how
Skill0 starsChanged 5 days agoMITView on GitHub
Use when the user asks how something works, wants a walkthrough, or asks who owns a layer or how layers fit together. Answers in chat; writes no tickets or code. Questions about why it was built this way go to why.
90 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- Loner1024/skillstheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- tristanphvn/keeltheir own version, first seen Nov 8, 2026
Used with
Projects with it also use setup-pstack, ketchup-video and 10 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
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 13 projects that use this
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 28 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
drafaelSkillin-your-own-words
Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.
Also in 26 projects that use this
Other versions90 projects use a version of this.
Word for word · 1
- Gabriel-Lafrance/Skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 89
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- backnotprop/pstack★ 3.8ksame name
- poteto/how★ 878same name
- moeru-ai/xsai★ 667same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- dsebban/skills★ 71same name
79 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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyzeSkill
- ask-gabrielSkill
- babysit-prSkill
- councilSkill
- gabriel-modeSkill
- grill-meSkill
- hillclimbSkill
- review-loopSkill
- reviewSkill
- rulesSkill
- setup-gabriel-skillsSkill
- takeover-prSkill
- taskSkill
- test-auditSkill
- verificationSkill
- whySkill
- write-ticketSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 88 edited versions we read keep these.
1
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 24
Read only. Do not edit code, open a ticket, or start /task.
- Distinctive: line 26
Use the shared roles and selection policy: explorers gather evidence.
“Common” is measured: kept by at least 6 in 10 of the 88 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
How
Answer "how does X work?" with the mental model a senior would give on day one. Not annotated source.
/why answers why it is this way. /analyze writes the broader memo (a bug, an idea, impact, an execution seed). This skill does not write tickets or code, and it does not start a build. The selected execution skill owns any later build.
The section shape is adapted from poteto's pstack /how (MIT). The steps below are this pack's.
Read when
- About to search the repo or read large files? Open main-context.md. Skip it and the walkthrough drowns in file dumps.
- About to describe layers, ownership, or a public API? Open code-quality.md and code-structure.md. Skip them and the model copies a messy layout.
- About to reply? Open Plain language and Unslop. Skip them and the walkthrough reads like a tour script.
- About to ask the user anything? Open Asking the user. Skip it and you ask what the repo already answers.
Contract
- Read only. Do not edit code, open a ticket, or start
/task. - Judgment stays in this chat. Bulk reading goes to readonly explorers that return a short result.
- Use the shared roles and selection policy: explorers gather evidence; analyzers synthesize only as deeply as the actual uncertainty requires. Routine lookups do not require a strong reasoning model.
Process
- Name the thing: a flow, a module, or a request path. If two targets fit, ask once which one, with a recommendation.
- Judge simple or complex before reading widely.
- Simple: one cohesive path, a few files, one owner. One readonly pass in this chat, with narrow reads. No explorer.
- Complex: several layers, several owners, or a path you cannot hold in one pass. Launch 2 to 4 readonly explorers in parallel. Ask each for paths, symbols, and a short note. Synthesize here. When the harness has no subagent, do the same pass as narrow reads, one area at a time, then synthesize once.
- Standalone, write the sections below. Lead with the model. Do not paste source as the answer. Nested, follow nested capabilities: return only the requested flow, owners, source pointers, and uncertainty. Give explorers the parent's locked outcome, bounded question, existing evidence, and stopping condition; reuse existing scouts instead of duplicating the investigation. The parent owns design synthesis.
Answer
Overview
What it does, who calls it, and what it returns or changes. A few sentences.
Key concepts
The few nouns a newcomer must have. One sentence each.
How it works
The path, in order. Name the modules. A small Mermaid diagram when the path has more than two hops.
Where things live
Paths and the job of each. Who owns the public API, and what callers must not import.
Gotchas
Traps that are real in this code: ordering, a caller that defeats a rule, a name that lies. If there are none, say there are none.
Anti-patterns
- Annotated source in place of the model
- A second build loop
- Inventing a layer the code does not have
- Launching explorers for a one-file path
- Writing a ticket or editing code
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.

