hillclimb
Skill4 starsChanged 33 days agoApache-2.0View on GitHub
Pick the next game capability to build from the cosmos sweep, build it as one composed concept rather than value by value, and re-sweep. Use when choosing or starting game-making work (cameras, topology, combat, quests, shots, passage of time…), when asked "what should we build next" or "what can we make", or after a capability lands, to record the move.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- niilohlin/skillstheir own version, first seen Nov 16, 2026
- markjoshwel/skillstheir own version, first seen Nov 16, 2026
- adelrodriguez/skillstheir own version, first seen Nov 15, 2026
- kadeski/skillstheir own version, first seen Nov 14, 2026
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- Suge8/friedbuntheir own version, first seen Nov 8, 2026
Used with
Projects with it also use grill-me.
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.
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- rebase-energy/hillclimb★ 37same name
- Suge8/friedbun★ 13same name
- michielvandermeer/skills★ 9same name
- jonmumm/skills★ 3same name
- paureis/pau-skills★ 2same name
- adelrodriguez/skills★ 1same name
- Astatide1337/Skills★ 1same name
- kadeski/skills★ 1same name
5 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- figure-studySkill
- find-unused-locale-keysSkill
- head-studySkill
- historic-cultureSkill
- sketchSkill
- skull-studySkill
- sync-localesSkill
- view-svgSkill
- write-catalystSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Read docs/tool-surface/hillclimb.md.
“Common” is measured: kept by at least 6 in 10 of the 14 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
/hillclimb
The cosmos cube (control/lib/graph/cosmos) describes a game as six facets of settings; the registry marks each
value built, local, partial or absent. The sweep rolls worlds and asks which are makeable. This skill turns that
into the next build. Internal: nothing here is an MCP surface.
1. Read where it stands
cd control && npm run tool-surfaceRead docs/tool-surface/hillclimb.md. It ranks three ways:
- One at a time: packages by worlds lifted per unit of effort. Cheap and high is the default pick.
- Recipes: the exact package sets worlds wait on. A recipe many worlds share is a target worth building whole.
- Pairs with synergy: worlds made only when both are built. High synergy means one concept split in two: build
them together, and declare them one package in
lib/graph/cosmos/packages.js(members name it withpkg).
An unpriced row ("–") cannot be compared. Price it first (effort: 'S' | 'M' | 'L' on the registry value, or on the
package) from a read-only look at what exists, then regenerate.
2. Choose, and say why
Name the pick, the rows it comes from, and what else it moves: the genre probes it touches, and whether it is web-only
(godot: false). Prefer a composed concept (a package, a recipe, a synergy pair) over a single value when the page
shows one. Confirm with the operator before building.
3. Build it the house way
- The plan section and the Unreleased changelog entry before code (CLAUDE.md, Plans and changelog).
- Opt-in: an absent key keeps every byte; char and trace pins re-pinned only with a stripped-source proof.
- Mark the registry: the value's
status,lowers(the module that makes it) andgodot. - Tests next to the change;
test:criticalandtest:deep:changedbefore the commit.
4. Re-sweep and record the move
cd control && npm run tool-surfaceCompare "Where it stands" and the genre probes with step 1. Write the before and after into the plan's Log. Commit
the regenerated pages with the change; scripts/tool-surface.test.js fails on a stale one.
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.

