CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/agnostic-planning-skills

Language-agnostic AI knowledge registry for Technical Project Management, PRDs, PRD review, Software Architecture planning, Task breakdown, Estimation, Risk assessment, Status reporting, Backlog prioritization, Sprint planning, Retrospectives, and Agile ticket generation. Uses Markdown + Front-matter architecture.

95

1.03x
Quality

97%

Does it follow best practices?

Impact

95%

1.03x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

calling-skills.mddocs/

Calling Skills and Agents

Agnostic Planning Skills can be invoked in different ways depending on your environment and desired level of autonomy.

Invocation Methods

MethodSyntaxBest For
Chat Commands@skill-name or /skill-nameExplicitly forcing the agent to follow a specific skill's instructions
CLI (gh skill / skills.sh)gh skill install ...Local installation, pinning versions, reproducible setups

MCP support (use_skill, use_agent) is planned but not yet implemented.


Using Skills

Via Chat Commands

In environments like Cursor, Windsurf, or Gemini CLI:

@create-prd Add Google OAuth login to the app
@review-prd Review the login PRD for completeness
@generate-tasks Break down the approved login PRD
@estimate-tasks Estimate the login task breakdown
@identify-risks Scan the login plan for risks
@prioritize-backlog Rank the remaining feature requests
@plan-tickets Draft tickets for the search feature
@plan-sprint Select tickets and define the sprint goal
@generate-status-report Create a status report for stakeholders
@create-retrospective Generate the sprint retrospective

Using Agents

Agents orchestrate multiple skills through phases with approval gates.

Via Chat Commands

@product-owner Plan the user notification system feature
@project-manager Track execution of the current sprint
@tech-lead Review the notification PRD for feasibility
@delivery-lead Run the full delivery cycle for the notification feature

Installing Skills

Via GitHub CLI

# Install a specific skill
gh skill install igmarin/agnostic-planning-skills create-prd --scope project

# Install all skills
gh skill install igmarin/agnostic-planning-skills

Via skills.sh

[!IMPORTANT] Because this repository has a root-level SKILL.md, you must include the --full-depth flag so the CLI scans and discovers all the nested skills.

Project-Level (Local) Installation

To install skills for your current project workspace:

# Install ALL skills and agents
npx skills add igmarin/agnostic-planning-skills --full-depth --all

# Install a specific skill (e.g., create-prd)
npx skills add igmarin/agnostic-planning-skills@create-prd --full-depth

Global Installation

To install skills globally for your AI coding assistant:

# Install ALL skills and agents globally
npx skills add igmarin/agnostic-planning-skills --full-depth --all --global

# Install a specific skill globally (e.g., create-prd)
npx skills add igmarin/agnostic-planning-skills@create-prd --full-depth --global

Available Skills and Agents

Skills (10)

NameCategoryDescription
create-prdPRDGenerate Product Requirements Documents
review-prdPRDReview PRDs for completeness and feasibility
generate-tasksTask ManagementBreak features into TDD task checklists
plan-ticketsTask ManagementDraft tracker-ready tickets
estimate-tasksTask ManagementAssign effort estimates with confidence levels
prioritize-backlogBacklogRank items using RICE, MoSCoW, or value-vs-effort
plan-sprintCeremonySelect tickets, define goal, allocate capacity
create-retrospectiveCeremonyGenerate sprint retrospectives with action items
identify-risksExecutionScan plans for dependency and capacity risks
generate-status-reportExecutionGenerate stakeholder status reports

Agents (4)

NamePhasesFocus
product-ownerDiscovery → PRD → Tasks → Tickets → SprintScope & planning
project-managerEstimation → Risks → Tracking → ReportsExecution tracking
tech-leadPRD Review → Feasibility → Estimation Quality → ReportTechnical feasibility
delivery-leadScope → Plan → Prioritize → Sprint → Execute → RetrospectEnd-to-end pipeline

docs

agent-guide.md

architecture.md

calling-skills.md

index.md

CODE_OF_CONDUCT.md

CONTRIBUTING.md

README.md

tile.json