
Task Effort Estimator
Gives a structured effort range, risks and confidence level for a coding task, based on the codebase.
- Repository
- Donchitos/Claude-Code-Game-Studios
- Stars
- 32,965
- Licence
- MIT
- Files
- 1 file
What it does
When you ask it to estimate a task, the agent reads your project notes (CLAUDE.md), any related design documents and past sprint records, then scans the affected code files by counting lines and branching statements. It then produces a report with optimistic, expected and pessimistic day estimates, a recommended budget, a confidence level, risks, dependencies and a suggested task breakdown. It is read-only and does not change any files.
Great for
- Engineering leads planning sprints for a game or software project that uses the Claude Code Game Studios setup
- Developers who want a second opinion on how big a feature is before committing to it
- Teams that keep design documents and sprint history in the repository so the estimate can be grounded in them
Skip it if
- Projects with no sprint history or documented codebase: the estimate will be uncalibrated and low-confidence, so treat it as a rough guess (the skill itself says so)
- Precise scheduling or commitments to clients: the output is heuristic, based on line counts and branch counts rather than measured complexity or real velocity data
Try asking
- “/estimate add inventory trading between players”
- “/estimate migrate the save system to the new file format”
- “/estimate add a pause menu to the HUD”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
estimate.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip estimate.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip estimate.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give a specific task description; vague requests make the skill ask for clarification and produce lower-confidence estimates.
- Keep design documents and sprint records in the repo so the estimate can use them; otherwise expect a Low confidence rating.
- Treat the line and branch counts as rough signals, not measured complexity, and check the flagged risks before committing to dates.
What's inside
- SKILL.md
Redistributed unmodified from Donchitos/Claude-Code-Game-Studios under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.