OpenParable
Skip to content
← Back to skills

Estimating Work

Productivity
estimating-work

Estimating Work is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Estimate effort for development tasks. Use when planning sprints, roadmaps, or project timelines. Covers story points, relative estimation, and uncertainty.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/estimating-work/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/estimating-work, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Estimating Work

Estimation Approaches

Story Points

Relative complexity, not time.

PointsComplexity
1Trivial, well understood
2Simple, minor unknowns
3Moderate complexity
5Complex, some unknowns
8Very complex, significant unknowns
13Extremely complex, many unknowns
21+Too big, needs decomposition

T-Shirt Sizing

For high-level estimates.

SizeRelative Effort
XSHours
S1-2 days
M3-5 days
L1-2 weeks
XL2-4 weeks

Estimation Factors

Consider:

  • Complexity: How difficult is the problem?
  • Uncertainty: How much is unknown?
  • Effort: How much work is involved?
  • Risk: What could go wrong?

Estimation Techniques

Planning Poker

  1. Present the task
  2. Everyone selects estimate privately
  3. Reveal simultaneously
  4. Discuss outliers
  5. Re-estimate if needed

Three-Point Estimation

Expected = (Optimistic + 4×Likely + Pessimistic) / 6

Reference Stories

Keep calibration stories:

  • "This 3-point story took 2 days"
  • "This 8-point story took a week"

Common Pitfalls

  • Anchoring: First estimate biases others
  • Optimism: Underestimating unknowns
  • Scope Creep: Original estimate doesn't match final scope
  • Ignoring Overhead: Code review, testing, deployment

Tips

  1. Estimate in ranges, not points
  2. Include buffer for unknowns
  3. Track actual vs. estimated
  4. Re-estimate when scope changes
  5. Don't estimate in hours (use relative sizing)