/estimate-calibrator

name: estimate-calibrator
description: 'Produces calibrated three-point PERT estimates (best/likely/worst) with confidence intervals, unknowns, and assumptions. Triggers on: "estimate this", "how long will this take", "effort estimate", "confidence interval", "story points", "t-shirt sizing". NOT for task decomposition, use task-decomposer.'
metadata:
  version: 1.1.1
  category: development
  tags: [estimation, pert, confidence-interval, planning]
  difficulty: intermediate
  phase: plan

Estimate Calibrator

Replaces single-point guesses with structured three-point estimates: decomposes work into atomic units, estimates best/likely/worst case for each, identifies unknowns and assumptions, calculates aggregate ranges using PERT, and assigns confidence levels with explicit rationale.

Reference Files

| File | Contents | Load When | | ---------------------------------- | ------------------------------------------------------------------------- | ---------------------- | | `references/estimation-methods.md` | PERT formula, three-point estimation, Monte Carlo basics | Always | | `references/unknown-categories.md` | Technical, scope, external, and organizational uncertainty types | Unknown identification | | `references/calibration-tips.md` | Cognitive biases in estimation, historical calibration, buffer strategies | Always | | `references/sizing-heuristics.md` | Common task size patterns, complexity indicators, reference class data | Quick sizing needed |

Prerequisites

• Work item description (feature, task, project)
• Decomposed tasks (or use task-decomposer skill first)
• Context: team familiarity, tech stack, existing codebase

Workflow

Phase 1: Decompose Work

If the work item is not already decomposed into atomic units:

1. **Break into tasks** — Each task should be estimable independently. 2. **Right granularity** — Tasks should be 1 hour to 3 days. Larger tasks have higher uncertainty; break them down further. 3. **Identify dependencies** — Tasks on the critical path determine the minimum duration.

Phase 2: Three-Point Estimate

For each task, estimate three scenarios:

| Scenario | Definition | Mindset | | ----------- | --------------------------------------- | --------------------------------------------- | | Best case | Everything goes right. No surprises. | "If I've done this exact thing before" | | Likely case | Normal friction. Some minor obstacles. | "Realistic expectation with typical setbacks" | | Worst case | Significant problems. Not catastrophic. | "Murphy's law but not a disaster" |

**Key rule:** Worst case is NOT "everything goes wrong." It's the realistic bad scenario (90th percentile), not the apocalyptic one (99th percentile).

Phase 3: Identify Unknowns

Categorize unknowns that affect estimates:

| Category | Example | Impact | | -------------- | ------------------------------------- | -------------------------------------------- | | Technical | "Never used this library before" | Likely case inflated, worst case much higher | | Scope | "Requirements may change" | All estimates may shift | | External | "Depends on API access from partner" | Blocking risk — could delay entirely | | Integration | "Haven't tested with production data" | Hidden complexity at integration | | Organizational | "Need design approval" | Calendar time, not effort time |

Phase 4: Calculate Ranges

For individual tasks, use the PERT formula:

Expected = (Best + 4 × Likely + Worst) / 6
Std Dev = (Worst - Best) / 6

For aggregate (project) estimates:

• **Sum of expected values** for total expected duration
• **Root sum of squares of std devs** for aggregate uncertainty

Phase 5: Assign Confidence

| Confidence | Meaning | When | | ---------- | -------------------------------- | --------------------------------------------- | | High | Likely case within ±20% | Well-understood task, team has done it before | | Medium | Likely case within ±50% | Some unknowns, moderate familiarity | | Low | Likely case within ±100% or more | Significant unknowns, new technology |

Output Format

## Estimate: {Work Item}

### Summary
| Scenario | Duration |
|----------|----------|
| Best case | {time} |
| Likely case | {time} |
| Worst case | {time} |
| **PERT expected** | **{time}** |
| **Confidence** | **{High/Medium/Low}** |

### Task-Level Estimates

| # | Task | Best | Likely | Worst | PERT | Unknowns |
|---|------|------|--------|-------|------|----------|
| 1 | {task} | {time} | {time} | {time} | {time} | {key unknown or "None"} |
| 2 | {task} | {time} | {time} | {time} | {time} | {key unknown} |
| | **Total** | **{sum}** | **{sum}** | **{sum}** | **{pert}** | |

### Key Unknowns

| # | Unknown | Category | Impact on Estimate | Mitigation |
|---|---------|----------|-------------------|------------|
| 1 | {unknown} | {Technical/Scope/External} | +{time} if realized | {spike, prototype, early test} |

### Assumptions
- {Assumption 1 — what must be true for this estimate to hold}
- {Assumption 2}

### Risk Factors
- {Risk}: If realized, adds {time}. Likelihood: {High/Medium/Low}.

### Confidence Rationale
**{High/Medium/Low}** because:
- {Specific reason — e.g., "Team has built 3 similar features"}
- {Specific reason — e.g., "External API is a new integration"}

### Recommendation
{Commit to PERT expected with {X}% buffer, or spike the top unknown first.}

Calibration