AI assistants need planning discipline.
This library adds it.

Ten skills. Four agents. One non-negotiable rule: no code without an approved plan. Turn your AI from eager coder into disciplined product collaborator — regardless of your tech stack.

Works with ChatGPT, Claude, Cursor, Copilot, Gemini, Windsurf, OpenCode

The Problem

AI assistants skip planning. That's the bug.

By default, AI coding assistants jump straight to code. No PRD. No task breakdown. No risk assessment. They generate plausible-looking output that passes a glance but lacks structure, test coverage, and traceable scope.

BEFORE — AI Without Planning Skills User: "Add Google OAuth login" AI: Writes auth.ts, installs passport, adds routes Result: Untested code, unclear scope, no review gate AFTER — AI With Agnostic Planning Skills User: "@create-prd Add Google OAuth login" AI: Drafts PRD → Gate: "Approve before code?" Result: Structured scope, TDD tasks, tracker tickets

The Mental Model

Think of it as a planning conveyor belt — with safety stops.

Every feature travels through stages before code is written. Each stage produces an artifact and gates block progress until the artifact is reviewed. You can enter and exit at any stage.

create-prd What & Why review-prd Is it good? generate-tasks TDD checklist plan-tickets Tracker drafts plan-sprint Sprint goal GATE GATE GATE PRD Approved Review Passes Sprint Confirmed estimate-tasks Story points identify-risks Risk register prioritize-backlog RICE / MoSCoW generate-status-report Executive Summary · Accomplishments · Blocked · Next Steps create-retrospective What went well & action items

The full pipeline: create-prd → review-prd → [Gate] → generate-tasks → estimate-tasks → identify-risks → prioritize-backlog → plan-tickets → plan-sprint → generate-status-report → create-retrospective

The Rule

No implementation without an approved PRD.

This one rule is encoded into every skill and agent. The PRD is the single source of truth for scope. Every HARD-GATE blocks the AI from proceeding until you explicitly approve the artifact.

HARD-GATE: PRD Approval

The AI must present the PRD draft and wait for explicit approval. It cannot generate tasks, create tickets, or write a single line of code until you say yes.

HARD-GATE: Ticket Approval

Tickets are always draft-only by default. The AI will not create issues in your tracker unless you explicitly ask it to. No ghost tickets.

HARD-GATE: Sprint Commitment

The agent does not assume sprint IDs, capacity, or team availability. Sprint placement must be explicitly confirmed by you.

The Tools

10 skills, 5 categories. Each is a single SKILL.md file.

Every skill has the same structure: frontmatter, quick reference, HARD-GATE rules, step-by-step process, output template, and integration table. They auto-detect your project's tooling — no config needed.

PRD

1 create-prd Skill

Generate a structured Product Requirements Document from a feature description: goals, user stories, functional requirements, success metrics, and open questions.

@create-prd Add Google OAuth login
2 review-prd Skill

Evaluate PRDs for completeness, testability, clarity, and feasibility. Findings classified as Critical, Suggestion, or Note. Every finding cites specific document evidence.

@review-prd Review the login PRD

Task Management

3 generate-tasks Skill

Break a feature into TDD task checklists. Task 0.0 is always "create feature branch." Uses TDD quadruplet: write test → watch it fail → implement → watch it pass.

@generate-tasks Break down the approved login PRD
4 plan-tickets Skill

Draft tracker-ready tickets with classification by type, area, execution order, and dependency level. Default: draft-only. Never creates tickets without explicit permission.

@plan-tickets Draft tickets for the search feature
5 estimate-tasks Skill

Assign effort estimates using story points (Fibonacci: 1,2,3,5,8,13), t-shirt sizes (XS–XL), or time ranges. Every estimate includes a confidence level: High, Medium, or Low.

@estimate-tasks Estimate the login task breakdown

Backlog

6 prioritize-backlog Skill

Rank items using RICE (Reach × Impact × Confidence / Effort), MoSCoW, value-vs-effort matrix, or WSJF. Must state rationale for every ranking decision.

@prioritize-backlog Rank the remaining feature requests

Ceremony

7 plan-sprint Skill

Select tickets from a prioritized backlog. Define a single sprint goal. Cap capacity at 80% of velocity. Uses team_size × sprint_days × 6h × utilization_factor.

@plan-sprint Select tickets and define the sprint goal
8 create-retrospective Skill

Generate structured retrospectives: What Went Well, What Didn't, Action Items (with Owner + Timeline), Metrics, and Kudos. Every "what didn't" must have a linked action item.

@create-retrospective Generate the sprint retrospective

Execution

9 identify-risks Skill

Scan plans for 6 risk patterns: dependency chains, single points of failure, ambiguous requirements, external dependencies, capacity issues, and technical uncertainty. Every risk cites specific evidence from the plan.

@identify-risks Scan the login plan for risks
10 generate-status-report Skill

Produce stakeholder status reports: Executive Summary, Accomplishments, In Progress, Blocked, Risks, Next Steps. Never fabricates progress — marks unknown items as "needs update."

@generate-status-report Create a status report

The Orchestrators

4 agents chain skills together. Each has a role, phases, and hard gates.

Agents don't just run one skill. They walk through a lifecycle: Discovery → Draft → Review → Estimate → Ticket → Sprint. Each agent has approval gates that pause the flow until you confirm.

PO
product-owner Planning lifecycle

Discovery → PRD Draft → Review & Revise → Task Estimation → Ticket Generation → Sprint Placement

create-prd generate-tasks plan-tickets
PM
project-manager Execution tracking

Estimation → Risk Assessment → Tracking Setup → Status Reporting

estimate-tasks identify-risks generate-status-report
TL
tech-lead Technical review

PRD Review → Feasibility Assessment → Estimation Quality Review → Technical Risk Report. Produces Go/No-Go/Go-with-Conditions.

review-prd estimate-tasks
DL
delivery-lead Full delivery cycle

Scope → Plan → Prioritize → Sprint → Execute → Retrospect. The meta-agent — orchestrates all 10 skills across the complete delivery lifecycle.

All 10 skills

Walkthrough

From a one-line feature request to a ready-for-development sprint.

Here's what happens when you use three skills in sequence on a real feature.

1

You start with a feature idea

@create-prd Add Google OAuth login

The AI reads the project context, then drafts a structured PRD in markdown — saved to /tasks/prd-google-oauth-login.md. It covers goals, user stories (login with Google, account linking, error handling), functional requirements, non-goals (no password fallback), design considerations, and success metrics.

2

You review and approve the PRD

The AI stops and asks: "Does this PRD capture the right scope? Anything to add or remove?" The gate holds. No tasks, no tickets, no code — until you say "approved." You can also invoke @review-prd for a structured quality check with findings classified as Critical, Suggestion, or Note.

3

The AI generates a TDD task checklist

@generate-tasks Break down the approved login PRD

Each feature turns into a task quadruplet:

Task 0.0: Create feature branch feat/google-oauth-login
Task 1.1a: Write test for Google OAuth callback handler
Task 1.1b: Run test — confirm it fails
Task 1.1c: Implement /auth/google/callback route
Task 1.1d: Run test — confirm it passes

The AI auto-detected your test command (npm test) from package.json and source directory (src/).

4

The AI drafts tracker-ready tickets

@plan-tickets Draft tickets for the Google OAuth feature

Each ticket gets classification — type (feature), area (auth), execution order (1), dependency level (none), target bucket (current sprint). The five-section format includes title, description, acceptance criteria, technical notes, and definition of done. Still draft-only — the AI waits for your go-ahead before creating issues in GitHub, Jira, or Linear.

You're now ready for development.

What was one vague sentence is now a reviewed PRD, a TDD task checklist with exact file paths, and draft tickets classified for your tracker. You have clear scope, test-first tasks, and no ambiguity about what to build next.

No Config Required

Works with any tech stack. It reads your project, not your mind.

Skills auto-detect your environment by inspecting the files already in your repository. No manual configuration, no setup file, no framework lock-in.

Skills auto-detect your project conventions package.json → npm test Gemfile → bundle exec rspec Cargo.toml → cargo test src/ source dir detected __tests__/ test dir detected JSDoc/YARD doc tool detected

Get Started

Two install commands, one chat command. That's it.

GitHub CLI

Requires gh v2.90.0+

gh skill install igmarin/agnostic-planning-skills
gh skill install igmarin/agnostic-planning-skills create-prd --scope project

skills.sh

Requires skills.sh CLI

npx skills add igmarin/agnostic-planning-skills --full-depth --all
npx skills add igmarin/agnostic-planning-skills@create-prd --full-depth --global

Your first command

@create-prd Your feature idea here

The AI drafts a PRD, stops for your approval, and only proceeds when you say yes. That's the gate working. That's the whole point.

Quick Reference

Which path should you take?

You don't need to run the full pipeline every time. Pick the path that matches your need.

New feature from scratch

@create-prd
@review-prd
@generate-tasks
@plan-tickets

Prioritize existing work

@prioritize-backlog
@plan-sprint

Full delivery cycle

@delivery-lead

Orchestrates all 10 skills across 6 phases

Remember This

"No implementation without an approved PRD."

If you take one idea from this page, take that. Every skill, every agent, every gate in this library exists to enforce that one rule. The AI becomes a planning partner, not a code cannon. Scope is explicit. Tests are written first. Nothing ships by accident.

github.com/igmarin/agnostic-planning-skills · MIT License · v3.0.7