Agent skill
task-estimation
Estimate software development tasks accurately using various techniques. Use when planning sprints, roadmaps, or project timelines. Handles story points, t-shirt sizing, planning poker, and estimation best practices.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/supercent-io/task-estimation
Metadata
Additional technical details for this skill
- tags
- estimation, agile, sprint-planning, story-points, planning-poker
- platforms
- Claude, ChatGPT, Gemini
SKILL.md
Task Estimation
When to use this skill
- Sprint Planning: Decide what work to include in the sprint
- Roadmap creation: Build long-term plans
- Resource planning: Estimate team size and schedule
Instructions
Step 1: Story Points (relative estimation)
Fibonacci sequence: 1, 2, 3, 5, 8, 13, 21
## Story Point guidelines
### 1 Point (Very Small)
- Example: text change, constant value update
- Time: 1-2 hours
- Complexity: very low
- Risk: none
### 2 Points (Small)
- Example: simple bug fix, add logging
- Time: 2-4 hours
- Complexity: low
- Risk: low
### 3 Points (Medium)
- Example: simple CRUD API endpoint
- Time: 4-8 hours
- Complexity: medium
- Risk: low
### 5 Points (Medium-Large)
- Example: complex form implementation, auth middleware
- Time: 1-2 days
- Complexity: medium
- Risk: medium
### 8 Points (Large)
- Example: new feature (frontend + backend)
- Time: 2-3 days
- Complexity: high
- Risk: medium
### 13 Points (Very Large)
- Example: payment system integration
- Time: 1 week
- Complexity: very high
- Risk: high
- **Recommended**: Split into smaller tasks
### 21+ Points (Epic)
- **Required**: Must be split into smaller stories
Step 2: Planning Poker
Process:
- Product Owner explains the story
- Team asks questions
- Everyone picks a card (1, 2, 3, 5, 8, 13)
- Reveal simultaneously
- Explain highest/lowest scores
- Re-vote
- Reach consensus
Example:
Story: "Users can upload a profile photo"
Member A: 3 points (simple frontend)
Member B: 5 points (image resizing needed)
Member C: 8 points (S3 upload, security considerations)
Discussion:
- Use an image processing library
- S3 is already set up
- File size validation needed
Re-vote → consensus on 5 points
Step 3: T-Shirt Sizing (quick estimation)
## T-Shirt sizes
- **XS**: 1-2 Story Points (within 1 hour)
- **S**: 2-3 Story Points (half day)
- **M**: 5 Story Points (1-2 days)
- **L**: 8 Story Points (1 week)
- **XL**: 13+ Story Points (needs splitting)
**When to use**:
- Initial backlog grooming
- Rough roadmap planning
- Quick prioritization
Step 4: Consider risk and uncertainty
Estimation adjustment:
interface TaskEstimate {
baseEstimate: number; // base estimate
risk: 'low' | 'medium' | 'high';
uncertainty: number; // 0-1
finalEstimate: number; // adjusted estimate
}
function adjustEstimate(estimate: TaskEstimate): number {
let buffer = 1.0;
// risk buffer
if (estimate.risk === 'medium') buffer *= 1.3;
if (estimate.risk === 'high') buffer *= 1.5;
// uncertainty buffer
buffer *= (1 + estimate.uncertainty);
return Math.ceil(estimate.baseEstimate * buffer);
}
// Example
const task = {
baseEstimate: 5,
risk: 'medium',
uncertainty: 0.2 // 20% uncertainty
};
const final = adjustEstimate(task); // 5 * 1.3 * 1.2 = 7.8 → 8 points
Output format
Estimation document template
## Task: [Task Name]
### Description
[work description]
### Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
### Estimation
- **Story Points**: 5
- **T-Shirt Size**: M
- **Estimated Time**: 1-2 days
### Breakdown
- Frontend UI: 2 points
- API Endpoint: 2 points
- Testing: 1 point
### Risks
- Uncertain API response time (medium risk)
- External library dependency (low risk)
### Dependencies
- User authentication must be completed first
### Notes
- Need to discuss design with UX team
Constraints
Required rules (MUST)
- Relative estimation: Relative complexity instead of absolute time
- Team consensus: Agreement from the whole team, not individuals
- Use historical data: Plan based on velocity
Prohibited (MUST NOT)
- Pressuring individuals: Estimates are not promises
- Overly granular estimation: Split anything 13+ points
- Turning estimates into deadlines: estimate ≠ commitment
Best practices
- Break Down: Split big work into smaller pieces
- Reference Stories: Reference similar past work
- Include buffer: Prepare for the unexpected
References
Metadata
Version
- Current version: 1.0.0
- Last updated: 2025-01-01
- Compatible platforms: Claude, ChatGPT, Gemini
Tags
#estimation #agile #story-points #planning-poker #sprint-planning #project-management
Examples
Example 1: Basic usage
Example 2: Advanced usage
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?