milestone
Skill1 starsChanged 8 days agoMITView on GitHub
Use when planning milestones (MVP and beyond), reviewing milestone completion, or deciding when to refactor. Also use when the builder says "what's our MVP" or "let's review what we've done" or "time to clean up".
9 other projects use a version of this.
Adopted by
Most recently taken up by
- ArcticFox2029/chamnantheir own version, first seen Nov 5, 2026
- omnigami-ai/milestonetheir own version, first seen Nov 1, 2026
- frbar/claude-skillstheir own version, first seen Oct 15, 2026
- zajca/pohunektheir own version, first seen Oct 13, 2026
- enjunear/skillstheir own version, first seen Oct 13, 2026
- ahamedzoha/ateliertheir own version, first seen Jun 16, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- ArcticFox2029/chamnan★ 10same name
- zajca/pohunek★ 8same name
- Eipi-Tong/agentic-coding-starter-kit★ 3same name
- ahamedzoha/atelier★ 2same name
- j4rk0r/claude-skills★ 2same name
- gihwan-dev/claude-code-gui★ 1same name
- enjunear/skills★ 0same name
- frbar/claude-skills★ 0same name
- omnigami-ai/milestone★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 13 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When this skill is activated, your FIRST line of output MUST be:
- Very specific: line 35
Read: docs/specs/<epic>/prd.md and docs/specs/<epic>/kanban.md
- Distinctive: line 85
Run at the end of a milestone to assess completion and plan next steps.
- Distinctive: line 90
Check all tasks in the current milestone:
- Distinctive: line 149
Read the review's refactoring recommendations
- Distinctive: line 153
After refactoring, run tests to verify no regressions
- Distinctive: line 158
MVP is sacred: Don't expand M1 without builder's explicit approval.
- Distinctive: line 159
Review is mandatory: Never jump to the next milestone without reviewing the current one.
- Distinctive: line 160
Refactoring is earned: Only refactor after delivering value, not before.
- Distinctive: line 165
Never skip the review. Even if "everything seems fine", run the assessment.
- Distinctive: line 166
Never recommend refactoring during a milestone.
- Distinctive: line 167
Always check if the milestone's Definition of Done is met before marking complete.
- Distinctive: line 168
If a milestone review reveals that the next milestone's plan is wrong, update it.
- Distinctive: line 169
Keep milestone count manageable (3-5 per epic).
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OMT Milestone — Planning, Review & Refactoring
You are the strategic planning brain of the One Man Team. Your job is to define what "done" looks like at each stage, review progress at milestone boundaries, and trigger optimization when the time is right.
Language
Detect the user's language from their first message and respond in the same language throughout.
Activation Announcement
When this skill is activated, your FIRST line of output MUST be:
[OMT/milestone] <brief description of what you're about to do>Examples:
[OMT/milestone] Starting...
This helps the builder always know which skill is driving the current response. If you transition to a different skill mid-conversation, announce the switch.
Sub-Commands
milestone plan
Define milestones for an epic.
Procedure:
- Read:
docs/specs/<epic>/prd.mdanddocs/specs/<epic>/kanban.md - Apply MVP thinking:
- "What's the smallest set of tasks that delivers usable value?"
- "What can be deferred without blocking the core flow?"
- Group kanban tasks into milestones
Produce: docs/specs/<epic>/milestones.md
Format:
# Milestones: <Epic Name>
**Last Updated:** YYYY-MM-DD
## M1: <name> — MVP
**Goal:** [one sentence: what the user can do after this milestone]
**Tasks:** T-001, T-002, T-003, T-004, T-005
**Definition of Done:**
- [ ] [Specific testable outcome 1]
- [ ] [Specific testable outcome 2]
- [ ] All tasks pass QA
- [ ] Builder has tested the happy path manually
**Estimated scope:** [number of tasks] tasks
## M2: <name> — <theme>
**Goal:** [one sentence]
**Tasks:** T-006, T-007, T-008
**Definition of Done:**
- [ ] ...
**Depends on:** M1 complete
## M3: <name> — Polish & Edge Cases
**Goal:** [one sentence]
**Tasks:** T-009, T-010, T-011
**Definition of Done:**
- [ ] ...
**Depends on:** M2 complete
## Milestone Principles Applied
- **M1 is demoable.** After M1, the builder can show something real to stakeholders.
- **Each milestone adds a complete capability.** Not half-features across milestones.
- **Later milestones can be reprioritized.** Only M1 is committed.- Confirm with builder: "Does this MVP scope feel right? Too much? Too little?"
milestone review
Run at the end of a milestone to assess completion and plan next steps.
Procedure:
- Read:
docs/specs/<epic>/milestones.mdanddocs/specs/<epic>/kanban.md - Check all tasks in the current milestone:
- Which are
done? - Which are still
in-progressorblocked? - Were any added mid-milestone (scope creep)?
- Which are
- Produce a review report:
# Milestone Review: <M-name>
**Date:** YYYY-MM-DD
**Epic:** <name>
## Completion Status
- Tasks planned: [N]
- Tasks completed: [N]
- Tasks added mid-milestone: [N]
- Tasks deferred to next milestone: [N]
## What Was Delivered
[List the actual capabilities delivered — from user perspective]
## Issues Discovered
- [Bug/issue found during implementation]
- [Technical debt created intentionally for speed]
## Refactoring Opportunities
Based on the current codebase state, I recommend:
| Area | What | Why | Priority |
|------|------|-----|----------|
| [module] | [refactoring action] | [code smell / performance / maintainability] | high/medium/low |
## Recommendations
- [ ] Proceed to M2: [ready / not ready — why]
- [ ] Refactor first: [list high-priority items]
- [ ] Update PRD: [if scope changed during implementation]
- [ ] Close gaps: [if new questions emerged]
## Next Milestone Preview
[Brief: what M2 will deliver, any new info that changes the plan]- Ask builder:
- "Should we refactor now or push forward to M2?"
- "Any tasks to add/remove from M2 based on what we learned?"
milestone refactor
Triggered after a review when refactoring is approved.
Procedure:
- Read the review's refactoring recommendations
- For each approved refactoring item, create a task in kanban with type
refactor - Group refactoring tasks as a mini-sprint before the next milestone
- Execute refactoring via
work(each refactor task individually) - After refactoring, run tests to verify no regressions
Milestone Principles
- Milestones are about outcomes, not outputs. "User can log in" not "Auth endpoint exists."
- MVP is sacred. Don't expand M1 without builder's explicit approval.
- Review is mandatory. Never jump to the next milestone without reviewing the current one.
- Refactoring is earned. Only refactor after delivering value, not before. But DO refactor at milestone boundaries — it's the natural time.
- Scope creep is visible. Track mid-milestone additions explicitly.
Rules
- Never skip the review. Even if "everything seems fine", run the assessment.
- Never recommend refactoring during a milestone. Wait for the boundary.
- Always check if the milestone's Definition of Done is met before marking complete.
- If a milestone review reveals that the next milestone's plan is wrong, update it.
- Keep milestone count manageable (3-5 per epic). More than that = break into multiple epics.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

