# Pc Estimation

> Use when reviewed tasks exist and the team must size them with explicit assumptions, confidence, and risk awareness before committing to a timeline or sprint scope.

- Skill: `yknothing/pc-estimation` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add yknothing/pc-estimation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yknothing/pc-estimation/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yknothing (https://skillmd.com/u/yknothing)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yknothing/pc-estimation

---


# Estimation

> Estimate to expose uncertainty and trade-offs, not to pretend the future is certain.

## Context

Estimation converts a task list into a planning signal the team can actually use.

See [context](references/context.md) and [anti-pattern](references/anti-patterns.md) notes.

## Inputs

[I/O contract notes](references/io-contract.md) define required inputs and authority.

## Process

### Step 1: Normalize the Unit of Estimation

Pick one estimation approach for the planning horizon: hours, ideal days, story points, or size buckets. Keep it consistent within the same plan.

### Step 2: Estimate Task by Task

For each task, record:

- base size
- confidence level
- key assumptions
- blockers or external dependencies that could widen the range

If the estimate depends on an unresolved question, say so explicitly instead of guessing low.

### Step 3: Calibrate Against Risk and History

Adjust estimates when risk, novelty, or coordination cost makes the base number misleading. Compare against similar recent work when available.

### Step 4: Publish the Estimate Set

Package the estimates in a form sprint or milestone planning can consume directly. Distinguish between:

- confident work
- work with wide uncertainty
- work that should not be scheduled until a risk or dependency is resolved

## Outputs

Produce only declared outputs at their documented quality boundary.

## Quality Gate

- [ ] Every planned task has an estimate
- [ ] Confidence or uncertainty is explicit
- [ ] Key assumptions and blockers are recorded
- [ ] Risk materially changes estimates where appropriate
- [ ] The output is usable by downstream sprint or milestone planning

## Distribution

- Public install surface: `skills/.curated`
- Canonical authoring source: `skills/03-planning/pc-estimation/SKILL.md`
- This package is exported for `npx skills add/update` compatibility.
- Packaging stability: `beta`
- Capability readiness: `beta`
- Portability: `portable_with_caveat`
- Public caveat: Portable as skill guidance; full governance guarantees require the Prodcraft repository contracts and validation checks.