Agent skill

Requirements Planning

by kid-sid in kid-sid/claude-spellbook

A skill your agent uses when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's…

MITAuto-check passedProduct & Project Management

Install Requirements Planning

skills CLI
$ npx skills add kid-sid/claude-spellbook --skill requirements-planning -a claude-code

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

GitHub CLI
$ gh skill install kid-sid/claude-spellbook requirements-planning --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/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/requirements-planning .claude/skills/requirements-planning && 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
requirements-planning
GitHub stars
190
Token cost
~3.4k tokens
SKILL.md length
1,276 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's…

  • Works in 3 steps: Build the thinnest possible end-to-end… → This proves the architecture works… → Subsequent stories add depth to each…
  • Drafting user stories with acceptance criteria
  • SKILL.md covers When to Activate, User Stories, Acceptance Criteria and PRD Template, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Requirements Planning is an agent skill from kid-sid/claude-spellbook. Use when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's Definition of Done.

Its SKILL.md is about 3.4k 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 User stories and PRD writing. The repository describes itself as: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.

When your agent uses it

  • Drafting user stories with acceptance criteria
  • Breaking an epic into sprint-sized vertical slices
  • Story pointing in planning poker
  • Defining a teams Definition of Done

Example prompts

  • “/requirements-planning”

Workflow steps

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

  1. Build the thinnest possible end-to-end slice first (e.g., login → dashboard with placeholder data).
  2. This proves the architecture works before building width.
  3. Subsequent stories add depth to each slice — more data, edge cases, polish.

What it can do on your machine

Read from SKILL.md and the folder at commit a7c2ac9. 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

Requirements Planning loads about 3.4k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 1,276 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

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 kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 1,276 words, ~3,447 tokens.

Download SKILL.mdSave it as .claude/skills/requirements-planning/SKILL.md (or your agent's skills folder).
name
requirements-planning
description
Use when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's Definition of Done.

Requirements Planning

A complete reference for writing requirements that are clear, testable, and ready for development — from individual user stories to full PRDs.

When to Activate

  • Writing a PRD, one-pager, or product requirements document
  • Creating user stories or acceptance criteria for a feature
  • Story pointing or sprint planning
  • Breaking down an epic into implementable tasks
  • Defining Done criteria for a story or sprint
  • Reviewing whether requirements are testable and complete

User Stories

INVEST Criteria

Every well-formed user story satisfies all six INVEST properties.

CriteriaMeaningTest question
IndependentCan be developed without depending on another story"Can this be built and deployed alone?"
NegotiableDetails can be discussed, not a rigid contract"Is there flexibility in the how?"
ValuableDelivers value to a user or stakeholder"Who benefits and how?"
EstimableTeam can roughly size it"Do we know enough to estimate?"
SmallCan be completed in one sprint"Can one developer finish this in ≤5 days?"
TestableAcceptance criteria can be verified"How will we know it's done?"
Story Format
As a <role>,
I want to <action>,
so that <benefit>.

BAD — This is a task disguised as a story:

As a developer,
I want to implement the login endpoint,
so that the API exists.

GOOD — Clear role, action, and benefit:

As a returning user,
I want to log in with my email and password,
so that I can access my account and personal data.
Common Anti-Patterns
  • Story is a task — "Implement the login endpoint" describes technical work, not user value. Reframe around what the user can do.
  • No acceptance criteria — Without AC, there is no shared definition of done. Write AC before any code is written.
  • Story spans multiple sprints — If a story cannot be completed in a single sprint, split it using vertical slicing (see below).
  • Story says how instead of what — Requirements describe the desired outcome, not the implementation. Leave the how to the team.
  • Passive voice hides the actor — "Notifications should be sent" — by whom? to whom? Make the subject explicit.

Acceptance Criteria

BDD Format (Gherkin-style)

Use for behavioral, user-facing requirements. Each scenario maps to a test case.

Given <initial context>
When <action is taken>
Then <expected outcome>
And <additional outcome>  # optional

Example — login story:

Given a registered user with email "user@example.com"
When they submit valid credentials
Then they receive a JWT access token
And they are redirected to the dashboard

Given a registered user
When they submit an incorrect password 3 times
Then their account is locked for 30 minutes

Given a registered user whose account is locked
When they attempt to log in
Then they see the message "Account locked. Try again in 30 minutes."
Checklist-Style AC

Use for non-behavioral or non-functional requirements where Given/When/Then does not fit naturally.

- [ ] Response time < 200ms at p95
- [ ] Works on Chrome, Firefox, Safari (last 2 versions)
- [ ] Error message shown for invalid input
- [ ] Form fields validated client-side before submission
Functional vs Non-Functional AC
TypeExampleWho writes it
Functional"User can reset password via email link"PO / Dev together
Performance"API responds in < 500ms"Dev / SRE
Security"Session expires after 30 min inactivity"Security / Dev
Accessibility"Form navigable by keyboard"Designer / Dev

Non-functional requirements are frequently omitted. Make them explicit on every story where they apply.


PRD Template

Use this template when writing a product requirements document, feature brief, or one-pager.

markdown
# PRD: [Feature Name]

## Problem Statement
[1–2 sentences: what problem are we solving and for whom?]

## Goals
- Goal 1 (measurable)
- Goal 2

## Non-Goals
- Explicitly out of scope item 1
- Explicitly out of scope item 2

## User Personas
| Persona | Description | Primary need |
|---------|-------------|-------------|
| ...     | ...         | ...         |

## Functional Requirements
1. [REQ-001] The system shall...
2. [REQ-002] The system shall...

## Non-Functional Requirements
- Performance: [e.g., p95 latency < 300ms]
- Security: [e.g., data encrypted at rest]
- Scalability: [e.g., support 10k concurrent users]

## Out of Scope
- ...

## Open Questions
| Question | Owner | Due |
|----------|-------|-----|
| ...      | ...   | ... |

## Success Metrics
- Metric 1: [e.g., 20% increase in activation rate]
- Metric 2: [e.g., 0 P0 security incidents]

## Timeline
| Milestone | Date |
|-----------|------|
| ...       | ...  |
PRD Writing Tips
  • Non-Goals are mandatory. Explicitly stating what is out of scope prevents scope creep and misaligned expectations.
  • Every goal must be measurable. "Improve performance" is not a goal. "Reduce p95 latency from 800ms to 300ms" is a goal.
  • Open questions block progress. Assign every open question an owner and a deadline. Review at the next refinement session.
  • Success metrics connect to goals. If you cannot measure whether a goal was achieved, the goal is not yet well-formed.

Story Pointing

Fibonacci Scale

Points are assigned from the sequence: 1, 2, 3, 5, 8, 13, 21 (and ∞ for "we cannot estimate this yet").

  • Points measure complexity + uncertainty, NOT hours worked.
  • A story pointed at 8 is roughly twice as complex and uncertain as a story pointed at 3.
  • Calibration anchor: pick a well-understood story the team agrees is a 3, then size all others relative to it.
  • If a story is pointed at 13 or 21, strongly consider splitting it before the sprint.
  • ∞ means the team lacks enough information to estimate — do discovery work before committing to the story.
T-Shirt Sizing (Alternative)

Use XS / S / M / L / XL when:

  • The team is new and has no calibration anchor.
  • Estimating at the epic level rather than the story level.
  • Rough relative sizing is sufficient (roadmap planning, not sprint planning).

Map to Fibonacci before sprint planning: XS → 1–2, S → 3, M → 5, L → 8, XL → 13+.

Planning Poker Norms
  • Everyone reveals their estimate simultaneously — avoids anchoring on a loud voice.
  • High variance (e.g., one person says 3, another says 13) means the team has different assumptions. Discuss, do not average.
  • After discussion, re-estimate if the spread was greater than 2 sizes.
  • Keep the round time-boxed: aim to settle an estimate in under 5 minutes.
What Affects Points
Increases pointsDoes NOT affect points
Technical complexityWho will work on it
Uncertainty / unknownsTime of day or week
Integration risk (third-party APIs, etc.)Developer seniority or speed
Testing surface areaCalendar deadline pressure
Cross-team dependenciesWhether the work is boring or fun

Epic and Feature Decomposition

Horizontal vs Vertical Slicing
ApproachDefinitionExampleProblem
HorizontalSplit by technical layer"Build the database schema", "Build the API", "Build the UI"Not independently valuable
VerticalSplit by user journey / thin feature slice"User can register with email (no profile picture yet)"None — preferred approach

Vertical slices are shippable. Each delivers some user value. Horizontal slices only deliver value when all layers are complete — meaning nothing is releasable until all layers are done.

Show full SKILL.md (510 more words)Show less
Walking Skeleton
  1. Build the thinnest possible end-to-end slice first (e.g., login → dashboard with placeholder data).
  2. This proves the architecture works before building width.
  3. Subsequent stories add depth to each slice — more data, edge cases, polish.

The walking skeleton is never the full feature. It is the minimal path through the system.

Decomposition Patterns
PatternDescriptionExample
By user roleDifferent actors get separate storiesAdmin story vs regular user story for the same screen
By data volumeSimple case first, then scale"View first 10 items" → "View paginated list"
By exception flowHappy path first, error paths separately"User logs in" → "User sees error on locked account"
By CRUD operationEach operation is a separate storyCreate → Read → Update → Delete as four stories
By configurationDefault behaviour first, then customization"Email sends with default template" → "Custom template"

Definition of Done

Org-Level DoD (applies to all stories)

Copy this into your team's working agreement and adjust as needed.

- [ ] Code reviewed and approved (minimum 1 reviewer)
- [ ] Unit tests written and passing
- [ ] Integration tests passing
- [ ] No new HIGH/CRITICAL security vulnerabilities introduced
- [ ] Feature deployed to staging and smoke-tested
- [ ] Acceptance criteria verified by PO or QA
- [ ] Documentation updated (if applicable)
- [ ] No unresolved review comments left open
Story-Level DoD (specific to the story)
  • Written by the team during refinement, before sprint start.
  • Lives inside the story ticket as part of the acceptance criteria.
  • Example for "User profile picture upload":
    - [ ] File size validated (max 5MB, reject otherwise with error message)
    - [ ] Uploaded file stored in S3 under /users/{id}/avatar
    - [ ] S3 URL saved to the users table (avatar_url column)
    - [ ] Profile page displays new avatar within 1 page reload
    - [ ] Old avatar deleted from S3 on successful replacement
Sprint-Level DoD (applies to the sprint as a whole)
- [ ] All stories meeting org-level DoD are merged to main
- [ ] Release notes drafted
- [ ] Regression suite passing on staging
- [ ] PO has signed off on the sprint goal

Red Flags

  • User stories without acceptance criteria — "as a user I want to log in" is untestable; every story needs explicit Given/When/Then scenarios agreed before development starts
  • Estimating in hours — hour estimates imply false precision and ignore team velocity variance; use relative Fibonacci story points for sizing
  • Horizontal technical slices ("backend API for X", "DB schema for X") — these deliver no user value alone; always slice to include the full end-to-end user-visible behavior
  • Definition of Done defined inconsistently per story — inconsistent DoD creates review surprises; agree on a team-wide DoD (tests, review, deployed to staging) before the sprint starts
  • Non-goals written as "future work" — "multi-tenant support in v2" in a non-goals section implies a promise; explicitly state items are out of scope with no timeline
  • Success metrics defined as "users will love it" — unmeasurable goals make it impossible to declare a feature successful or failed; tie metrics to specific, observable behavior
  • No timebox for stories with unknown technical risk — committing to high-uncertainty stories without a spike investigation leads to wildly missed estimates and scope creep

Checklist

  • Every story follows the "As a / I want / so that" format
  • Story satisfies all INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable)
  • Acceptance criteria are written before development starts
  • BDD Given/When/Then used for behavioral requirements
  • Non-functional requirements captured explicitly (performance, security, accessibility)
  • Epic decomposed into vertical slices, not horizontal layers
  • Story is sized (points or T-shirt) and team agrees on the estimate
  • Definition of Done agreed upon before sprint starts
  • Open questions in the PRD have owners and deadlines assigned
  • Success metrics are defined, measurable, and tied to stated goals

© kid-sid, MIT. 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 skills/requirements-planning of kid-sid/claude-spellbook.

Open the folder on GitHubat commit a7c2ac9

Compare with similar skills

Requirements Planning 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.

Requirements Planning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Requirements Planning this skillkid-sid/claude-spellbook190—~3.4kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT
Ralph Tui Create JSONsubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
To Prdywwynm/EverythingDone14411 repos~777Automated safety check: PassGPL-3.0
Use Case Writerphucnt-bazone-vietnam/use-case-writer143—~4.1kAutomated safety check: PassMIT

Similar skills

  • 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
  • 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
  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format 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
  • To Prd

    ywwynm/EverythingDone

    Turn the current conversation context into a PRD and publish it to the project issue tracker.

    144 GitHub starsUsed in 11 repos~777 tokens
    Product & Project ManagementAuto-check passed
  • Use Case Writer

    phucnt-bazone-vietnam/use-case-writer

    Generate Use Case specifications in English Markdown following the IT BA standard 13-field template (Karl Wiegers / IIBA).

    143 GitHub stars~4.1k tokensUpdated 4 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

More from kid-sid/claude-spellbook

All 55 skills in this repo
  • Accessibility

    kid-sid/claude-spellbook

    A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…

    190 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Agentex

    kid-sid/claude-spellbook

    A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…

    190 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • AI Engineer

    kid-sid/claude-spellbook

    A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

    190 GitHub stars~3.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Angular

    kid-sid/claude-spellbook

    A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…

    190 GitHub stars~5k tokensUpdated 2 mo ago
    Auto-check passed
  • API Design

    kid-sid/claude-spellbook

    A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…

    190 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Auth

    kid-sid/claude-spellbook

    A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…

    190 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Requirements Planning

What does Requirements Planning do?

A skill your agent uses when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's…. Requirements Planning is an agent skill from kid-sid/claude-spellbook. Use when writing a PRD, drafting user stories with acceptance criteria, breaking an epic into sprint-sized vertical slices, story pointing in planning poker, or defining a team's Definition of Done.

When should I use Requirements Planning?

Requirements Planning fits situations like: drafting user stories with acceptance criteria; breaking an epic into sprint-sized vertical slices; story pointing in planning poker; defining a teams Definition of Done.

How do I install Requirements Planning in Claude Code?

Run `npx skills add kid-sid/claude-spellbook --skill requirements-planning -a claude-code`. Or copy the skill folder (skills/requirements-planning in kid-sid/claude-spellbook) into .claude/skills/requirements-planning in your project. Claude Code loads it when a task matches its description.

How do I install Requirements Planning in Codex?

Run `npx skills add kid-sid/claude-spellbook --skill requirements-planning -a codex`. Or copy the skill folder (skills/requirements-planning in kid-sid/claude-spellbook) into .agents/skills/requirements-planning in your project. Codex loads it when a task matches its description.

Can I use Requirements Planning 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 kid-sid/claude-spellbook --skill requirements-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/requirements-planning, .gemini/skills/requirements-planning, .github/skills/requirements-planning and .opencode/skills/requirements-planning in your project.

What does Requirements Planning need to run?

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

Does Requirements Planning 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 Requirements Planning 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 Requirements Planning use?

Requirements Planning is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Requirements Planning use?

About 3.4k tokens (SKILL.md is roughly 14k 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 Requirements Planning?

Skills that share tags, products or a category with Requirements Planning: Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars), Ralph Tui Create JSON (subsy/ralph-tui, 2.5k stars) and To Prd (ywwynm/EverythingDone, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Requirements Planning?

kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 190 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on August 5, 2026.

Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.