Proceed immediately (no detailed breakdown needed for trivial tasks)
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: elliotjlt-claude-skill-potions-eta3description: ETA4---56# ETA78<purpose>9Provides realistic time estimates for coding tasks before work begins. Users often10underestimate task complexity. This skill analyzes codebase scope, categorizes task11complexity, identifies risk factors, and calculates estimates based on measured12Claude Code performance baselines. Prevents surprise delays and enables better planning.13</purpose>1415## Instructions1617### Step 1: Gather Task Context1819When triggered, collect:20- Task description from the user21- Path to relevant codebase (default: current directory)22- Number of files likely in scope (if known)2324### Step 2: Run Estimation2526```bash27python scripts/estimate_task.py --task "<task_description>" --path "<codebase_path>"28```2930Optional flags:31- `--files <n>`: Override estimated files in scope32- `--json`: Output structured JSON for programmatic use3334### Step 3: Present Estimate3536Return the formatted estimate showing:37- Task category (trivial/simple/medium/complex/major)38- Scope analysis (files, lines, test coverage)39- Time range (low-high estimate)40- Breakdown by phase (analysis, implementation, testing, verification)41- Risk factors with explanations42- Checkpoint recommendations for long tasks4344### Step 4: Adjust Based on Feedback4546If user provides more context:47- Re-run with `--files` override if scope is clearer48- Adjust category interpretation based on domain knowledge4950## NEVER5152- Start a complex task without providing an estimate first53- Give single-point estimates (always provide ranges)54- Ignore risk factors when they're detected55- Skip the estimate for tasks over 15 minutes56- Promise exact completion times5758## ALWAYS5960- Run the estimate script before non-trivial tasks61- Show the breakdown so users understand where time goes62- Flag risk factors visibly with explanations63- Recommend checkpoints for tasks over 30 minutes64- Update estimates if scope changes mid-task6566## Examples6768### Example 1: User asks about task duration6970**Input:** "How long will it take to add user authentication?"7172**Workflow:**731. Run `scripts/estimate_task.py --task "Add user authentication" --path .`742. Output shows:75 - Category: Complex76 - Estimated time: 24-53 minutes77 - Risk factors: High-risk changes, External dependencies78 - Recommendation: Break into phases with commits between each7980### Example 2: Before starting a feature8182**Input:** "Add a dark mode toggle to settings"8384**Workflow:**851. Detect this is a non-trivial task (feature keyword)862. Run `scripts/estimate_task.py --task "Add dark mode toggle to settings" --path ./src`873. Present estimate: 10-22 minutes (Medium complexity)884. Begin implementation with checkpoint plan8990### Example 3: Quick fix request9192**Input:** "Fix the typo in the README"9394**Workflow:**951. Detect trivial task (typo keyword)962. Run quick estimate: 3-6 minutes973. Proceed immediately (no detailed breakdown needed for trivial tasks)9899---100> Converted and distributed by [TomeVault](https://tomevault.io/claim/elliotjlt) — claim your Tome and manage your conversions.101<!-- tomevault:4.0:skill_md:2026-04-11 -->
Run npx skillmds@latest add tomevault-io/elliotjlt-claude-skill-potions-eta in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
ETA It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.