# Eta

> |

- **Type:** Skill
- **Install:** `agentstack add skill-elliotjlt-claude-skill-potions-eta`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ElliotJLT](https://agentstack.voostack.com/s/elliotjlt)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ElliotJLT](https://github.com/ElliotJLT)
- **Source:** https://github.com/ElliotJLT/Claude-Skill-Potions/tree/main/skills/eta

## Install

```sh
agentstack add skill-elliotjlt-claude-skill-potions-eta
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ETA

Provides realistic time estimates for coding tasks before work begins. Users often
underestimate task complexity. This skill analyzes codebase scope, categorizes task
complexity, identifies risk factors, and calculates estimates based on measured
Claude Code performance baselines. Prevents surprise delays and enables better planning.

## Instructions

### Step 1: Gather Task Context

When triggered, collect:
- Task description from the user
- Path to relevant codebase (default: current directory)
- Number of files likely in scope (if known)

### Step 2: Run Estimation

```bash
python scripts/estimate_task.py --task "" --path ""
```

Optional flags:
- `--files `: Override estimated files in scope
- `--json`: Output structured JSON for programmatic use

### Step 3: Present Estimate

Return the formatted estimate showing:
- Task category (trivial/simple/medium/complex/major)
- Scope analysis (files, lines, test coverage)
- Time range (low-high estimate)
- Breakdown by phase (analysis, implementation, testing, verification)
- Risk factors with explanations
- Checkpoint recommendations for long tasks

### Step 4: Adjust Based on Feedback

If user provides more context:
- Re-run with `--files` override if scope is clearer
- Adjust category interpretation based on domain knowledge

## NEVER

- Start a complex task without providing an estimate first
- Give single-point estimates (always provide ranges)
- Ignore risk factors when they're detected
- Skip the estimate for tasks over 15 minutes
- Promise exact completion times

## ALWAYS

- Run the estimate script before non-trivial tasks
- Show the breakdown so users understand where time goes
- Flag risk factors visibly with explanations
- Recommend checkpoints for tasks over 30 minutes
- Update estimates if scope changes mid-task

## Examples

### Example 1: User asks about task duration

**Input:** "How long will it take to add user authentication?"

**Workflow:**
1. Run `scripts/estimate_task.py --task "Add user authentication" --path .`
2. Output shows:
   - Category: Complex
   - Estimated time: 24-53 minutes
   - Risk factors: High-risk changes, External dependencies
   - Recommendation: Break into phases with commits between each

### Example 2: Before starting a feature

**Input:** "Add a dark mode toggle to settings"

**Workflow:**
1. Detect this is a non-trivial task (feature keyword)
2. Run `scripts/estimate_task.py --task "Add dark mode toggle to settings" --path ./src`
3. Present estimate: 10-22 minutes (Medium complexity)
4. Begin implementation with checkpoint plan

### Example 3: Quick fix request

**Input:** "Fix the typo in the README"

**Workflow:**
1. Detect trivial task (typo keyword)
2. Run quick estimate: 3-6 minutes
3. Proceed immediately (no detailed breakdown needed for trivial tasks)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ElliotJLT](https://github.com/ElliotJLT)
- **Source:** [ElliotJLT/Claude-Skill-Potions](https://github.com/ElliotJLT/Claude-Skill-Potions)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-elliotjlt-claude-skill-potions-eta
- Seller: https://agentstack.voostack.com/s/elliotjlt
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.