Agent skill

Prd

by smallnest in smallnest/autoresearch

Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues.

MITAuto-check passedProduct & Project Management

Install Prd

skills CLI
$ npx skills add smallnest/autoresearch --skill prd -a claude-code

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

GitHub CLI
$ gh skill install smallnest/autoresearch 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/smallnest/autoresearch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prd .claude/skills/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
prd
GitHub stars
571
Token cost
~3.7k tokens
SKILL.md length
1,128 words
Files
4
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues.

  • Works in 3 steps: Clarifying Questions → PRD Structure → Issue Decomposition & Creation
  • Planning a feature
  • SKILL.md covers The Job, Step 1: Clarifying Questions, Edge Cases & Fallback and Step 2: PRD Structure, plus 4 more sections
  • Calls gh

What it does

Prd is an agent skill from smallnest/autoresearch. Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues. 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, 写PRD, 需求文档, 需求分析, 规格说明.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `README.md` and `test-prompts.json`).

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: autodevelop: autoresearch for software development. The licence is MIT.

When your agent uses it

  • Planning a feature
  • Starting a new project
  • Asked to create a PRD
  • Plan this feature

Example prompts

  • “/prd”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Clarifying Questions
  2. PRD Structure
  3. Issue Decomposition & Creation

What it can do on your machine

Read from SKILL.md and the folder at commit 3bb6898. 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

    Shell commands in SKILL.md call:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Prd loads about 3.7k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 1,128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

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 smallnest/autoresearch at commit 3bb6898, republished under its MIT licence (© smallnest). 1,128 words, ~3,674 tokens.

Download SKILL.mdSave it as .claude/skills/prd/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
prd
description
Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues. 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, 写PRD, 需求文档, 需求分析, 规格说明.
user-invocable
true

PRD Generator + Issue Decomposer

Create detailed Product Requirements Documents that are clear, actionable, and suitable for implementation. After PRD is confirmed, decompose it into small, independent Issues and create them in the user's chosen platform.


The Job

  1. Receive a feature description from the user
  2. Ask 3-5 essential clarifying questions (with lettered options)
  3. Generate a structured PRD based on answers
  4. Present PRD to user for review — ask "Please review the PRD. Let me know if any adjustments are needed, or reply OK to confirm."
  5. Apply any adjustments, then save to tasks/prd-[feature-name].md
  6. Decompose PRD into Issues — break each User Story into one or more independent, implementable Issues
  7. Ask user to choose Issue creation mode — GitHub / Local / Baidu iCafe
  8. Create Issues in the chosen platform

Important: Do NOT start implementing. Just create the PRD and Issues.


Step 1: Clarifying Questions

Ask only critical questions where the initial prompt is ambiguous. Focus on:

  • Problem/Goal: What problem does this solve?
  • Core Functionality: What are the key actions?
  • Scope/Boundaries: What should it NOT do?
  • Success Criteria: How do we know it's done?
Format Questions Like This:
1. What is the primary goal of this feature?
   A. Improve user onboarding experience
   B. Increase user retention
   C. Reduce support burden
   D. Other: [please specify]

2. Who is the target user?
   A. New users only
   B. Existing users only
   C. All users
   D. Admin users only

3. What is the scope?
   A. Minimal viable version
   B. Full-featured implementation
   C. Just the backend/API
   D. Just the UI

This lets users respond with "1A, 2C, 3B" for quick iteration. Remember to indent the options.


Edge Cases & Fallback

ScenarioHandling
User skips clarifying questions (e.g., replies "whatever", "just write it")Fill with reasonable defaults, mark with [Assumption] in PRD, prompt user to confirm during review
User input is too vague (e.g., "add a feature")Ask once for specifics; if still vague, infer from project context and mark assumptions
tasks/ directory does not existAuto-create tasks/ directory
feature-name is hard to extract from inputAsk the user directly: "Suggested PRD filename is prd-XXX.md, please confirm or modify"
User requests PRD changes after reviewApply changes and re-save without re-running the clarification flow
PRD content exceeds 500 linesSuggest the user consider splitting into multiple sub-feature PRDs
User declines Issue creationJust save the PRD, skip Step 3
gh CLI not authenticated for GitHub modeShow error, suggest gh auth login, offer to switch to Local mode
icafe-cli / icode-cli not installed for baidu modeShow error, suggest installation, offer to switch to Local mode
Issue folder does not exist for Local modeAuto-create the folder

Step 2: PRD Structure

Generate the PRD with these sections:

1. Introduction/Overview

Brief description of the feature and the problem it solves. Use plain language — avoid jargon or explain it. Assume the reader may be a junior developer or AI agent.

2. Goals

Specific, measurable objectives (bullet list).

3. User Stories

Each story needs:

  • Title: Short descriptive name
  • Description: "As a [user], I want [feature] so that [benefit]"
  • Acceptance Criteria: Verifiable checklist of what "done" means

Numbering rule: US-001, US-002, US-003... (three digits, starting from 001). Each US should be independently implementable, ideally completable within one agent session.

Each story should be small enough to implement in one focused session.

Acceptance criteria self-check template: Each criterion must satisfy at least one of the following, otherwise it is considered "vague" and must be rewritten:

  • Observable: describes a specific UI state or API response (e.g., "button shows confirmation dialog")
  • Testable: has clear input/output pairs (e.g., "entering an empty email shows a red warning")
  • Verifiable: can be checked by tools (e.g., "Typecheck/lint passes")
  • ❌ Bad example: "works correctly", "good user experience", "excellent performance" → these are unverifiable

Format:

markdown
### US-001: [Title]
**Description:** As a [user], I want [feature] so that [benefit].

**Acceptance Criteria:**
- [ ] Specific verifiable criterion
- [ ] Another criterion
- [ ] Typecheck/lint passes
- [ ] **[UI stories only]** Verify in browser using dev-browser skill

Important:

  • Acceptance criteria must be verifiable, not vague. "Works correctly" is bad. "Button shows confirmation dialog before deleting" is good.
  • For any story with UI changes: Always include "Verify in browser using dev-browser skill" as acceptance criteria. This ensures visual verification of frontend work.
4. Functional Requirements

Numbered list of specific functionalities:

  • "FR-1: The system must allow users to..."
  • "FR-2: When a user clicks X, the system must..."

FR specification: Each FR starts with FR-N: (N increments from 1), uses "system must / system shall" phrasing, and describes one specific behavior. Avoid combining multiple "and"-linked behaviors in a single FR.

5. Non-Goals (Out of Scope)

What this feature will NOT include. Critical for managing scope.

6. Design Considerations (Optional)
  • UI/UX requirements
  • Link to mockups if available
  • Relevant existing components to reuse
7. Technical Considerations (Optional)
  • Known constraints or dependencies
  • Integration points with existing systems
  • Performance requirements
Show full SKILL.md (483 more words)Show less
8. Success Metrics

How will success be measured?

  • "Reduce time to complete X by 50%"
  • "Increase conversion rate by 10%"
9. Open Questions

Remaining questions or areas needing clarification.


Output

  • Format: Markdown (.md)
  • Location: tasks/
  • Filename: prd-[feature-name].md (kebab-case)

Step 3: Issue Decomposition & Creation

After the PRD is saved, decompose it into implementable Issues and create them.

3.1 Decompose PRD into Issues

Based on the PRD's User Stories and Functional Requirements, generate a list of Issues. Follow these rules:

  • One Issue per User Story — each US-XXX becomes at least one Issue
  • Split large stories — if a US has 5+ acceptance criteria or spans frontend + backend, split into 2-3 smaller Issues with clear dependencies
  • Merge tiny stories — if a US has only 1-2 trivial criteria, merge it with a related US into a single Issue
  • Each Issue must be independently implementable — a single agent session should be able to complete it
  • Number Issues sequentially starting from 1

Issue format:

Issue #N: [Title]
---
Description: [From US description, with context]
Acceptance Criteria:
- [ ] [From US acceptance criteria]
- [ ] ...
Dependencies: [None / Issue #X]
Type: [backend / frontend / fullstack / ui / infra]
Priority: [high / medium / low]

Present the Issue list to the user for review:

📋 Generated N Issues from PRD:

#1: Add priority field to database (backend, high)
#2: Display priority indicator on task cards (frontend, high) — depends on #1
#3: Add priority selector to task edit (frontend, medium) — depends on #1
#4: Filter tasks by priority (frontend, medium) — depends on #1, #2

Please review. You can:
- Remove issues: "remove #3"
- Merge issues: "merge #2 and #3"
- Add issues: "add an issue for sorting by priority"
- Adjust: "change #2 priority to high"
- Confirm: reply OK to proceed

Wait for user confirmation before creating any Issues.

3.2 Ask User to Choose Creation Mode

After user confirms the Issue list, ask:

Choose where to create these Issues:

A. GitHub (via gh CLI)
B. Local (save as .md files)
C. Baidu iCafe (via icafe-cli)

Your choice:
3.3 Mode-Specific Parameters & Creation
Mode A: GitHub

Prerequisites: gh CLI installed and authenticated.

Actions:

  1. For each Issue, run:
    bash
    gh issue create --title "[Title]" --body "[Description + Acceptance Criteria]" --label "[type]" --label "priority: [priority]"
  2. If labels don't exist, create them first or skip the --label flag
  3. Report created Issue numbers and URLs
Mode B: Local

Ask user:

Where should I save the Issue files? (default: .autoresearch/issues)

Actions:

  1. If the specified folder does not exist, create it with mkdir -p
  2. For each Issue #N, save a file named issue-NNN-[slug].md (zero-padded to 3 digits):
    markdown
    # [Title]
    
    ## Description
    [Description from Issue]
    
    ## Acceptance Criteria
    - [ ] [criterion 1]
    - [ ] [criterion 2]
    
    ## Dependencies
    [None / Issue #X]
    
    ## Type
    [backend / frontend / fullstack / ui / infra]
    
    ## Priority
    [high / medium / low]
  3. Report created file paths
Mode C: Baidu iCafe

Ask user:

Please provide the iCafe space prefix code (--space):

Optionally ask:

Target branch for iCode CR? (default: master)

Prerequisites: icafe-cli installed and logged in.

Actions:

  1. For each Issue, run:
    bash
    icafe-cli card create --space [SPACE] --title "[Title]" --description "[Description + Acceptance Criteria]" --cardtype "[Task/Bug/Story]"
    • Map Issue type to iCafe card type: bug → Bug, ui/frontend → Story, others → Task
    • Map priority: high → 高, medium → 中, low → 低
  2. If iCafe card creation fails for an Issue, log the error and continue with remaining Issues
  3. Report created card sequence numbers
3.4 Summary Report

After all Issues are created, print a summary:

✅ Issue creation complete!

Mode: [GitHub / Local / Baidu iCafe]
PRD: tasks/prd-[feature-name].md
Issues created: N

#  | Title                                    | Identifier
---|------------------------------------------|------------
1  | Add priority field to database           | #42 (GitHub) / issue-001-*.md (Local) / #22210 (iCafe)
2  | Display priority indicator               | #43 / issue-002-*.md / #22211
3  | Add priority selector                    | #44 / issue-003-*.md / #22212
4  | Filter tasks by priority                 | #45 / issue-004-*.md / #22213

💡 Tip: You can now run autoresearch on each Issue:
  ./run.sh 42                    # GitHub mode
  ./run.sh 1                     # Local mode
  ./run.sh --issue-source=baidu --space=[SPACE] 22210  # Baidu iCafe mode

Example PRD

markdown
# PRD: Task Priority System

## Introduction

Add priority levels to tasks so users can focus on what matters most. Tasks can be marked as high, medium, or low priority, with visual indicators and filtering to help users manage their workload effectively.

## Goals

- Allow assigning priority (high/medium/low) to any task
- Provide clear visual differentiation between priority levels
- Enable filtering and sorting by priority
- Default new tasks to medium priority

## User Stories

### US-001: Add priority field to database
**Description:** As a developer, I need to store task priority so it persists across sessions.

**Acceptance Criteria:**
- [ ] Add priority column to tasks table: 'high' | 'medium' | 'low' (default 'medium')
- [ ] Generate and run migration successfully
- [ ] Typecheck passes

### US-002: Display priority indicator on task cards
**Description:** As a user, I want to see task priority at a glance so I know what needs attention first.

**Acceptance Criteria:**
- [ ] Each task card shows colored priority badge (red=high, yellow=medium, gray=low)
- [ ] Priority visible without hovering or clicking
- [ ] Typecheck passes
- [ ] Verify in browser using dev-browser skill

### US-003: Add priority selector to task edit
**Description:** As a user, I want to change a task's priority when editing it.

**Acceptance Criteria:**
- [ ] Priority dropdown in task edit modal
- [ ] Shows current priority as selected
- [ ] Saves immediately on selection change
- [ ] Typecheck passes
- [ ] Verify in browser using dev-browser skill

### US-004: Filter tasks by priority
**Description:** As a user, I want to filter the task list to see only high-priority items when I'm focused.

**Acceptance Criteria:**
- [ ] Filter dropdown with options: All | High | Medium | Low
- [ ] Filter persists in URL params
- [ ] Empty state message when no tasks match filter
- [ ] Typecheck passes
- [ ] Verify in browser using dev-browser skill

## Functional Requirements

- FR-1: Add `priority` field to tasks table ('high' | 'medium' | 'low', default 'medium')
- FR-2: Display colored priority badge on each task card
- FR-3: Include priority selector in task edit modal
- FR-4: Add priority filter dropdown to task list header
- FR-5: Sort by priority within each status column (high to medium to low)

## Non-Goals

- No priority-based notifications or reminders
- No automatic priority assignment based on due date
- No priority inheritance for subtasks

## Technical Considerations

- Reuse existing badge component with color variants
- Filter state managed via URL search params
- Priority stored in database, not computed

## Success Metrics

- Users can change priority in under 2 clicks
- High-priority tasks immediately visible at top of lists
- No regression in task list performance

## Open Questions

- Should priority affect task ordering within a column?
- Should we add keyboard shortcuts for priority changes?

Checklist

Before saving the PRD:

  • Asked clarifying questions with lettered options
  • Incorporated user's answers
  • User stories are small and specific
  • Functional requirements are numbered and unambiguous
  • Non-goals section defines clear boundaries
  • Saved to tasks/prd-[feature-name].md

Before finishing Issue creation:

  • Decomposed PRD into independent, implementable Issues
  • Presented Issue list to user for review and confirmation
  • Asked user to choose creation mode (GitHub / Local / Baidu iCafe)
  • Collected mode-specific parameters (folder path for Local, --space for Baidu iCafe)
  • Created all Issues and reported results
  • Printed summary with autoresearch usage tips

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

Files

SKILL.md and 3 other files in skills/prd of smallnest/autoresearch.

  • SKILL.md
  • LICENSE
  • README.md
  • test-prompts.json

Open the folder on GitHubat commit 3bb6898

Compare with similar skills

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.

Prd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd this skillsmallnest/autoresearch571—~3.7kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated 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
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed
  • To Issues

    ywwynm/EverythingDone

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    144 GitHub starsUsed in 12 repos~893 tokens
    Product & Project ManagementAuto-check passed

Questions about Prd

What does Prd do?

Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues. Prd is an agent skill from smallnest/autoresearch. Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues.

When should I use Prd?

Prd fits situations like: planning a feature; starting a new project; asked to create a PRD; plan this feature.

How do I install Prd in Claude Code?

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

How do I install Prd in Codex?

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

Can I use 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 smallnest/autoresearch --skill 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/prd, .gemini/skills/prd, .github/skills/prd and .opencode/skills/prd in your project.

What does Prd need to run?

Going by SKILL.md and its folder, Prd needs the command-line tools its instructions call (gh).

Does Prd access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is 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 Prd use?

Prd is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prd use?

About 3.7k tokens (SKILL.md is roughly 15k 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 Prd?

Skills that share tags, products or a category with Prd: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd?

smallnest (a GitHub user) maintains it in smallnest/autoresearch, which has 571 GitHub stars. The repository was last updated on July 14, 2026.

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