/template owners, tests, fixtures, scenarios, and examples.
  5. Proven OSS implementations from local clones when relevant.

If these contradict, repair or record the decision before publishing the PRD.

Scope Ambition

Write one PRD for one end-to-end developer outcome. Include all owners necessary for it to work: package/API, Convex runtime, auth/data flow, CLI/scaffold, examples, docs/package skill, fixtures/scenarios, and observability/proof.

Do not split supporting tests, guards, types, docs, or internal helpers into independent PRDs. Do not inflate the PRD with adjacent roadmap ideas.

Required Decisions

The PRD settles:

  • user/developer problem and success story;
  • familiar mental model and deviations from it;
  • public API names, types, errors, and hard-cut stance;
  • service/runtime entry points and Convex static import boundaries;
  • canonical data, identity, auth/session, permission, and lifecycle flow;
  • plugin/extensibility and bundle-size consequences;
  • CLI commands, --json, --yes, and non-interactive behavior when relevant;
  • source/generated owners and regeneration commands;
  • migration/deletion behavior;
  • docs, package skill, examples, fixtures, and scenario ownership;
  • testing, benchmark, runtime, browser, and repository proof.

Unsettled irreversible choices go in an explicit decision table with a recommended answer and disconfirming evidence. Do not hide them in “TBD.”

Design Lane

When UI is part of the outcome, include the real subject, route, tokens, primitives, state matrix, accessibility, responsive behavior, and Browser proof. Link a prototype only as evidence; source implementation remains the owner.

Show full SKILL.md (176 more words)Show less

Task Packets

Decompose directly into local packets inside the PRD.

Each packet has:

  • outcome and owner files;
  • prerequisites and conflict group;
  • behavior/API decisions it consumes;
  • source/generated work;
  • acceptance and proof;
  • explicit exclusions;
  • blocking, parallel-join, or detached status.

Packets should be vertical and independently provable. Consolidate guard-only, test-only, docs-only, and refactor-only fragments into the behavior packet they support unless they have a genuinely separate owner and outcome.

PRD Template

md
# <Title> PRD

## Milestone Context
## Problem Statement
## Target Story
## Solution
## Vision Alignment
## Self-Grill Receipt
## Current Source Evidence
## Public API And Mental Model
## Service, Auth, And Data Flow
## Package And Bundle Ownership
## CLI, Scaffold, And Generated Ownership
## Design Lock
## Implementation Decisions
## Testing And Proof Decisions
## Task Packets
## Acceptance Criteria
## Source-Backed Claim Ledger
## Out Of Scope
## Open Decisions
## Done Means

Use N/A with reason for irrelevant sections; do not delete the reasoning surface.

Scoring Gate

Before publication, score 0-5 with citations:

  • vision fit;
  • user/developer leverage;
  • source capability;
  • public API and type clarity;
  • auth/data-flow clarity;
  • bundle/ownership safety;
  • implementation readiness;
  • proof and rollback strength;
  • scope discipline.

Any dimension below 4 blocks implementation readiness unless the PRD records a real external blocker and safe boundary. Run a contradiction pass, self-grill, agent-native-reviewer when agent workflow is involved, then autoreview.

Publish

Write to docs/prds/<date>-<slug>.md, link it from the selected milestone or docs/README.md, and name the first packet owner. Publication is not implementation; auto full continues through packets, verification, and GitHub delivery when asked.

© udecode, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/to-prd of udecode/kitcn.

Open the folder on GitHubat commit c6010f5

Compare with similar skills

To Prd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

To Prd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
To Prd this skilludecode/kitcn450—~1.1kAutomated safety check: PassApache-2.0
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Project Planneradrianpuiu/claude-skills-marketplace1001 repos~6kAutomated safety check: PassNone
Shep Workstreamsshep-ai/shep264—~2.5kAutomated safety check: PassMIT
App Spec Packagerinstructa/agent-skills139—~1.5kAutomated safety check: PassNone
Fireauto Project Guideimgompanda/fireauto140—~674Automated safety check: PassMIT

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Project Planner

    adrianpuiu/claude-skills-marketplace

    Comprehensive project planning and documentation generator for software projects.

    100 GitHub starsUsed in 1 repo~6k tokens
    Product & Project ManagementAuto-check passed
  • Shep Workstreams

    shep-ai/shep

    A skill your agent uses when a large body of work (a version milestone, an epic, a roadmap, a set of PRDs/design docs) needs to be broken into parallel workstreams and executed with the shep CLI.

    264 GitHub stars~2.5k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • App Spec Packager

    instructa/agent-skills

    A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification…

    139 GitHub stars~1.5k tokensUpdated 9 days ago
    Product & Project ManagementAuto-check passed
  • Fireauto Project Guide

    imgompanda/fireauto

    프로젝트 생성, 마일스톤 관리, 태스크 추적이 필요할 때 사용하세요. An agent skill from imgompanda/fireauto.

    140 GitHub stars~674 tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Roadmap

    YougLin-dev/Aha-Loop

    Creates and manages project roadmaps with milestones and PRD queues.

    181 GitHub stars~2.7k tokensUpdated 8 mo ago
    Product & Project ManagementAuto-check passed

More from udecode/kitcn

All 33 skills in this repo
  • Walkthrough

    udecode/kitcn

    Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

    450 GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed
  • Avoid Feature Creep

    udecode/kitcn

    Prevent feature creep when building software, apps, and AI-powered products.

    450 GitHub stars~2.7k tokensUpdated 6 days ago
    Auto-check passed
  • Changeset Resolve

    udecode/kitcn

    Repair an unreleased .changeset/.md file so it matches the real branch delta against main.

    450 GitHub stars~922 tokensUpdated 6 days ago
    Auto-check passed
  • Audit newer Convex npm releases against kitcn. An agent skill from udecode/kitcn.

    450 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed
  • Jotai X

    udecode/kitcn

    A skill your agent uses when working with Jotai X stores (createAtomStore), accessing state in components or callbacks, persisting state to cookies or localStorage

    450 GitHub stars~3.7k tokensUpdated 6 days ago
    Auto-check passed
  • Linear Backlog

    udecode/kitcn

    Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task.

    450 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check passed

Questions about To Prd

What does To Prd do?

Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts. To Prd is an agent skill from udecode/kitcn. Turn a settled kitcn capability or milestone rung into an ambitious, implementation-ready local PRD with decisions, owner maps, task packets, and proof contracts.

When should I use To Prd?

To Prd fits situations like: tasks that involve PRD writing; tasks that involve Project management.

How do I install To Prd in Claude Code?

Run `npx skills add udecode/kitcn --skill to-prd -a claude-code`. Or copy the skill folder (.agents/skills/to-prd in udecode/kitcn) into .claude/skills/to-prd in your project. Claude Code loads it when a task matches its description.

How do I install To Prd in Codex?

Run `npx skills add udecode/kitcn --skill to-prd -a codex`. Or copy the skill folder (.agents/skills/to-prd in udecode/kitcn) into .agents/skills/to-prd in your project. Codex loads it when a task matches its description.

Can I use To Prd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add udecode/kitcn --skill to-prd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/to-prd, .gemini/skills/to-prd, .github/skills/to-prd and .opencode/skills/to-prd in your project.

What does To Prd need to run?

SKILL.md names no scripts, command-line tools or credentials: To Prd is instructions for the agent only.

Does To Prd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is To Prd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does To Prd use?

To Prd is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does To Prd use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to To Prd?

Skills that share tags, products or a category with To Prd: CCPM Project Management (automazeio/ccpm, 8.4k stars), Project Planner (adrianpuiu/claude-skills-marketplace, 100 stars), Shep Workstreams (shep-ai/shep, 264 stars) and App Spec Packager (instructa/agent-skills, 139 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains To Prd?

udecode (a GitHub organization) maintains it in udecode/kitcn, which has 450 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 1, 2026.

Source: udecode/kitcn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.