principle-build-the-lever
Skill1 starsChanged 14 days agoMITView on GitHub
Apply to any non-trivial analysis or data work: bulk edits, notebook conversions, backfills, reconciliations, and checks. Build the script or query that does the work or proves it, so a reviewer can rerun it instead of trusting a hand-done result.
53 other projects use a version of this, 50 of them edited.
Adopted by
Most recently taken up by
- gfunc/skillsedited, first seen Nov 16, 2026
- shiwenbin1617/pstackedited, first seen Nov 16, 2026
- Dimon94/dverityedited, first seen Nov 15, 2026
- Dimon94/skillsedited, first seen Nov 15, 2026
- backnotprop/pstackedited, first seen Nov 15, 2026
- sammyjoyce/prime-pstackedited, first seen Nov 15, 2026
Used with
Projects with it also use setup-pstack, poteto-help and 4 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.
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 25 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 18 projects that use this
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 10 projects that use this
JoshueOsunaSkillPoteto Mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Also in 3 projects that use this
instructureSkillketchup
Rebuild context after /clear by analyzing uncommitted changes across Canvas LMS and all plugin repositories
Also in 17 projects that use this
Other versions53 projects use a version of this.
Word for word · 0
None found.
Edited · 50
- backnotprop/pstack★ 4.2k21% same
- jtaroreh/agystack★ 12818% same
- uzairansaruzi/p3-stack★ 12620% same
- Dimon94/dverity★ 10721% same
- Dimon94/skills★ 10721% same
- dsebban/skills★ 7121% same
- painhardcore/pstack★ 2221% same
- creedants/pstack-t3★ 1821% same
- mariusflorescu/pstack-t3★ 1321% same
- Scino/fstack★ 1320% same
40 more not listed
Wrote their own version · 3
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- requie/endostack★ 4same name
- 3metaJun/mstack★ 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 repository50 other files it gives its agents.
- analyst-modeSkill
- architectSkill
- arenaSkill
- astack-helpSkill
- benchmark-checklistSkill
- blast-radiusSkill
- catch-upSkill
- correctSkill
- create-formal-verification-skillSkill
- figure-it-outSkill
- howSkill
- interrogateSkill
- in-your-own-wordsSkill
- maintain-formal-verification-skillSkill
- no-commentsSkill
- plain-wordsSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-define-the-questionSkill
- principle-encode-lessons-in-structureSkill
- principle-experience-firstSkill
- principle-explain-the-numberSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-guard-the-context-windowSkill
- principle-laziness-protocolSkill
- principle-make-operations-idempotentSkill
- principle-minimize-reader-loadSkill
- principle-model-the-domainSkill
- principle-name-the-estimandSkill
- principle-never-block-on-the-humanSkill
- principle-prove-it-worksSkill
- principle-reproduce-from-clean-stateSkill
- principle-respect-the-grainSkill
- principle-sequence-verifiable-unitsSkill
- principle-simulate-the-methodSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- recallSkill
- reflectSkill
- retail-analyticsSkill
- sharpenSkill
- show-me-your-workSkill
- statechartSkill
- swarmSkill
- tddSkill
- teachSkill
- technical-writingSkill
- unslopSkill
- whySkill
The file
We split this skill into the rules it gives an agent
7 rules. 1 is common, 6 are distinctive, and 0 are very specific to this project.
1
Common
Most of the 53 edited versions we read keep these.
6
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
- could be automatic: a setting could enforce it
- Distinctive: line 8
When the work is not trivial, build the tool that does it or proves it, instead of doing it by hand in a notebook cell.
- Distinctive: line 12
Default to building the lever.
- Distinctive: line 14
Do the first unit on synthetic data to learn the recipe.
- Distinctive: line 15
Use a script for repeated transforms, a generator for repetitive notebooks or report pages, a pinned query file for analysis, and a …
- Common: line 17
When you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch …
- Distinctive: line 18
Commit the lever with git commit when the work outlives the session.
- Distinctive: line 22
If you cite this principle and the diff contains no script, query file, or generator, you did not apply it.
“Common” is measured: kept by at least 6 in 10 of the 53 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
Build the Lever
When the work is not trivial, build the tool that does it or proves it, instead of doing it by hand in a notebook cell.
A script, a SQL query file, a Polars pipeline, or a re-runnable check does the same work the same way every time. A reviewer can read it and rerun it. A result clicked through by hand can only be re-verified by redoing the clicks.
Default to building the lever. Skip it only for trivial work, such as one obvious edit or one glance at a table.
- Do the first unit on synthetic data to learn the recipe. Then script it. Prove the script on synthetic data, including a case it must reject, before the human runs it on real data. Make it safe to rerun.
- Use a script for repeated transforms, a generator for repetitive notebooks or report pages, a pinned query file for analysis, and a re-runnable assertion script for checks.
- A deterministic lever beats fan-out. If one script can process every partition, table, or segment in one pass, hand the human that one script in one run request. Do not hand the same manual check to subagents.
- When you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch fences in one artifact. Keep it outside the write scope of the delegates so they cannot quietly edit the contract.
- Commit the lever with
git commitwhen the work outlives the session. Commit code, queries, and lockfiles. Never commit raw data, credentials, or notebook outputs.
The bar is triviality, not repetition. A one-off analysis still earns a lever when the lever is what makes the number checkable. Per principle-laziness-protocol, build the smallest script that does or proves the job, never a framework. For the check itself, see principle-prove-it-works.
If you cite this principle and the diff contains no script, query file, or generator, you did not apply it.
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.

