mcpbeat Sign in

Plan Feature Agent Skill

Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
536
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/HoangNguyen0403/agent-skills-standard --skill plan-feature

The instruction itself

8 sections, as written by the author

Plan Feature Skill

> [!IMPORTANT]

> Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.

Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.

Instructions

When the user asks to perform this workflow, execute the following steps:

Feature Planning Workflow (PRD / What)

Goal: Produce a PM-owned decision-complete PRD, delivery plan, and IT Department handoff before code starts.

Steps

  • Load context:
  • Load baseline PRD section and search docs/brd/ for the matching [slug]; if multiple candidates exist and intent is unclear, ask the user to choose/input the target slug.
  • Load BRD-lite, ticket text, existing specs, repo patterns, common-product-requirements, common-operator-profile, quality-engineering-business-analysis, and matched framework skills.
  • Carry forward operator_profile, BRD objective IDs, SMART metric, scope fence, assumptions, glossary, risks, and delivery context.
  • Interview:
  • Draft a provisional PRD direction from current context before asking.
  • Ask only for business logic, scope, constraints, and acceptance criteria that cannot be inferred.
  • Ask max 3 blocking decisions at a time; include a recommended default and 2-3 options for each.
  • Treat non-critical unknowns as explicit assumptions.
  • Confirm problem statement, assumptions, target users, JTBD/use cases, platforms, data, analytics, security, performance, rollout, and non-goals.
  • Confirm each requirement has owner, priority, and status.
  • Confirm success metrics and guardrails that must not regress.
  • Stop when requirements are actionable.
  • Draft PRD:
  • Save to docs/prd/prd-[slug].md when file writes are allowed.
  • Keep "what" separate from "how".
  • Add stable requirement IDs and AC IDs.
  • Use Given/When/Then AC when behavior can be misread.
  • Check user stories for specific persona, business value, INVEST, happy path, edge path, and negative path.
  • Link each requirement back to BRD-lite business objective.
  • Include risk categories, rollout/ops, decision log, analytics/telemetry, and changelog.
  • Mark unresolved blocking product decisions as blockers.
  • Include a RACI table for BA, PM, architect, backend, frontend, mobile, QA, release, and business/UAT approver when more than one delivery role is involved.
  • Create implementation plan:
  • Define components, contracts, data changes, migrations, risks, and verification.
  • Slice work into fresh-context tasks.
  • Map each task slice to requirement IDs, AC IDs, likely owner role, repo/module, expected artifact, and verification lane.
  • Estimate each slice (t-shirt size + confidence); roll up a delivery-window range in time/cost terms for operator_profile=business, points otherwise.
  • Identify whether design-solution is required before coding.
  • Route:
  • Continue when assumptions are non-critical; return BLOCKED for missing owner, untestable AC, approval, or release constraint.
  • Architecture unclear -> design-solution; approved build-ready plan with AC IDs and trace -> implementation-readiness.

Runtime Contract

  • Use after BRD-lite or when clear feature intent exists but PRD does not.
  • Required inputs: BRD-lite or equivalent intent, plus enough context to name users, goals, and constraints.
  • Return BLOCKED only for missing owner, untestable AC, approval, or release constraint.

Handoff Payload

  • slug, operator_profile, PRD path, REQ-*, AC-*, decisions, RACI, rollout notes, task slices, delivery-window estimate, verification plan, outcome report, next workflow.

Blocking Questions

  • Ask max 3 at a time with a recommended default and 2-3 options.

Output Template

# Feature Plan: [Name]
## PRD
## Problem Statement
## Goals And Guardrails
## Personas / JTBD
## Use Cases
## Requirement Trace
## User Stories And ACs
## Decisions
| Decision   | Choice   | Reason   |
| ---------- | -------- | -------- |
| [decision] | [choice] | [reason] |
## RACI / IT Department Handoff
## Analytics / Telemetry
## Risks And Assumptions
## Rollout / Ops
## Implementation Plan
## Task Slices And Delivery Estimate
## Verification Plan
## Outcome Report
feature_status: requirements_ready | blocked
requirement_trace: BRD-OBJ-* -> REQ-* -> AC-*
completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: design-solution | implementation-readiness
## Next Workflow
design-solution | implementation-readiness
## Cost Report
Call `get_session_cost(workflow="plan-feature")` before final handoff.

Other skills for the same job

different authors, same section of the catalogue
Doc Coauthoring
by anthropics
vendor ×10

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

4k tokens
File Organizer
by frostant
×10

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

3k tokens
Domain Name Brainstormer
by frostant
×8

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

1k tokens
Brainstorming
by ZhanlinCui
×4

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

626 tokens
Planning With Files
by ZhanlinCui
×3

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

9k tokens scripts
Scientific Brainstorming
by christophacham
×3

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

5k tokens
GitHub Project Management
by ComeOnOliver
×3

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

14k tokens
Grill Me
by ComeOnOliver
×3

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

3k tokens

How to use it

Copy the folder

Take hoangnguyen0403/plan-feature from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.