make-bot-ui
Skill1 starsChanged 22 days agoMITView on GitHub
Build a local control UI for an existing agent webhook receiver, optionally exposed on Tailscale.
20 other projects use a version of this, 14 of them edited.
Adopted by
Most recently taken up by
- TheVeller/claude-skillsedited, first seen Nov 8, 2026
- requie/endostacktheir own version, first seen Nov 8, 2026
- creedants/pstack-t3their own version, first seen Nov 3, 2026
- dsebban/skillsedited, first seen Nov 1, 2026
- DarthJonathan/guac-skillstheir own version, first seen Nov 1, 2026
- lengjingxu/pstack-for-codexedited, first seen Oct 25, 2026
Used with
Projects with it also use poteto-help.
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.
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 9 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 14
- backnotprop/pstack★ 3.8k11% same
- uzairansaruzi/p3-stack★ 12610% same
- dsebban/skills★ 7111% same
- mariusflorescu/pstack-t3★ 1312% same
- TheVeller/claude-skills★ 411% same
- EvanBatten/pstack-for-cc★ 211% same
- iancleary/skills★ 111% same
- lengjingxu/pstack-for-codex★ 110% same
- 3metaJun/mstack★ 011% same
- ahmedbenaw/pstack★ 010% same
4 more not listed
Wrote their own version · 6
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- creedants/pstack-t3★ 18same name
- requie/endostack★ 4same name
- jmporchet/pstack-hermes★ 2same name
- Timmyy3000/skills★ 2same name
- DarthJonathan/guac-skills★ 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 repository107 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audit-agent-documentationSkill
- automate-meSkill
- babysit-and-shipSkill
- chief-of-staffSkill
- coordinatorSkill
- figure-it-outSkill
- git-guardrailsSkill
- maintain-skillsSkill
- principlesSkill
- pstack-helpSkill
- pstack-modeSkill
- pstack-setupSkill
- recallSkill
- reflectSkill
- retroSkill
- setup-matt-pocock-skillsSkill
- show-me-your-workSkill
- swarmSkill
- usage-reviewSkill
- wizardSkill
- writing-for-agentsSkill
- broSkill
- in-your-own-wordsSkill
- ketchupSkill
- ketchup-videoSkill
- next-optionsSkill
- prSkill
- reply-shapeSkill
- teachSkill
- technical-writingSkill
- unslopSkill
- write-like-meSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- diagnosing-bugsSkill
- implementSkill
- implement-specSkill
- linting-alignmentSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- pstack-tddSkill
- setup-agent-sign-inSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- statechartSkill
- tddSkill
- typescript-best-practicesSkill
- update-dependenciesSkill
- architectSkill
- arenaSkill
- codebase-designSkill
- design-prototypeSkill
- domain-modelingSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- howSkill
- improve-codebase-architectureSkill
- The first 60 shown.
The file
Files
Make a webhook control UI
- Identify an existing receiver and read its documented request, authentication, and success contracts. Confirm which event starts agent work and how delivery can be observed. If no receiver exists, report that prerequisite and stop this integration path. Complete when the endpoint contract is known without inventing a Codex or Claude webhook service.
- Define the UI's small action schema and the receiver's allowed operations. Treat request bodies as untrusted data. Obtain credentials through the environment's existing secure mechanism and keep them server-side. Do not put the credential in the browser, in chat, or in this skill. Do not print the value. Do not log the value. Complete when input validation, authorization, and credential storage are concrete.
- Build a UI and local server-side proxy using the repository's stack. Bind to localhost by default. Follow the receiver's actual headers, timeout, idempotency, and retry contract; never treat an arbitrary HTTP 200 as proof that work started. Do not send media bytes on the webhook. Complete when browser requests reach only the local proxy and the proxy follows the documented receiver protocol.
- Verify with a harmless supported event or a contract fixture, then inspect the corresponding delivery or execution evidence. Preserve failures visibly; a durable retry queue is appropriate only when the receiver can actually drain or acknowledge it. Complete when the claimed delivery behavior has evidence and any real-service gap is stated.
- Expose the UI through Tailscale only when requested. Reuse an existing node, inspect the available CLI, and follow current documented setup if a node is needed. Do not create a second hostname on a node that is already online. Bind the server to
0.0.0.0:<port>, not127.0.0.1, for this exposure. Tailscale peers cannot reach a localhost-only bind. When setup prints a login URL, send that URL to the user. The user approves the machine in the browser. Do not ask for Tailscale credentials. Do not type them. If the login URL expires, runtailscale upagain and send the new URL. Give the user bothhttp://<hostname>.<tailnet>.ts.net:<port>andhttp://<100.x.x.x>:<port>. Use HTTP. Do not add HTTPS unless the user asks. Complete when the requested URL is reachable from the intended network and its access boundary is clear.
Return local URLs, the action contract, delivery evidence, and remaining prerequisites. Provide additional network URLs only for exposure the user requested.
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.

