Estimation
Estimate the work for "$ARGUMENTS". Select an estimation method, establish reference stories for calibration, estimate each story relative to references, flag stories needing splitting, and calculate total backlog size and sprint projections.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"project-management-estimation","workflow":"project-management","phase":1,"project":"<project>","event":"skipped","artifact":"01-plan.md","note":"<reason or \"none given\">"}.
Prerequisites
Part of a workflow. This skill is phase 1 (Plan) of the Scrum workflow (project-management); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or project-management when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"project-management-estimation","workflow":"project-management","phase":1,"project":"<project>","event":"refused","artifact":"01-plan.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"project-management-estimation","workflow":"project-management","phase":1,"project":"<project>","event":"started","artifact":"01-plan.md","note":""}.
Check that .singularskills/project-management/<project>/00-initiate.md exists. If it does not, tell the user to run an Initiate skill first (e.g., project-charter) and stop.
Process
Read existing context:
- Read
.singularskills/project-management/<project>/00-initiate.mdfor charter and team context - Read
.singularskills/project-management/<project>/01-plan.mdif it exists (for backlog, user stories, and roadmap) - Read
references/scrum-guide.mdfor Scrum alignment
- Read
Select the estimation method:
- Story points with Fibonacci scale (recommended): 1, 2, 3, 5, 8, 13, 21 — measures relative complexity, effort, and uncertainty
- T-shirt sizing: XS, S, M, L, XL — useful for early rough estimation before detailed planning
- Planning poker: team-based estimation using story points with discussion rounds
- Document the selected method and rationale
- If the team has an existing preference, use that
Establish reference stories (calibration):
- Select 2-3 well-understood stories from the backlog as reference points:
- "1" story — the simplest meaningful change (e.g., update a label, add a tooltip)
- "5" story — moderate complexity (e.g., build a form with validation, add a new API endpoint)
- "8" story — significant complexity (e.g., implement a multi-step workflow, add a new integration)
- Document why each reference story was chosen and what makes it that size
- These references anchor all subsequent estimates
- Select 2-3 well-understood stories from the backlog as reference points:
Estimate each story relative to references:
- Compare each story to the reference stories: is it simpler, similar, or more complex?
- Assign a story point value from the Fibonacci scale
- Consider three dimensions: complexity (how hard?), effort (how much work?), uncertainty (how unknown?)
- Document brief rationale for estimates that may be surprising (very high or very low)
- For T-shirt sizing: map XS=1, S=2, M=3-5, L=8, XL=13+
Flag stories that need splitting:
- Any story estimated at >13 points should be flagged for splitting
- Stories at 13 points should be reviewed — can they be split for lower risk?
- For flagged stories, suggest splitting strategies (by workflow, data variation, operation, or persona)
- Re-estimate the split stories
Calculate total backlog size:
- Sum all story points across the entire backlog
- Break down by epic, theme, priority (Must/Should/Could), and release milestone
- Calculate MVP size (total points for Must-have or Release 1 stories)
- Identify the largest epics and any estimation outliers
Estimate sprint and timeline projections:
- For new teams: assume velocity of 20-30 points per sprint (start conservative at 20)
- For existing teams: use average of last 3 sprints as velocity baseline
- Calculate: number of sprints = total backlog size / expected velocity
- Project timeline: number of sprints x sprint length
- Calculate MVP delivery estimate separately
- Add buffer: +20% for known risks, +40% for high-uncertainty projects
- Compare projected timeline with roadmap milestones — flag misalignments
Write the artifact — append to
.singularskills/project-management/<project>/01-plan.mdunder a## Estimationsection. Create the file with a# Plan — <project>heading if it does not exist; if a## Estimationsection already exists, replace only that section. The section contains:- Method — selected estimation approach and rationale
- Reference Stories — calibration stories with point values and rationale
- Estimated Backlog — each story with its estimate, organized by epic
- Stories to Split — flagged stories with recommended splitting strategies
- Backlog Size Summary — total points, breakdown by epic/priority/release
- Sprint Projections — velocity assumption, number of sprints, projected timeline, buffer
Output
Estimation appended to .singularskills/project-management/<project>/01-plan.md. Present a summary highlighting:
- Estimation method used and reference stories selected
- Total backlog size in story points
- MVP size and estimated delivery timeline
- Number of stories flagged for splitting
- Projected number of sprints with buffer
Record the run. After you have written your section, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"project-management-estimation","workflow":"project-management","phase":1,"project":"<project>","event":"finished","artifact":"01-plan.md","note":""}.
This artifact is shared by every skill of phase 1 (Plan). The frontmatter is written once, by whoever creates the file: if you create it, open it with the block below (skill is the phase title, started the time of that first write; gate is passed when the gate ran clean and skipped under --skip-checks); if it already exists, leave the block alone except to update finished and to set gate to the worst value among the sections (skipped over passed).
---
skill: Plan
workflow: project-management
phase: 1
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
Open your ## Estimation section with one italic line, *<skill name> · <ISO timestamp> · gate: <passed|skipped>* (your skill name is project-management-estimation).
End your section with ### Decisions and ### Open questions (one level under your ## Estimation heading, so the section stays one block), in this shape:
### Decisions
- <what was chosen> — <why> — <what was rejected>
### Open questions
- <what the next phase or a reviewer must settle>