hill-climb
Skill2 starsChanged 35 days agoMITView on GitHub
Improves a plan, design, code or skill in graded rounds: fresh reviewers grade fixed properties 0 to 10, the author revises, and a script decides when to stop. Use when asked to hill-climb, iterate to a better version or improve something in rounds.
11 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- MichaelLeeHobbs/skillstheir own version, first seen Nov 16, 2026
- tunnckoCore/skillstheir own version, first seen Nov 16, 2026
- malinskibeniamin/skillstheir own version, first seen Nov 16, 2026
- lennoxsaint/Skillstheir own version, first seen Nov 15, 2026
- richard-better/skillstheir own version, first seen Nov 15, 2026
- Enjoyoer/loadouttheir own version, first seen Nov 8, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- niksavis/basicly★ 297% same
Wrote their own version · 10
- Bil0000/Hill-Climb★ 137same name
- skillberry-ai/cap-evolve★ 70same name
- lennoxsaint/Skills★ 48same name
- malinskibeniamin/skills★ 4same name
- tunnckoCore/skills★ 2same name
- jpoindexter/ai-agent-skills★ 1same name
- MichaelLeeHobbs/skills★ 1same name
- richard-better/skills★ 1same name
- salalaslam/skills★ 1same name
- Enjoyoer/loadout★ 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.
In this repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- best-practices-auditSkill
- catalog-authoringSkill
- cli-toolsSkill
- conventional-commitsSkill
- councilSkill
- decompose-planSkill
- falsify-firstSkill
- find-skillsSkill
- harness-clientSkill
- harness-loopSkill
- hill-climbSkill
- interface-factsSkill
- no-commentsSkill
- nodeSkill
- plain-englishSkill
- pythonSkill
- release-processSkill
- repair-in-placeSkill
- retention-probeSkill
- root-causeSkill
- session-finishSkill
- skill-creatorSkill
- swarmSkill
- test-disciplineSkill
- tier-injectionSkill
- validate-as-consumerSkill
- work-trackerSkill
- worktree-isolationSkill
- wslSkill
- best-practices-auditSkill
- catalog-authoringSkill
- cli-toolsSkill
- conventional-commitsSkill
- councilSkill
- decompose-planSkill
- falsify-firstSkill
- find-skillsSkill
- harness-clientSkill
- harness-loopSkill
- interface-factsSkill
- no-commentsSkill
- nodeSkill
- plain-englishSkill
- pythonSkill
- release-processSkill
- repair-in-placeSkill
- retention-probeSkill
- root-causeSkill
- session-finishSkill
- skill-creatorSkill
- swarmSkill
- test-disciplineSkill
- tier-injectionSkill
- validate-as-consumerSkill
- work-trackerSkill
- worktree-isolationSkill
- wslSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
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
- Very specific: line 22
Record: Put the round's replies in a new folder DIR/rN and run:
- Distinctive: line 30
Follow measurements for the manifest and its limits.
- Distinctive: line 46
Ask the user only after the climb, unless a finding needs a fact only the user has.
“Common” is measured: kept by at least 6 in 10 of the 11 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
<!-- Generated by `basicly skills-build` from skill.yaml. Do not edit; edit the source. -->Hill Climb
Improve one artifact in graded rounds until the grades stop rising. This skill uses the swarm steps; read that skill first.
The script is ${CLAUDE_SKILL_DIR}/../swarm/scripts/swarm.py, in the swarm skill folder beside this one. DIR is a new folder per climb in the session scratchpad.
Steps
Round 0. Choose 3 to 9 properties from property sets, a subset or your own, named in lowercase with hyphens. Write one line per property that says what a 10 means. Start the state:
python3 -B ${CLAUDE_SKILL_DIR}/../swarm/scripts/swarm.py climb-init --state DIR/climb.json --properties coverage,done-states,poka-yoke- Grade. Save the version as
DIR/vN, where N is the graded round, starting at 1, and run theswarmsteps Brief, Launch, Collect and Verify on it with 3 to 6 lenses, at least one not used in the last round. Each brief's rubric holds the line per property that says what a 10 means; each reply holdslens,gradesfor every property andfindings.climb-roundreplaces the swarm Check. Record. Put the round's replies in a new folder
DIR/rNand run:python3 -B ${CLAUDE_SKILL_DIR}/../swarm/scripts/swarm.py climb-round --state DIR/climb.json --lenses a,b,c --dir DIR/rN --refuted 0Set
--refutedto the number of important findings Verify refuted. Supply host usage with--usage DIR/rN/usage.jsonwhen available. Follow measurements for the manifest and its limits. Missing usage stays unknown. The script prints the decision, grades, finding counts and reported usage. Rounds lists the existing stop rules and refusals.- Revise or stop. On continue, revise the artifact from the findings, note what changed, and go to step 2. On stop, report.
- Report. Give the final version, changes, grades, finding counts, reported usage and open decisions. Name which verified finding or unresolved decision each revision addressed. Give one recommendation for each open decision. Report missing measurements and cost estimates explicitly.
Rules
- Grades and citation counts do not prove usefulness or consumer readiness. Verify findings through the existing swarm steps.
- The author never grades its own version. Grades come only from reviewer replies.
- The properties stay the same after round 0. For a new property, start a new climb.
- The script owns the stop rule. Run past a stop only when the user asks, with
--past-stopon each extra round, and say so in the report. - Ask the user only after the climb, unless a finding needs a fact only the user has. The user's request for a climb approves its reviewer and Verify agents; run them in batches of at most 8.
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.

