milestone-review
Skill2 starsChanged 3 months agoMITView on GitHub
Verify an Ephesus milestone's exit criteria before declaring it done — run the named scenario suites, check every package's evidence, update PROGRESS.md, and produce an architect-facing review. Use when a milestone looks complete or the user asks "are we done with M<x>?".
19 other projects use a version of this.
Adopted by
Most recently taken up by
- tatashbar/Economic-Modeling-Studiotheir own version, first seen Nov 16, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Nov 9, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- zajca/pohunektheir own version, first seen Oct 13, 2026
Used with
Projects with it also use soak-test, team-live-ops and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
- +10 more from lilangMax
Other versions19 projects use a version of this.
Word for word · 1
- mertefesensoy/Ephesus★ 2100% same
Edited · 0
None found.
Wrote their own version · 18
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- striderZA/OpenCodeGameStudios★ 124same name
- tranhieutt/software_development_department★ 71same name
- cenconq25/claude-code-app-studio★ 40same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- dawn840705/codex-code-studios★ 17same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
- zajca/pohunek★ 9same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
8 more not listed
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.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-packageSkill
- doc-syncSkill
- ephesus-engineerSkill
- goalSkill
- improveSkill
- researchSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read its section in docs/IMPLEMENTATION.md and list its exit criteria and
- Very specific: line 13
Run the milestone's S-suites (specs in docs/TEST-STRATEGY.md §3).
- Very specific: line 19
Write the verdict into docs/PROGRESS.md under the milestone: DONE (with evidence links) or NOT DONE (with the precise gap list as new …
- Distinctive: line 26
Never soften a criterion to close a milestone.
“Common” is measured: kept by at least 6 in 10 of the 17 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
Milestone exit review
- Identify the milestone under review from
docs/PROGRESS.md. - Read its section in
docs/IMPLEMENTATION.mdand list its exit criteria and named scenario suites (S-*) verbatim. - For each exit criterion: verify it by running it, not by reading code. Record the command and observed result. A criterion nobody ran is unmet.
- Run the milestone's S-suites (specs in
docs/TEST-STRATEGY.md§3). All must pass. A suite that doesn't exist yet means the milestone is NOT done — implementing it is part of the milestone. - Sweep for debt that blocks closing: unchecked packages, TODO/stub markers in
milestone code (
grep -rn "TODO\|FIXME" src/), must-ask questions still open in past session reports, docs that now lie about the code (run/doc-sync). - Write the verdict into
docs/PROGRESS.mdunder the milestone: DONE (with evidence links) or NOT DONE (with the precise gap list as new unchecked items). Update the Resume here block and the milestone index in the same commit. When the milestone closes, move its section verbatim todocs/progress/M<x>.md(relative links rebased one folder, nothing else changed) and carry anything it leaves open into the block. - Report to the Architect: verdict first, then the evidence table, then gaps.
Never soften a criterion to close a milestone. If a criterion seems wrong, that is a must-ask for the Architect, not a judgment call.
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.

