principle-never-block-on-the-human
Skill1 starsChanged 14 days agoMITView on GitHub
Apply when tempted to stop and ask 'should I do X?' during reversible analysis work, such as writing a query, adding a cleaning step, choosing a bin width, or drafting a chart. Proceed with a reasonable choice, state it, and let the human correct it afterward.
52 other projects use a version of this, 48 of them edited.
Adopted by
Most recently taken up by
- 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
- B16B1RD/bb-writtheir own version, 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 19 projects that use this
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 11 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 18 projects that use this
Other versions52 projects use a version of this.
Word for word · 0
None found.
Edited · 48
- backnotprop/pstack★ 4.2k21% same
- jtaroreh/agystack★ 12812% same
- uzairansaruzi/p3-stack★ 12616% same
- Dimon94/dverity★ 10721% same
- Dimon94/skills★ 10721% same
- dsebban/skills★ 7121% same
- painhardcore/pstack★ 2222% same
- creedants/pstack-t3★ 1822% same
- mariusflorescu/pstack-t3★ 1321% same
- Scino/fstack★ 1321% same
38 more not listed
Wrote their own version · 4
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- requie/endostack★ 4same name
- jaydubya818/MissionControl★ 2same name
- B16B1RD/bb-writ★ 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-build-the-leverSkill
- 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-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
Files
Never Block on the Human
The human supervises asynchronously. Keep the work unblocked. Make a reasonable decision, proceed, and let the human course-correct after the fact. Queries, scripts, and charts are reversible and reviewable, so a wrong default usually costs less than a stalled session.
- Proceed, then present. Write the analysis, prove it on synthetic data, and hand over one run request with the decisions behind it: the time window, the exclusions, and the metric definition. Do not ask "should I use 28 days?" Use 28 days, say so, and offer the alternative.
- Make the pipeline self-healing where it is safe. When a check fails, log it and fix it in the next round.
- Irreversible actions still need explicit confirmation. These are writes to a shared warehouse or production table, changes to a scheduled job, deletes, and sending results to people outside the session. Prefer a dry run or a compile step first.
- Reversible actions proceed without blocking. These are files in the repo, notebooks, charts, scripts, and runs on synthetic data.
- A run on real data is the human's step, and it is the one wait you accept. Make it cheap. Batch every check and every option the next decision needs into one run request, so the human runs once instead of answering a string of questions.
- Product direction comes from the human. Which question matters, and which metric the business owns, is theirs to decide. Execution should not wait on 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.

